Image segmentation is a fundamental task for extracting semantically meaningful regions from an image. The goal is to assign object labels to each image location. Due to image-noise, shortcomings of algorithms and other ambiguities in the images, there is uncertainty in the assigned labels. In multiple application domains, estimates of this uncertainty are important. For example, object segmentation and uncertainty quantification is essential for many medical application, including tumor segmentation for radiation treatment planning. While a Bayesian characterization of the label posterior provides estimates of segmentation uncertainty, Bayesian approaches can be computationally prohibitive for practical applications. On the other hand, typical optimization based algorithms are computationally very efficient, but only provide maximum a-posteriori solutions and hence no estimates of label uncertainty. In this paper, we propose Active Mean Fields (AMF), a Bayesian technique that uses a mean-field approximation to derive an efficient segmentation and uncertainty quantification algorithm. This model, which allows combining any label-likelihood measure with a boundary length prior, yields a variational formulation that is convex. A specific implementation of that model is the Chan--Vese segmentation model (CV), which formulates the binary segmentation problem through Gaussian likelihoods combined with a boundary-length regularizer. Furthermore, the Euler--Lagrange equations derived from the AMF model are equivalent to those of the popular Rudin-Osher-Fatemi (ROF) model for image de-noising. Solutions to the AMF model can thus be implemented by directly utilizing highly-efficient ROF solvers on log-likelihood ratio fields. We demonstrate the approach using synthetic data, as well as real medical images (for heart and prostate segmentations), and on standard computer vision test images.

UR - http://arxiv.org/abs/1501.05680 ER - TY - Generic T1 - AGA: Attribute Guided Augmentation T2 - CVPR Y1 - 2017 A1 - Dixit, Mandar A1 - Kwitt, Roland A1 - Niethammer, Marc A1 - Vasconcelos, Nuno AB -We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data such that an attribute of a synthesized sample is at a desired value or strength. This is particularly interesting in situations where little data with no attribute annotation is available for learning, but we have access to a large external corpus of heavily annotated samples. While prior works primarily augment in the space of images, we propose to perform augmentation in feature space instead. We implement our approach as a deep encoderdecoder architecture that learns the synthesis function in an end-to-end manner. We demonstrate the utility of our approach on the problems of (1) one-shot object recognition in a transfer-learning setting where we have no prior knowledge of the new classes, as well as (2) object-based oneshot scene recognition. As external data, we leverage 3D depth and pose information from the SUN RGB-D dataset. Our experiments show that attribute-guided augmentation of high-level CNN features considerably improves one-shot recognition performance on both problems.

JF - CVPR UR - https://arxiv.org/pdf/1612.02559.pdf ER - TY - JOUR T1 - Brain Extraction from Normal and Pathological Images: A Joint PCA/Image-Reconstruction Approach Y1 - 2017 A1 - X. Han A1 - R. Kwitt A1 - S. Aylward A1 - B. Menze A1 - A. Asturias A1 - P. Vespa A1 - J. Van Horn A1 - M. Niethammer AB -Brain extraction from 3D medical images is a common pre-processing step. A variety of approaches exist, but they are frequently only designed to perform brain extraction from images without strong pathologies. Extracting the brain from images exhibiting strong pathologies, for example, the presence of a brain tumor or of a traumatic brain injury (TBI), is challenging. In such cases, tissue appearance may substantially deviate from normal tissue appearance and hence violates algorithmic assumptions for standard approaches to brain extraction; consequently, the brain may not be correctly extracted.

This paper proposes a brain extraction approach which can explicitly account for pathologies by jointly modeling normal tissue appearance and pathologies. Specifically, our model uses a three-part image de- composition: (1) normal tissue appearance is captured by a statistical appearance model (via principal component analysis (PCA)), (2) pathologies are captured via a total variation term, and (3) the skull and surrounding tissue is captured by a sparsity term. Due to its convexity, the resulting decomposition model allows for efficient optimization. Decomposition and image registration steps are alternated to allow statistical modeling of normal tissue appearance in a fixed atlas coordinate system. As a beneficial side effect, the decomposition model allows for the identification of potentially pathological areas and the reconstruction of a quasi-normal image in atlas space.

We demonstrate the effectiveness of our approach on four datasets: the publicly available IBSR and LPBA40 datasets which show normal image appearance, the BRATS dataset containing imaging with brain tumors, and a dataset containing clinical TBI images. We compare the performance with other popular brain extraction models: ROBEX, BET, BSE and a recently proposed deep learning approach. Our model performs better than these competing approaches on all four datasets. Hence, our approach is an effective method for brain extraction for a wide variety of images with high-quality brain extraction results.

ER - TY - CONF T1 - Compressing Networks with Super Nodes T2 - arXiv Y1 - 2017 A1 - N. Stanely A1 - R. Kwitt A1 - M. Niethammer A1 - P. Mucha AB -Community detection is a commonly used technique for identifying groups in a network based on similarities in connectivity patterns. To facilitate community detection in large networks, we recast the network to be partitioned into a smaller network of 'super nodes', each super node comprising one or more nodes in the original network. To define the seeds of our super nodes, we apply the 'CoreHD' ranking from dismantling and decycling. We test our approach through the analysis of two common methods for community detection: modularity maximization with the Louvain algorithm and maximum likelihood optimization for fitting a stochastic block model. Our results highlight that applying community detection to the compressed network of super nodes is significantly faster while successfully producing partitions that are more aligned with the local network connectivity, more stable across multiple (stochastic) runs within and between community detection algorithms, and overlap well with the results obtained using the full network.

JF - arXiv UR - https://arxiv.org/abs/1706.04110 ER - TY - CONF T1 - Constructing Shape Spaces from a Topological Perspective T2 - Proceedings of the International Conference on Information Processing in Medical Imaging (IPMI) Y1 - 2017 A1 - C. Hofer A1 - R. Kwitt A1 - M. Niethammer A1 - Y. Hoeller A1 - E. Trinka A1 - A. Uhl AB -We consider the task of constructing (metric) shape space(s) from a topological perspective. In particular, we present a generic construction scheme and demonstrate how to apply this scheme when shape is interpreted as the differences that remain after factoring out translation, scaling and rotation. This is achieved by leveraging a recently proposed injective functional transform of 2D/3D (binary) objects, based on persistent homology. The resulting shape space is then equipped with a similarity measure that is (1) by design robust to noise and (2) fulfills all metric axioms. From a practical point of view, analyses of object shape can then be carried out directly on segmented objects obtained from some imaging modality without any preprocessing, such as alignment, smoothing, or landmark selection. We demonstrate the utility of the approach on the problem of distinguishing segmented hippocampi from normal controls vs. patients with Alzheimer's disease in a challenging setup where volume

changes are no longer discriminative.

Inferring topological and geometrical information from data can offer an alternative perspective on machine learning problems. Methods from topological data analysis, e.g., persistent homology, enable us to obtain such information, typically in the form of summary representations of topological features. However, such topological signatures often come with an unusual structure (e.g., multisets of intervals) that is highly impractical for most machine learning techniques. While many strategies have been proposed to map these topological signatures into machine learning compatible representations, they suffer from being agnostic to the target learning task. In contrast, we propose a technique that enables us to input topological signatures to deep neural networks and learn a task-optimal representation during training. Our approach is realized as a novel input layer with favorable theoretical properties. Classification experiments on 2D object shapes and social network graphs demonstrate the versatility of the approach and, in case of the latter, we even outperform the state-of-the-art by a large margin.

JF - arXiv UR - https://arxiv.org/abs/1707.04041 ER - TY - CONF T1 - Efficient Registration of Pathological Images: A Joint PCA/Image-Reconstruction Approach T2 - ISBI Y1 - 2017 A1 - X. Han A1 - X. Yang A1 - S. Aylward A1 - R. Kwitt A1 - M. Niethammer AB -Registration involving one or more images containing pathologies is challenging, as standard image similarity measures and spatial transforms cannot account for common changes due to pathologies. Low-rank/Sparse (LRS) decomposition removes pathologies prior to registration; however, LRS is memory-demanding and slow, which limits its use on larger data sets. Additionally, LRS blurs normal tissue regions, which may degrade registration performance. This paper proposes an efficient alternative to LRS: (1) normal tissue appearance is captured by principal component analysis (PCA) and (2) blurring is avoided by an integrated model for pathology removal and image reconstruction. Results on synthetic and BRATS 2015 data demonstrate its utility.

JF - ISBI ER - TY - CONF T1 - Fast Predictive Multimodal Image Registration T2 - ISBI Y1 - 2017 A1 - X. Yang A1 - R. Kwitt A1 - M. Styner A1 - M. Niethammer AB -We introduce a deep encoder-decoder architecture for image deformation prediction from multimodal images. Specifically, we design an image-patch-based deep network that jointly (i) learns an image similarity measure and (ii) the relationship between image patches and deformation parameters. While our method can be applied to general image registration formulations, we focus on the Large Deformation Diffeomorphic Metric Mapping (LDDMM) registration model. By predicting the initial momentum of the shooting formulation of LDDMM, we preserve its mathematical properties and drastically reduce the computation time, compared to optimization-based approaches. Furthermore, we create a Bayesian probabilistic version of the network that allows evaluation of registration uncertainty via sampling of the network at test time. We evaluate our method on a 3D brain MRI dataset using both T1- and T2-weighted images. Our experiments show that our method generates accurate predictions and that learning the similarity measure leads to more consistent registrations than relying on generic multimodal image similarity measures, such as mutual information. Our approach is an order of magnitude faster than optimization-based LDDMM.

JF - ISBI ER - TY - CONF T1 - Fast Predictive Simple Geodesic Regression T2 - MICCAI Workshop on Deep Learning in Medical Image Analysis (DLMIA) Y1 - 2017 A1 - Z. Ding A1 - G. Fleishman A1 - X. Yang A1 - P. Thompson A1 - R. Kwitt A1 - M. Niethammer A1 - ADNI AB -Analyzing large-scale imaging studies with thousands of images is computationally expensive. To assess localized morphological differences, deformable image registration is a key tool. However, as registrations are costly to compute, large-scale studies frequently require large compute clusters. This paper explores a fast predictive approximation to image registration. In particular, it uses these fast registrations to approximate a simplified geodesic regression model to capture longitudinal brain changes. The resulting approach is orders of magnitude faster than the optimization-based regression approach and hence facilitates large-scale analysis on a single graphics processing unit. We show results on 2D and 3D brain magnetic resonance images from OASIS and ADNI.

JF - MICCAI Workshop on Deep Learning in Medical Image Analysis (DLMIA) ER - TY - JOUR T1 - Fast Predictive Simple Geodesic Regression Y1 - 2017 A1 - Z. Ding A1 - G. Fleishman A1 - X. Yang A1 - P. Thompson A1 - R. Kwitt A1 - M. Niethammer A1 - ADNI AB -Deformable image registration and regression are important tasks in medical image analysis. However, they are computationally expensive, especially when analyzing large-scale datasets that contain thousands of images. Hence, cluster computing is typically used, making the approaches dependent on such computational infrastructure. Even larger computational resources are required as study sizes increase. This limits the use of deformable image registration and regression for clinical applications and as component algorithms for other image analysis approaches. We therefore propose using a fast predictive approach to perform image registrations. In particular, we employ these fast registration predictions to approximate a simplified geodesic regression model to capture longitudinal brain changes. The resulting method is orders of magnitude faster than the standard optimization-based regression model and hence facilitates large-scale analysis on a single graphics processing unit (GPU). We evaluate our results on 3D brain magnetic resonance images (MRI) from the ADNI datasets.

ER - TY - Generic T1 - International Conference on Information Processing in Medical Imaging (IPMI), Boone, North Carolina, USA T2 - Lecture Notes in Computer Science Y1 - 2017 A1 - M. Niethammer A1 - M. Styner A1 - S. Aylward A1 - H. Zhu A1 - I. Oguz A1 - P.-T. Yap A1 - D. Shen AB -This book constitutes the proceedings of the 25th International Conference on Information Processing in Medical Imaging, IPMI 2017, held at the Appalachian State University, Boon, NC, USA, in June 2017.

JF - Lecture Notes in Computer Science PB - Springer VL - 10265 SN - 978-3-319-59050-9 UR - http://www.springer.com/us/book/9783319590493#otherversion=9783319590509 ER - TY - CONF T1 - Orthotropic Thin Shell Elasticity Estimation for Surface Registration T2 - Proceedings of the International Conference on Information Processing in Medical Imaging (IPMI) Y1 - 2017 A1 - Q. Zhao A1 - S. Pizer A1 - R. Alterovitz A1 - M. Niethammer A1 - J. Rosenman AB -Elastic physical models have been widely used to regularize deformations in different medical object registration tasks. Traditional approaches usually assume uniform isotropic tissue elasticity (a constant regularization weight) across the whole domain, which contradicts human tissue elasticity being not only inhomogeneous but also anisotropic. We focus on producing more physically realistic deformations for the task of surface registration. We model the surface as an orthotropic elastic thin shell, and we propose a novel statistical framework to estimate inhomogeneous and anisotropic shell elasticity parameters only from a group of known surface deformations. With this framework we show that a joint estimation of within-patient surface deformations and the shell elasticity parameters can improve groupwise registration accuracy. The method is tested in the context of endoscopic reconstruction-surface registration.

JF - Proceedings of the International Conference on Information Processing in Medical Imaging (IPMI) ER - TY - JOUR T1 - Quicksilver: Fast Predictive Image Registration – A Deep Learning Approach JF - NeuroImage Y1 - 2017 A1 - X. Yang A1 - R. Kwitt A1 - M. Styner A1 - M. Niethammer AB -This paper introduces Quicksilver, a fast deformable image registration method. Quicksilver registration for image-pairs works by patch-wise prediction of a deformation model based directly on image appearance. A deep encoder-decoder network is used as the prediction model. While the prediction strategy is general, we focus on predictions for the Large Deformation Diffeomorphic Metric Mapping (LDDMM) model. Specifically, we predict the momentum-parameterization of LDDMM, which facilitates a patch-wise prediction strategy while maintaining the theoretical properties of LDDMM, such as guaranteed diffeomorphic mappings for sufficiently strong regularization. We also provide a probabilistic version of our prediction network which can be sampled during test time to calculate uncertainties in the predicted deformations. Finally, we introduce a new correction network which greatly increases the prediction accuracy of an already existing prediction network. Experiments are conducted for both atlas-to-image and image-to-image registrations. These experiments show that our method accurately predicts registrations obtained by numerical optimization, is very fast, and achieves state-of-the-art registration results on four standard validation datasets. Quicksilver is freely available as open-source software.

VL - 158 UR - https://arxiv.org/abs/1703.10908 ER - TY - CONF T1 - Regression Uncertainty on the Grassmannian T2 - Proceedings of the AISTATS conference Y1 - 2017 A1 - Y. Hong A1 - X. Yang A1 - R. Kwitt A1 - M. Styner A1 - M. Niethammer AB -Trends in longitudinal or cross-sectional studies over time are often captured through regression models. In their simplest manifestation, these regression models are formulated in Rn. However, in the context of imaging studies, the objects of interest which are to be regressed are frequently best modeled as elements of a Riemannian manifold. Regression on such spaces can be accomplished through geodesic regression. This paper develops an approach to compute confidence intervals for geodesic regression models. The approach is general, but illustrated and specifically developed for the Grassmann manifold, which allows us, e.g., to regress shapes or linear dynamical systems. Extensions to other manifolds can be obtained in a similar manner. We demonstrate our approach for regression with 2D/3D shapes using synthetic and real data.

JF - Proceedings of the AISTATS conference ER - TY - JOUR T1 - The UNC-Wisconsin Rhesus Macaque Neurodevelopment Database: A Structural MRI and DTI Database of Early Postnatal Development JF - Frontiers in Neuroscience Y1 - 2017 A1 - J. T. Young A1 - Y. Shi A1 - M. Niethammer A1 - M. Grauer A1 - C. L. Coe A1 - G. R. Lubach A1 - B. Davis A1 - F. Budin A1 - R. C. Knickmeyer A1 - A. L. Alexander A1 - M. A. Styner AB -Rhesus macaques are commonly used as a translational animal model in neuroimaging and neurodevelopmental research. In this report, we present longitudinal data from both structural and diffusion MRI images generated on a cohort of 34 typically developing monkeys from two weeks to 36 months of age. All images have been manually skull stripped and are being made freely available via an online repository for use by the research community. Additionally, this database will continue to be updated as we process the data, create atlases, and perform fiber tracking on the DTI data.

UR - http://journal.frontiersin.org/article/10.3389/fnins.2017.00029/abstract ER - TY - CONF T1 - The Endoscopogram: a 3D model reconstructed from endoscopic video frames T2 - MICCAI Y1 - 2016 A1 - Q. Zhao A1 - T. Price A1 - S. Pizer A1 - M. Niethammer A1 - R. Alterovitz A1 - J. Rosenman AB -Endoscopy enables high resolution visualization of tissue texture and is a critical step in many clinical workflows, including diagnosis and treatment planning for cancers in the nasopharynx. However, an endoscopic video does not provide 3D spatial information, making it difficult to use in tumor localization, and it is inefficient to review. We introduce a pipeline for automatically reconstructing a textured 3D surface model, which we call an endoscopogram, from multiple 2D endoscopic video frames. Our pipeline first reconstructs a partial 3D surface model for each input individual 2D frame. In the next step (which is the focus of this paper), we generate a single high-quality 3D surface model using a groupwise registration approach that fuses multiple, partially overlapping, incomplete and deformed surface models together. We generate endoscopograms from synthetic, phantom, and patient data and show that our registration approach can account for tissue deformations and reconstruction inconsistency across endoscopic video frames.

JF - MICCAI ER - TY - CONF T1 - Fast Predictive Image Registration T2 - arXiv Y1 - 2016 A1 - X. Yang A1 - R. Kwitt A1 - M. Niethammer AB - We present a method to predict image deformations based on patch-wise image appearance. Specifically, we design a patch-based deep encoder-decoder network which learns the pixel/voxel-wise mapping between image appearance and registration parameters. Our approach can predict general deformation parameterizations, however, we focus on the large deformation diffeomorphic metric mapping (LDDMM) registration model. By predicting the LDDMM momentum-parameterization we retain the desirable theoretical properties of LDDMM, while reducing computation time by orders of magnitude: combined with patch pruning, we achieve a 1500x/66x speed up compared to GPU-based optimization for 2D/3D image registration. Our approach has better prediction accuracy than predicting deformation or velocity fields and results in diffeomorphic transformations. Additionally, we create a Bayesian probabilistic version of our network, which allows evaluation of deformation field uncertainty through Monte Carlo sampling using dropout at test time. We show that deformation uncertainty highlights areas of ambiguous deformations. We test our method on the OASIS brain image dataset in 2D and 3D. JF - arXiv ER - TY - CONF T1 - Memory Efficient LDDMM for Lung CT T2 - MICCAI Y1 - 2016 A1 - T. Polzin A1 - M. Niethammer A1 - M. P. Heinrich A1 - H. Handels A1 - J. Modersitzki AB -In this paper a novel Large Deformation Diffeomorphic Metric Mapping (LDDMM) scheme is presented which has significantly lower computational and memory demands than standard LDDMM but achieves the same accuracy. We exploit the smoothness of velocities and transformations by using a coarser discretization compared to the image resolution. This reduces required memory and accelerates numerical optimization as well as solution of transport equations. Accuracy is essentially unchanged as the mismatch of transformed moving and fixed image is incorporated into the model at high resolution. Reductions in memory consumption and runtime are demonstrated for registration of lung CT images. State-of-the-art accuracy is shown for the challenging DIR-Lab chronic obstructive pulmonary disease (COPD) lung CT data sets obtaining a mean landmark distance after registration of 1.03 mm and the best average results so far.

JF - MICCAI ER - TY - CONF T1 - One-Shot Learning of Scene Categories via Feature Trajectory Transfer T2 - Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) Y1 - 2016 A1 - R. Kwitt A1 - S. Hegenbart A1 - Niethammer, M AB -The appearance of (outdoor) scenes changes considerably with the strength of certain transient attributes, such as ``rainy'', ``dark'' or ``sunny''. Obviously, this also affects the representation of an image in feature space, e.g., as activations at a certain CNN layer, and consequently impacts scene recognition performance. In this work, we investigate the variability in these transient attributes as a rich source of information for studying how image representations change as a function of attribute strength. In particular, we leverage a recently introduced dataset with fine-grain annotations to estimate feature trajectories for a collection of transient attributes and then show how these trajectories can be transferred to new image representations. This enables us to synthesize new data along the transferred trajectories with respect to the dimensions of the space spanned by the transient attributes. Applicability of this concept is demonstrated on the problem of one-shot scene recognition. We show that data synthesized via feature trajectory transfer considerably boosts recognition performance, (1) with respect to baselines and (2) in combination with state-of-the-art approaches in one-shot learning.

JF - Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) N1 -accepted

ER - TY - JOUR T1 - Parametric Regression on the Grassmannian JF - IEEE Transactions on Pattern Analysis and Machine Intelligence Y1 - 2016 A1 - Y. Hong A1 - N. Singh A1 - R. Kwitt A1 - N. Vasconcelos A1 - Niethammer, M AB -We address the problem of fitting parametric curves on the Grassmann manifold for the purpose of intrinsic parametric regression. As customary in the literature, we start from the energy minimization formulation of linear least-squares in Euclidean spaces and generalize this concept to general nonflat Riemannian manifolds, following an optimal-control point of view. We then specialize this idea to the Grassmann manifold and demonstrate that it yields a simple, extensible and easy-to-implement solution to the parametric regression problem. In fact, it allows us to extend the basic geodesic model to (1) a time-warped variant and (2) cubic splines. We demonstrate the utility of the proposed solution on different vision problems, such as shape regression as a function of age, traffic-speed estimation and crowd-counting from surveillance video clips. Most notably, these problems can be conveniently solved within the same framework without any specifically-tailored steps along the processing pipeline.

UR - http://arxiv.org/abs/1505.03832 N1 -\url{http://arxiv.org/abs/1505.03832}

ER - TY - CONF T1 - Registration of Developmental Image Sequences With Missing Data T2 - Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, WBIR Y1 - 2016 A1 - I. Csapo A1 - Y. Shi A1 - M. Sanchez A1 - M. Styner A1 - M. Niethammer JF - Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, WBIR ER - TY - CONF T1 - Registration of Pathological Images T2 - Proceedings of the MICCAI Workshop on Simulation and Synthesis in Medical Imaging (SASHIMI) Y1 - 2016 A1 - X. Yang A1 - X. Han A1 - E. Park A1 - S. Aylward A1 - R. Kwitt A1 - M. Niethammer AB - This paper proposes an approach to improve atlas-to-image registration accuracy with large pathologies. Instead of directly registering an atlas to a pathological image, the method learns a mapping from the pathological image to a quasi-normal image, for which more accurate registration is possible. Specifically, the method uses a deep variational convolutional encoder-decoder network to learn the mapping. Furthermore, the method estimates local mapping uncertainty through network inference statistics and uses those estimates to down-weight the image registration similarity measure in areas of high uncertainty. The performance of the method is quantified using synthetic brain tumor images and images from the brain tumor segmentation challenge (BRATS 2015). JF - Proceedings of the MICCAI Workshop on Simulation and Synthesis in Medical Imaging (SASHIMI) ER - TY - CONF T1 - Ultrasound Spectroscopy T2 - Proceedings of the International Symposium on Biomedical Imaging (ISBI) Y1 - 2016 A1 - S. Aylward A1 - M. McCormick A1 - H. J. Kang A1 - S. Razzaque A1 - R. Kwitt A1 - Niethammer, M AB -We introduce the concept of “Ultrasound Spectroscopy”. The premise of ultrasound spectroscopy is that by acquiring ultrasound RF data at multiple power and frequency settings, a rich set of features can be extracted from that RF data and used to characterize the underlying tissues. This is beneficial for a variety of problems, such as accurate tissue classification, application-specific image generation, and numerousother quantitative tasks. These capabilities are particularly relevant to point-of-care ultrasound (POCUS) applications, where operator experience with ultrasound may be limited. Instead of displaying B-mode images, a POCUS application using ultrasound spectroscopy can, for example, automatically detect internal abdominal bleeding. In this paper, we present ex vivo tissue phantom studies to demonstrate the accuracy of ultrasound spectroscopy over previous approaches. Our studies suggest that ultrasound spectroscopy provides exceptional accuracy and informative features for classifying blood versus other tissues across image locations and body habitus.

JF - Proceedings of the International Symposium on Biomedical Imaging (ISBI) N1 -accepted

ER - TY - JOUR T1 - Appearance Normalization of Histology Slides JF - Computerized Medical Imaging and Graphics Y1 - 2015 A1 - J. Vicory A1 - H. D. Couture A1 - N.E. Thomas A1 - D. Borland A1 - J.S. Marron A1 - J. Woosley A1 - Niethammer, M AB -This paper presents a method for automatic color and intensity normalization of digitized histology slides stained with two different agents. In comparison to previous approaches, prior information on the stain vectors is used in the plane estimation process, resulting in improved stability of the estimates. Due to the prevalence of hematoxylin and eosin staining for histology slides, the proposed method has significant practical utility. In particular, it can be used as a first step to standardize appearance across slides and is effective at countering effects due to differing stain amounts and protocols and counteracting slide fading. The approach is validated against non-prior plane-fitting using synthetic experiments and 13 real datasets. Results of application of the method to adjustment of faded slides are given, and the effectiveness of the method in aiding statistical classification is shown.

ER - TY - JOUR T1 - Diseased Region Detection of Longitudinal Knee Magnetic Resonance Imaging Data JF - IEEE Transactions on Medical Imaging Y1 - 2015 A1 - C. Huang A1 - L. Shan A1 - H. C. Charles A1 - W. Wirth A1 - Niethammer, M A1 - H. Zhu AB -Magnetic resonance imaging (MRI) has become an important imaging technique for quantifying the spatial location and magnitude/direction of longitudinal cartilage morphology changes in patients with osteoarthritis (OA). Although several analytical methods, such as subregion-based analysis, have been developed to refine and improve quantitative cartilage analyses, they can be suboptimal due to two major issues: the lack of spatial correspondence across subjects and time and the spatial heterogeneity of cartilage progression across subjects. The aim of this paper is to present a statistical method for longitudinal cartilage quantification in OA patients, while addressing these two issues. The 3D knee image data is preprocessed to establish spatial correspondence across subjects and/or time. Then, a Gaussian hidden Markov model (GHMM) is proposed to deal with the spatial heterogeneity of cartilage progression across both time and OA subjects. To estimate unknown parameters in GHMM, we employ a pseudo-likelihood function and optimize it by using an expectation-maximization (EM) algorithm. The proposed model can effectively detect diseased regions in each OA subject and present a localized analysis of longitudinal cartilage thickness within each latent subpopulation. Our GHMM integrates the strengths of two standard statistical methods including the local subregion-based analysis and the ordered value approach. We use simulation studies and the Pfizer longitudinal knee MRI dataset to evaluate the finite sample performance of GHMM in the quantification of longitudinal cartilage morphology changes. Our results indicate that GHMM significantly outperforms several standard analytical methods.

ER - TY - CONF T1 - Group testing for longitudinal data T2 - International Conference on Information Processing in Medical Imaging (IPMI) Y1 - 2015 A1 - Y. Hong A1 - N. Singh A1 - R. Kwitt A1 - Niethammer, M AB - We consider how to test for group differences of shapes given longitudinal data. In particular, we are interested in differences of longitudinal models of each group’s subjects. We introduce a generalization of principal geodesic analysis to the tangent bundle of a shape space. This allows the estimation of the variance and principal directions of the distribution of trajectories that summarize shape variations within the longitudinal data. Each trajectory is parameterized as a point in the tangent bundle. To study statistical differences in two distributions of trajectories, we generalize the Bhattacharyya distance in Euclidean space to the tangent bundle. This not only allows to take second-order statistics into account, but also serves as our test-statistic during permutation testing. Our method is validated on both synthetic and real data, and the experimental results indicate improved statistical power in identifying group differences. In fact, our study sheds new light on group differences in longitudinal corpus callosum shapes of subjects with dementia versus normal controls. JF - International Conference on Information Processing in Medical Imaging (IPMI) ER - TY - CONF T1 - Hierarchical Task-Driven Feature Learning for Tumor Histology T2 - International Symposium on Biomedical Imaging (ISBI) Y1 - 2015 A1 - H. D. Couture A1 - J.S. Marron A1 - N.E. Thomas A1 - C. M. Perou A1 - Niethammer, M AB -Through learning small and large-scale image features, we can capture the local and architectural structure of tumor tissue from histology images. This is done by learning a hierarchy of dictionaries using sparse coding, where each level captures progressively larger scale and more abstract properties. By optimizing the dictionaries further using class labels, discriminating properties of classes that are not easily visually distinguishable to pathologists are captured. We explore this hierarchical and task-driven model in classifying malignant melanoma and the genetic subtype of breast tumors from histology images. We also show how interpreting our model through visualizations can provide insight to pathologists.

JF - International Symposium on Biomedical Imaging (ISBI) ER - TY - JOUR T1 - Low-rank atlas image analyses in the presence of pathologies JF - IEEE Transactions on Medical Imaging Y1 - 2015 A1 - X. Liu A1 - Niethammer, M A1 - R. Kwitt A1 - M. McCormick A1 - S. Aylward AB -We present a common framework, for registering images to an atlas and for forming an unbiased atlas, that tolerates the presence of pathologies such as tumors and traumatic brain injury lesions. This common framework is particularly useful when a sufficient number of protocol-matched scans from healthy subjects cannot be easily acquired for atlas formation and when the pathologies in a patient cause large appearance changes. Our framework combines a low-rank-plus-sparse image decomposition technique with an iterative, diffeomorphic, group-wise image registration method. At each iteration of image registration, the decomposition technique estimates a ``healthy" version of each image as its low-rank component and estimates the pathologies in each image as its sparse component. The healthy version of each image is used for the next iteration of image registration. The low-rank and sparse estimates are refined as the image registrations iteratively improve. When that framework is applied to image-to-atlas registration, the low-rank image is registered to a pre-defined atlas, to establish correspondence that is independent of the pathologies in the sparse component of each image. Ultimately, image-to-atlas registrations can be used to define spatial priors for tissue segmentation and to map information across subjects. When that framework is applied to unbiased atlas formation, at each iteration, the average of the low-rank images from the patients is used as the atlas image for the next iteration, until convergence. Since each iteration's atlas is comprised of low-rank components, it provides a population-consistent, pathology-free appearance. Evaluations of the proposed methodology are presented using synthetic data as well as simulated and clinical tumor MRI images from the brain tumor segmentation (BRATS) challenge from MICCAI 2012.

N1 -accepted for publication

ER - TY - CONF T1 - Model Criticism for Regression on the Grassmannian T2 - MICCAI Y1 - 2015 A1 - Y. Hong A1 - R. Kwitt A1 - Niethammer, M AB -Reliable estimation of model parameters from data requires a suitable model. In this work, we investigate and extend a recent model criticism approach to evaluate regression models on the Grassmann manifold. Model criticism allows us to check if a model fits and if the underlying model assumptions are justified by the observed data. This is a critical step to check model validity which is often neglected in practice. Using synthetic data we demonstrate that the proposed model criticism approach can indeed reject models that are improper for observed data and that the approach can guide the model selection process. We study two real applications: degeneration of corpus callosum shapes during aging and developmental shape changes in the rat calvarium. Our experimental results suggest that the three tested regression models on the Grassmannian (equivalent to linear, time-warped, and cubic-spline regression in R^n, respectively) can all capture changes of the corpus callosum, but only the cubic-spline model is appropriate for shape changes of the rat calvarium. While our approach is developed for the Grassmannian, the principles are applicable to smooth manifolds in general.

JF - MICCAI ER - TY - JOUR T1 - Quantitative assessment of the upper airway in infants and children with subglottic stenosis JF - The Laryngoscope Y1 - 2015 A1 - C. J. Zdanski A1 - S. D. Davis A1 - Y. Hong A1 - D. Miao A1 - C. Quammen A1 - S. Mitran A1 - B. Davis A1 - Niethammer, M A1 - J. S. Kimbell A1 - E. Pitkin A1 - J. Fine A1 - L. Fordham A1 - B. Vaughn A1 - R. Superfine AB -OBJECTIVES: Determine whether geometric measures and computational fluid dynamic modeling (CFD) derived from medical imaging are effective diagnostic and treatment planning tools for pediatric subglottic stenosis (SGS). STUDY DESIGN: Retrospective chart and imaging review. SETTING: Tertiary Care Hospital SUBJECTS AND METHODS: CT scans of children (n=17) with SGS were analyzed by geometric and (CFD) methods. Polysomnograms (n=15) were also analyzed. CT’s were also analyzed by age/weight flow normalization and comparison to an Atlas created from normal CT’s. Five geometric, seven CFD, and five PSG measures were analyzed to determine their correlation with which patients received surgery subsequent to the CT/PSG dataset versus those who did not. Statistical analysis was performed using a two-sample t-test with Bonferroni correction and area under the curve analysis. RESULTS: Two geometric indices and one CFD measure were significant for determining which children with SGS received surgery. Polysomnography was less helpful in this determination. Optimal cutoffs for these values were determined from this dataset. CONCLUSIONS: A number of geometric and CFD variables were sensitive at determining which patients with SGS received surgical intervention versus those who did not. Polysomnography was less helpful in making this determination. Discrete, quantitative assessment of the pediatric airway was performed, yielding preliminary data regarding possible objective thresholds for surgical versus non-surgical treatment of disease. This study is limited by its small, retrospective, single institution nature; further studies to validate these findings and possibly optimize treatment threshold recommendations are warranted.

ER - TY - JOUR T1 - Robust estimation of group-wise cortical correspondence with an application to macaque and human neuroimaging studies JF - Frontiers in Neuroscience Y1 - 2015 A1 - I. Lyu A1 - S. H. Kim A1 - J.-K. Seong A1 - S. W. Yoo A1 - A. Evans A1 - Y. Shi A1 - M. Sanchez A1 - Niethammer, M A1 - M. A. Styner AB -We present a novel group-wise registration method for cortical correspondence for local cortical thickness analysis in human and non-human primate neuroimaging studies. The proposed method is based on our earlier template based registration that estimates a continuous, smooth deformation field via sulcal curve-constrained registration employing spherical harmonic decomposition of the deformation field. This pairwise registration though results in a well-known template selection bias, which we aim to overcome here via a group-wise approach. We propose the use of an unbiased ensemble entropy minimization following the use of the pairwise registration as an initialization. An individual deformation field is then iteratively updated onto the unbiased average. For the optimization, we use metrics specific for cortical correspondence though all of these are straightforwardly extendable to the generic setting: The first focused on optimizing the correspondence of automatically extracted sulcal landmarks and the second on that of sulcal depth property maps. We further propose a robust entropy metric and a hierarchical optimization by employing spherical harmonic basis orthogonality. We also provide the detailed methodological description of both our earlier work and the proposed method with a set of experiments on a population of human and non-human primate subjects. In the experiment, we have shown that our method achieves superior results on consistency through quantitative and visual comparisons as compared to the existing methods.

VL - 9 N1 -\url{http://dx.doi.org/10.3389/fnins.2015.00210}

ER - TY - CONF T1 - Semi-Coupled Dictionary Learning for Deformation Prediction T2 - International Symposium on Biomedical Imaging (ISBI) Y1 - 2015 A1 - T. Cao A1 - N. Singh A1 - V. Jojic A1 - Niethammer, M AB -We propose a coupled dictionary learning method to predict deformation fields based on image appearance. Rather than estimating deformations by standard image registration methods, we investigate how to obtain a basis of the space of deformations. In particular, we explore how image appearance differences with respect to a common atlas image can be used to predict deformations represented by such a basis. We use a coupled dictionary learning method to jointly learn a basis for image appearance differences and their related deformations. Our proposed method is based on local image patches. We evaluate our method on synthetically generated datasets as well as on a structural magnetic resonance brain imaging (MRI) dataset. Our method results in an improved prediction accuracy while reducing the search space compared to nearest neighbor search and demonstrates that learning a deformation basis is feasible.

JF - International Symposium on Biomedical Imaging (ISBI) ER - TY - JOUR T1 - Shape Analysis Based on Depth-Ordering JF - Medical Image Analysis Y1 - 2015 A1 - Hong, Yi A1 - Gao, Yi A1 - Niethammer, Marc A1 - Bouix, Sylvain AB -In this paper we propose a new method for shape analysis based on the ordering of shapes using band-depth. We use this band-depth to non-parametrically define a global depth for a shape with respect to a reference population, typically consisting of normal control subjects. This allows us to globally quantify differences with respect to “normality”. Using the depth-ordering of shapes also allows the detection of localized shape differences by using α-central values of shapes. We propose permutation tests to statistically assess global and local shape differences. We further determine the directionality of shape differences (local inflation versus deflation). The method is evaluated on a synthetically generated striatum dataset, and applied to detect shape differences in the hippocampus between subjects with first-episode schizophrenia and normal controls.

PB - Elsevier ER - TY - JOUR T1 - Splines for Diffeomorphisms JF - Medical Image Analysis Y1 - 2015 A1 - Singh, Nikhil A1 - Vialard, François-Xavier A1 - Niethammer, Marc AB -This paper develops a method for higher order parametric regression on diffeomorphisms for image regression. We present a principled way to define curves with nonzero acceleration and nonzero jerk. This work extends methods based on geodesics which have been developed during the last decade for computational anatomy in the large deformation diffeomorphic image analysis framework. In contrast to previously proposed methods to capture image changes over time, such as geodesic regression, the proposed method can capture more complex spatio-temporal deformations. We take a variational approach that is governed by an underlying energy formulation, which respects the nonflat geometry of diffeomorphisms. Such an approach of minimal energy curve estimation also provides a physical analogy to particle motion under a varying force field. This gives rise to the notion of the quadratic, the cubic and the piecewise cubic splines on the manifold of diffeomorphisms. The variational formulation of splines also allows for the use of temporal control points to control spline behavior. This necessitates the development of a shooting formulation for splines. The initial conditions of our proposed shooting polynomial paths in diffeomorphisms are analogous to the Euclidean polynomial coefficients. We experimentally demonstrate the effectiveness of using the parametric curves both for synthesizing polynomial paths and for regression of imaging data. The performance of the method is compared to geodesic regression.

PB - Elsevier ER - TY - CONF T1 - Statistical Topological Data Analysis – A Kernel Perspective T2 - NIPS Y1 - 2015 A1 - R. Kwitt A1 - U. Bauer A1 - S. Huber A1 - Niethammer, M A1 - W. Lin AB -We consider the problem of statistical computations with persistence diagrams, a summary representation of topological features in data. These diagrams encode persistent homology, a widely used invariant in topological data analysis. While several avenues towards a statistical treatment of the diagrams have been explored recently, we follow an alternative route that is motivated by the success of methods based on the embedding of probability measures into reproducing kernel Hilbert spaces. In fact, a positive definite kernel on persistence diagrams has recently been proposed, connecting persistent homology to popular kernel-based learning techniques such as support vector machines. However, important properties of that kernel which would enable a principled use in the context of probability measure embeddings remain to be explored. Our contribution is to close this gap by proving universality of a variant of the original kernel, and to demonstrate its effective use in two-sample hypothesis testing on synthetic as well as real-world data.

JF - NIPS UR - http://papers.nips.cc/paper/5887-statistical-topological-data-analysis-a-kernel-perspective N1 -accepted

ER - TY - CONF T1 - Surface Registration in the Presence of Missing Patches and Topology Change T2 - Proceedings of the Medical Image Understanding and Analysis Conference Y1 - 2015 A1 - Q. Zhao A1 - T. Price A1 - S. Pizer A1 - Niethammer, M A1 - R. Alterovitz A1 - J. Rosenman AB -The fusion between an endoscopic movie and a CT poses a special surface registration problem. The surface extracted from CT is complete and accurate, whereas the surface extracted from endoscopy suffers from serious missing patches and topology change. We propose a surface registration method, Thin Shell Demons, that is robust under these two situations. Motivated by Thirion’s Demons idea, the partial surface can provide virtual forces to attract the complete surface, which is equipped with a novel physics-based deformation energy. This energy can help preserve the correct surface topology while producing realistic deformation for the regions that don’t have any attracting counterpart regions. The attraction direction assures the deformation is not affected by the surface completeness. Moreover, we propose to use geometric feature matching for computing virtual forces to handle inaccurate 3D point positions and large deformations. We test our method for CT/endoscope fusion and show its potential to achieve successful registration.

JF - Proceedings of the Medical Image Understanding and Analysis Conference ER - TY - CONF T1 - Uncertainty Quantification for LDDMM Using a Low-rank Hessian Approximation T2 - MICCAI Y1 - 2015 A1 - X. Yang A1 - Niethammer, M AB -This paper presents an approach to estimate the uncertainty of registration parameters for the large displacement diffeomorphic metric mapping (LDDMM) registration framework. Assuming a local multivariate Gaussian distribution as an approximation for the registration energy at the optimal registration parameters, we propose a method to approximate the covariance matrix as the inverse of the Hessian of the registration energy to quantify registration uncertainty. In particular, we make use of a low-rank approximation to the Hessian to accurately and efficiently estimate the covariance matrix using few eigenvalues and eigenvectors. We evaluate the uncertainty of the LDDMM registration results for both synthetic and real imaging data.

JF - MICCAI ER - TY - JOUR T1 - Automatic Atlas-based Three-label Cartilage Segmentation from MR Knee Images JF - Medical Image Analysis Y1 - 2014 A1 - L. Shan A1 - Zach, C A1 - C. Charles A1 - Niethammer, M AB -Osteoarthritis (OA) is the most common form of joint disease and often characterized by cartilage changes. Accurate quantitative methods are needed to rapidly screen large image databases to assess changes in cartilage morphology. We therefore propose a new automatic atlas-based cartilage segmentation method for future automatic OA studies. Atlas-based segmentation methods have been demonstrated to be robust and accurate in brain imaging and therefore also hold high promise to allow for reliable and high-quality segmentations of cartilage. Nevertheless, atlas-based methods have not been well explored for cartilage segmentation. A particular challenge is the thinness of cartilage, its relatively small volume in comparison to surrounding tissue and the difficulty to locate cartilage interfaces -- for example the interface between femoral and tibial cartilage. This paper focuses on the segmentation of femoral and tibial cartilage, proposing a multi-atlas segmentation strategy with non-local patch-based label fusion which can robustly identify candidate regions of cartilage. This method is combined with a novel three-label segmentation method which guarantees the spatial separation of femoral and tibial cartilage, and ensures spatial regularity while preserving the thin cartilage shape through anisotropic regularization. Our segmentation energy is convex and therefore guarantees globally optimal solutions. We perform an extensive validation of the proposed method on 706 images of the Pfizer Longitudinal Study. Our validation includes comparisons of different atlas segmentation strategies, different local classifiers, and different types of regularizers. To compare to other cartilage segmentation approaches we validate based on the 50 images of the SKI10 dataset.

ER - TY - THES T1 - Automatic localized analysis of longitudinal cartilage changes Y1 - 2014 A1 - Shan, Liang AB -Osteoarthritis (OA) is the most common form of arthritis; it is characterized by the loss of cartilage. Automatic quantitative methods are needed to screen large image databases to assess changes in cartilage morphology. This dissertation presents an automatic analysis method to quantitatively analyze longitudinal cartilage changes from knee magnetic resonance (MR) images. A novel robust automatic cartilage segmentation method is proposed to overcome the limitations of existing cartilage segmentation methods. The dissertation presents a new and general convex three-label segmentation approach to ensure the separation of touching objects, i.e., femoral and tibial cartilage. Anisotropic spatial regularization is introduced to avoid over-regularization by isotropic regularization on thin objects. Temporal regularization is further incorporated to encourage temporally-consistent segmentations across time points for longitudinal data. The state-of-the-art analysis of cartilage changes relies on the subdivision of cartilage, which is coarse and purely geometric whereas cartilage loss is a local thinning process and exhibits spatial nonuniformity. A statistical analysis method is proposed to study localized longitudinal cartilage thickness changes by establishing spatial correspondences across time and between subjects. The method is general and can be applied to nonuniform morphological changes in other diseases.

PB - The university of North Carolina at Chapel Hill UR - http://dc.lib.unc.edu/cdm/ref/collection/etd/id/5965 ER - TY - CONF T1 - Depth-Based Shape Analysis T2 - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2014 A1 - Y. Hong A1 - Y. Gao A1 - Niethammer, M A1 - Bouix, S AB - In this paper we propose a new method for shape analysis based on the depth-ordering of shapes. We use this depth-ordering to non-parametrically define depth with respect to a normal control population. This allows us to quantify differences with respect to “normality”. We combine this approach with a permutation test allowing it to test for localized shape differences. The method is evaluated on a synthetically generated striatum dataset as well as on a real caudate dataset. JF - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - CONF T1 - Geodesic Regression on the Grassmannian T2 - Proceedings of the European Conference on Computer Vision (ECCV) Y1 - 2014 A1 - Y. Hong A1 - N. Singh A1 - R. Kwitt A1 - N. Vasconcelos A1 - Niethammer, M AB -This paper considers the problem of regressing data points on the Grassmann manifold over a scalar-valued variable. The Grassmannian has recently gained considerable attention in the vision community with applications in domain adaption, face recognition, shape analysis, or the classification of linear dynamical systems. Motivated by the success of these approaches, we introduce a principled formulation for regression tasks on that manifold. We propose an intrinsic geodesic regression model generalizing classical linear least-squares regression. Since geodesics are parametrized by a starting point and a velocity vector, the model enables the synthesis of new observations on the manifold. To exemplify our approach, we demonstrate its applicability on three vision problems where data objects can be represented as points on the Grassmannian: the prediction of traffic speed and crowd counts from dynamical system models of surveillance videos and the modeling of aging trends in human brain structures using an affine-invariant shape representation.

JF - Proceedings of the European Conference on Computer Vision (ECCV) ER - TY - CONF T1 - Geometric-Feature-Based Spectral Graph Matching in Pharyngeal Surface Registration T2 - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2014 A1 - Q. Zhao A1 - S. Pizer A1 - Niethammer, M A1 - J. Rosenman AB - Fusion between an endoscopic movie and a CT can aid specifying the tumor target volume for radiotherapy. That requires a deformable pharyngeal surface registration between a 3D endoscope reconstruction and a CT segmentation. In this paper, we propose to use local geometric features for deriving a set of initial correspondences between two surfaces, with which an association graph can be constructed for registration by spectral graph matching. We also define a new similarity measurement to provide a meaningful way for computing inter-surface affinities in the association graph. Our registration method can deal with large non-rigid anatomical deformation, as well as missing data and topology change. We tested the robustness of our method with synthetic deformations and showed registration results on real data. JF - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - JOUR T1 - Large Deformation Diffeomorphic Registration of Diffusion-Weighted Imaging Data JF - Medical Image Analysis Y1 - 2014 A1 - P. Zhang A1 - Niethammer, M A1 - D. Shen A1 - P.-T. Yap AB -Registration plays an important role in group analysis of diffusion-weighted imaging (DWI) data. It helps build a white matter anatomy that is crucial for investigating variation or tracking changes in white matter within a population. Unlike traditional scalar image registration where spatial alignment is the only focus, registration of DWI data requires both spatial alignment of structures and reorientation of local diffusivity profiles. As such, DWI registration is much more complex and challenging than scalar image registration. Although a variety of algorithms has been proposed to tackle the problem, most of them are restricted by the diffusion model used for registration, making it difficult to fit to the registered data a different model. In this paper we describe a method that allows any diffusion model to be fitted after registration for subsequent multifaceted analysis. This is achieved by directly aligning DWI data using a large deformation diffeomorphic registration framework. Our algorithm seeks the optimal coordinate mapping by simultaneously considering structural alignment, local diffusivity profile reorientation, and deformation regularization. Our algorithm also incorporates a multikernel strategy to concurrently register anatomical structures of different scales. We demonstrate the efficacy of our approach using in vivo data and report detailed qualitative and quantitative results in comparison with several different registration strategies.

ER - TY - CONF T1 - Low-Rank to the Rescue – Atlas-based Analyses in the Presence of Pathologies T2 - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2014 A1 - X. Liu A1 - Niethammer, M A1 - R. Kwitt A1 - M. McCormick A1 - S. Aylward AB - Low-rank image decomposition has the potential to address a broad range of challenges that routinely occur in clinical practice. Its novelty and utility in the context of atlas-based analysis stems from its ability to handle images containing large pathologies and large deformations. Potential applications include atlas-based tissue segmentation and unbiased atlas building from data containing pathologies. In this paper we present atlas-based tissue segmentation of MRI from patients with large pathologies. Specifically, a healthy brain atlas is registered with the low-rank components from the input MRIs, the low-rank components are then re-computed based on those registrations, and the process is then iteratively repeated. Preliminary evaluations are conducted using the brain tumor segmentation challenge data (BRATS ’12). JF - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - JOUR T1 - PORTR: Pre-Operative and Post-Recurrence Brain Tumor Registration. JF - IEEE Transactions on Medical Imaging Y1 - 2014 A1 - Kwon, Dongjin A1 - Niethammer, Marc A1 - Akbari, Hamed A1 - Bilello, Michel A1 - Davatzikos, Christos A1 - Pohl, Kilian M AB -We propose a new method for deformable registration of pre-operative and post-recurrence brain MR scans of glioma patients. Performing this type of intra-subject registration is challenging as tumor, resection, recurrence, and edema cause large deformations, missing correspondences, and inconsistent intensity profiles between the scans. To address this challenging task, our method, called PORTR, explicitly accounts for pathological information. It segments tumor, resection cavity, and recurrence based on models specific to each scan. PORTR then uses the resulting maps to exclude pathological regions from the image-based correspondence term while simultaneously measuring the overlap between the aligned tumor and resection cavity. Embedded into a symmetric registration framework, we determine the optimal solution by taking advantage of both discrete and continuous search methods. We apply our method to scans of 24 glioma patients. Both quantitative and qualitative analysis of the results clearly show that our method is superior to other state-of-the-art approaches.

VL - 33 IS - 3 U1 -http://www.ncbi.nlm.nih.gov/pubmed/24595340?dopt=Abstract

ER - TY - CONF T1 - Probabilistic Diffeomorphic Registration: Representing Uncertainty T2 - Proceedings of the International Workshop on Biomedical Image Registration (WBIR) Y1 - 2014 A1 - D. Wassermann A1 - M. Toews A1 - Niethammer, M A1 - W. Wells III AB -This paper presents a novel mathematical framework for representing uncertainty in large deformation diffeomorphic image registration. The Bayesian posterior distribution over the deformations aligning a moving and a fixed image is approximated via a variational formulation. A stochastic differential equation (SDE) modeling the deformations as the evolution of a time-varying velocity field leads to a prior density over deformations in the form of a Gaussian process. This permits estimating the full posterior distribution in order to represent uncertainty, in contrast to methods in which the posterior is approximated via Monte Carlo sampling or maximized in maximum a-posteriori (MAP) estimation. The framework is demonstrated in the case of landmark-based image registration, including simulated data and annotated pre and intra-operative 3D images.

JF - Proceedings of the International Workshop on Biomedical Image Registration (WBIR) UR - https://hal.archives-ouvertes.fr/hal-01095091 ER - TY - JOUR T1 - Scene Parsing with Object Instance Inference Using Regions and Per-exemplar Detectors JF - International Journal of Computer Vision Y1 - 2014 A1 - J. Tighe A1 - Niethammer, M A1 - S. Lazebnik AB -This paper describes a system for interpreting a scene by assigning a semantic label at every pixel and inferring the spatial extent of individual object instances together with their occlusion relationships. First we present a method for labeling each pixel aimed at achieving broad coverage across hundreds of object categories, many of them sparsely sampled. This method combines region-level features with per-exemplar sliding window detectors. Unlike traditional bounding box detectors, per-exemplar detectors perform well on classes with little training data and high intra-class variation, and they allow object masks to be transferred into the test image for pixel-level segmentation. Next, we use per-exemplar detections to generate a set of candidate object masks for a given test image. We then select a subset of objects that explain the image well and have valid overlap relationships and occlusion ordering. This is done by minimizing an integer quadratic program either using a greedy method or a standard solver. We alternate between using the object predictions to refine the pixel labels and using the pixel labels to improve the object predictions. The proposed system obtains promising results on two challenging subsets of the LabelMe dataset, the largest of which contains 45,676 images and 232 classes.

ER - TY - CONF T1 - Scene Parsing with Object Instances and Occlusion Ordering T2 - Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) Y1 - 2014 A1 - J. Tighe A1 - Niethammer, M A1 - S. Lazebnik AB -This work proposes a method to interpret a scene by assigning a semantic label at every pixel and inferring the spatial extent of individual object instances together with their occlusion relationships. Starting with an initial pixel labeling and a set of candidate object masks for a given test image, we select a subset of objects that explain the image well and have valid overlap relationships and occlusion ordering. This is done by minimizing an integer quadratic program either using a greedy method or a standard solver. Then we alternate between using the object predictions to improve the pixel labels and using the pixel labels to improve the object predictions. The proposed system obtains promising results on two challenging subsets of the LabelMe dataset, the largest of which contains 45,676 images and 232 classes.

JF - Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) ER - TY - Generic T1 - Spatio-temporal Image Analysis for Longitudinal and Time-Series Image Data T2 - Third International Workshop, STIA 2014, Held in Conjunction with MICCAI 2014, Boston, USA Y1 - 2014 ED - S. Durrleman ED - Fletcher, T ED - G. Gerig ED - Niethammer, M AB -This book constitutes the refereed proceedings of the Third International Workshop on Spatio-temporal Image Analysis for Longitudinal and Time-Series Image Data, STIA 2014, held in conjunction with MICCAI 2014 in Boston, MA, in October 2014.

JF - Third International Workshop, STIA 2014, Held in Conjunction with MICCAI 2014, Boston, USA T3 - Lecture Notes in Computer Science PB - Springer VL - 8682 UR - http://link.springer.com/book/10.1007/978-3-319-14905-9 ER - TY - CONF T1 - Splines for Diffeomorphic Image Regression T2 - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2014 A1 - N. Singh A1 - Niethammer, M AB -This paper develops a method for splines on diffeomorphisms for image regression. In contrast to previously proposed methods to capture image changes over time, such as geodesic regression, the method can capture more complex spatio-temporal deformations. In particular, it is a first step towards capturing periodic motions for example of the heart or the lung. Starting from a variational formulation of splines the proposed approach allows for the use of temporal control points to control spline behavior. This necessitates the development of a shooting formulation for splines. Experimental results are shown for synthetic and real data. The performance of the method is compared to geodesic regression.

JF - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - JOUR T1 - Statistical Atlas Construction via Weighted Functional Boxplots JF - Medical Image Analysis Y1 - 2014 A1 - Y. Hong A1 - B. Davis A1 - J.S. Marron A1 - R. Kwitt A1 - N. Singh A1 - J. S. Kimbell A1 - E. Pitkin A1 - R. Superfine A1 - S. D. Davis A1 - C. J. Zdanski A1 - Niethammer, M AB -Atlas-building from population data is widely used in medical imaging. However, the emphasis of atlas-building approaches is typically to estimate a spatial alignment to compute a mean / median shape or image based on population data. In this work, we focus on the statistical characterization of the population data, once spatial alignment has been achieved. We introduce and propose the use of the weighted functional boxplot. This allows the generalization of concepts such as the median, percentiles, or outliers to spaces where the data objects are functions, shapes, or images, and allows spatio-temporal atlas-building based on kernel regression. In our experiments, we demonstrate the utility of the approach to construct statistical atlases for pediatric upper airways and corpora callosa revealing their growth patterns. We also define a score system based on the pediatric airway atlas to quantitatively measure the severity of subglottic stenosis (SGS) in the airway. This scoring allows the classification of pre- and post-surgery SGS subjects and radiographically normal controls. Experimental results show the utility of atlas information to assess the effect of airway surgery in children.

ER - TY - CONF T1 - Time-warped Geodesic Regression T2 - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2014 A1 - Y. Hong A1 - N. Singh A1 - R. Kwitt A1 - Niethammer, M AB - We consider geodesic regression with parametric time-warps. This allows, for example, to capture saturation effects as typically observed during brain development or degeneration. While highly-flexible models to analyze time-varying image and shape data based on generalizations of splines and polynomials have been proposed recently, they come at the cost of substantially more complex inference. Our focus in this paper is therefore to keep the model and its inference as simple as possible while allowing to capture expected biological variation. We demonstrate that by augmenting geodesic regression with parametric time-warp functions, we can achieve comparable flexibility to more complex models while retaining model simplicity. In addition, the time-warp parameters provide useful information of underlying anatomical changes as demonstrated for the analysis of corpora callosa and rat calvariae. We exemplify our strategy for shape regression on the Grassmann manifold, but note that the method is generally applicable for time-warped geodesic regression. JF - Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - CONF T1 - Topological Descriptors of Histology Images T2 - Proceedings of the MICCAI Workshop on Machine Learning in Medical Imaging (MLMI) Y1 - 2014 A1 - N. Singh A1 - H. D. Couture A1 - J.S. Marron A1 - C. Perou A1 - Niethammer, M AB -The purpose of this study is to investigate architectural characteristics of cell arrangements in breast cancer histology images. We propose the use of topological data analysis to summarize the geometric information inherent in tumor cell arrangements. Our goal is to use this information as signatures that encode robust summaries of cell arrangements in tumor tissue as captured through histology images. In particular, using ideas from algebraic topology we construct topological descriptors based on cell nucleus segmentations such as persistency charts and Betti sequences. We assess their performance on the task of discriminating the breast cancer subtypes Basal, Luminal A, Luminal B and HER2. We demonstrate that the topological features contain useful complementary information to image-appearance based features that can improve discriminatory performance of classifiers.

JF - Proceedings of the MICCAI Workshop on Machine Learning in Medical Imaging (MLMI) ER - TY - CONF T1 - Diffusion Propagator Estimation using Radial Basis Functions T2 - Proceedings of the MICCAI Workshop on Computational Diffusion MRI (CDMRI) Y1 - 2013 A1 - Y. Rathi A1 - Niethammer, M A1 - F. Laun A1 - K. Setsompop A1 - O. Michailovich A1 - P. E. Grant A1 - C.-F. Westin AB -The average diffusion propagator (ADP) obtained from diffusion MRI (dMRI) data encapsulates important structural properties of the underlying tissue. Measures derived from the ADP can be potentially used as markers of tissue integrity in characterizing several mental disorders. Thus, accurate estimation of the ADP is imperative for its use in neuroimaging studies. In this work, we propose a simple method for estimating the ADP by representing the acquired diffusion signal in the entire q-space using radial basis functions (RBF). We demonstrate our technique using two different RBF’s (generalized inverse multiquadric and Gaussian) and derive analytical expressions for the corresponding ADP’s.We also derive expressions for computing the solid angle orientation distribution function (ODF) for each of the RBF’s. Estimation of the weights of the RBF’s is done by enforcing positivity constraint on the estimated ADP or ODF. Finally, we validate our method on data obtained from a physical phantom with known fiber crossing of 45 degrees and also show comparison with the solid spherical harmonics method of [7].We also demonstrate our method on in-vivo human brain data.

JF - Proceedings of the MICCAI Workshop on Computational Diffusion MRI (CDMRI) ER - TY - JOUR T1 - Diffusion Tensor Imaging-Based Characterization of Brain Neurodevelopment in Primates. JF - Cerebral cortex (New York, N.Y. : 1991) Y1 - 2013 A1 - Shi, Yundi A1 - Short, Sarah J A1 - Knickmeyer, Rebecca C A1 - Wang, Jiaping A1 - Coe, Christopher L A1 - Niethammer, Marc A1 - Gilmore, John H A1 - Zhu, Hongtu A1 - Styner, Martin A AB -Primate neuroimaging provides a critical opportunity for understanding neurodevelopment. Yet the lack of a normative description has limited the direct comparison with changes in humans. This paper presents for the ﬁrst time a cross-sectional diffusion tensor imaging (DTI) study characterizing primate brain neurodevelopment between 1 and 6 years of age on 25 healthy undisturbed rhesus monkeys (14 male, 11 female). A comprehensive analysis including region-of-interest, voxel-wise, and ﬁber tract-based approach demonstrated signiﬁcant changes of DTI properties over time. Changes in fractional anisotropy (FA), mean diffusivity, axial diffusivity (AD), and radial diffusivity (RD) exhibited a heterogeneous pattern across different regions as well as along ﬁber tracts. Most of these patterns are similar to those from human studies yet a few followed unique patterns. Overall, we observed substantial increase in FA and AD and a decrease in RD for white matter (WM) along with similar yet smaller changes in gray matter (GM). We further observed an overall posterior-to-anterior trend in DTI property changes over time and strong correlations between WM and GM development. These DTI trends provide crucial insights into underlying age-related biological maturation, including myelination, axonal density changes, ﬁber tract reorganization, and synaptic pruning processes.

VL - 23 UR - http://cercor.oxfordjournals.org/content/23/1/36.long IS - 1 U1 -http://www.ncbi.nlm.nih.gov/pubmed/22275483?dopt=Abstract

ER - TY - CONF T1 - Diseased Region Detection of Longitudinal Knee MRI Data T2 - Proceedings of the Conference on Information Processing in Medical Imaging (IPMI) Y1 - 2013 A1 - C. Huang A1 - L. Shan A1 - C. Charles A1 - Niethammer, M A1 - H. Zhu AB -Statistical analysis of longitudinal cartilage changes in osteoarthritis (OA) is of great importance and still a challenge in knee MRI data analysis. A major challenge is to establish a reliable correspondence across subjects within the same latent subpopulations. We develop a novel Gaussian hidden Markov model (GHMM) to establish spatial correspondence of cartilage thinning across both time and subjects within the same latent subpopulations and make statistical inference on the detection of diseased regions in each OA patient. A hidden Markov random field (HMRF) is proposed to extract such latent subpopulation structure. The EM algorithm and pseudo-likelihood method are both considered in making statistical inference. The proposed model can effectively detect diseased regions and present a localized analysis of longitudinal cartilage thickness within each latent subpopulation. Simulation studies and diseased region detection on 2D thickness maps extracted from full 3D longitudinal knee MRI Data for Pfizer Longitudinal Dataset are performed, which show that our proposed model outperforms standard voxel-based analysis.

JF - Proceedings of the Conference on Information Processing in Medical Imaging (IPMI) VL - 7917 UR - http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4012563/ ER - TY - CONF T1 - Group-wise Cortical Correspondence via Sulcal Curve-Constrained Entropy Minimization T2 - Proceedings of the Conference on Information Processing in Medical Imaging (IPMI) Y1 - 2013 A1 - I. Lyu A1 - S. H. Kim A1 - J.-K. Seong A1 - S. W. Yoo A1 - A. C. Evans A1 - Y. Shi A1 - M. Sanchez A1 - Niethammer, M A1 - Styner, M AB - We present a novel cortical correspondence method employing group-wise registration in a spherical parametrization space for the use in local cortical thickness analysis in human and non-human primate neuroimaging studies. The proposed method is unbiased registration that estimates a continuous smooth deformation eld into an unbiased average space via sulcal curve-constrained entropy minimization using spherical harmonic decomposition of the spherical deformation field. We initialize a correspondence by our pair-wise method that establishes a surface correspondence with a prior template. Since this pair-wise correspondence is biased to the choice of a template, we further improve the correspondence by employing unbiased ensemble entropy minimization across all surfaces, which yields a deformation field onto the iteratively updated unbiased average. The specific entropy metric incorporates two terms: the first focused on optimizing the correspondence of automatically extracted sulcal landmarks and the second on that of sulcal depth maps. We also propose an encoding scheme for spherical deformation via spherical harmonics as well as a novel method to choose an optimal spherical polar coordinate system for the most efficient deformation field estimation. The experimental results show evidence that the proposed method improves the correspondence quality in non-human primate and human subjects as compared to the pair-wise method. JF - Proceedings of the Conference on Information Processing in Medical Imaging (IPMI) N1 -accepted for publication

ER - TY - CONF T1 - Large Deformation Diffeomorphic Registration of Diffusion-Weighted Images with Explicit Orientation Optimization T2 - MICCAI Y1 - 2013 A1 - P. Zhang A1 - Niethammer, M A1 - D. Shen A1 - P.-T. Yap AB - We seek to compute a diffeomorphic map between a pair of diffusion-weighted images under large deformation. Unlike existing techniques, our method allows any diffusion model to be fitted after registration for subsequent multifaceted analysis. This is achieved by directly aligning the diffusion-weighted images using a large deformation diffeomorphic registration framework formulated from an optimal control perspective. Our algorithm seeks the optimal coordinate mapping by simultaneously considering structural alignment, local fiber reorientation, and deformation regularization. Our algorithm also incorporates a multikernel strategy to concurrently register anatomical structures of different scales. We demonstrate the efficacy of our approach using in vivo data and report on detailed qualitative and quantitative results in comparison with several different registration strategies. JF - MICCAI ER - TY - CONF T1 - Large Deformation Image Classification Using Generalized Locality-Constrained Linear Coding T2 - MICCAI Y1 - 2013 A1 - P. Zhang A1 - C.-Y. Wee A1 - Niethammer, M A1 - D. Shen A1 - P.-T. Yap AB -Magnetic resonance (MR) imaging has been demonstrated to be very useful for clinical diagnosis of Alzheimer’s disease (AD). A common approach to using MR images for AD detection is to spatially normalize the images by non-rigid image registration, and then perform statistical analysis on the resulting deformation fields. Due to the high nonlinearity of the deformation field, recent studies suggest to use initial momentum instead as it lies in a linear space and fully encodes the deformation field. In this paper we explore the use of initial momentum for image classification by focusing on the problem of AD detection. Experiments on the public ADNI dataset show that the initial momentum, together with a simple sparse coding technique—locality-constrained linear coding (LLC)—can achieve a classification accuracy that is comparable to or even better than the state of the art.We also show that the performance of LLC can be greatly improved by introducing proper weights to the codebook.

JF - MICCAI ER - TY - JOUR T1 - A locally adaptive regularization based on anisotropic diffusion for deformable image registration of sliding organs. JF - IEEE transactions on medical imaging Y1 - 2013 A1 - Pace, Danielle F A1 - Aylward, Stephen R A1 - Niethammer, Marc AB -We propose a deformable image registration algorithm that uses anisotropic smoothing for regularization to find correspondences between images of sliding organs. In particular, we apply the method for respiratory motion estimation in longitudinal thoracic and abdominal computed tomography scans. The algorithm uses locally adaptive diffusion tensors to determine the direction and magnitude with which to smooth the components of the displacement field that are normal and tangential to an expected sliding boundary. Validation was performed using synthetic, phantom, and 14 clinical datasets, including the publicly available DIR-Lab dataset. We show that motion discontinuities caused by sliding can be effectively recovered, unlike conventional regularizations that enforce globally smooth motion. In the clinical datasets, target registration error showed improved accuracy for lung landmarks compared to the diffusive regularization. We also present a generalization of our algorithm to other sliding geometries, including sliding tubes (e.g., needles sliding through tissue, or contrast agent flowing through a vessel). Potential clinical applications of this method include longitudinal change detection and radiotherapy for lung or abdominal tumours, especially those near the chest or abdominal wall.

VL - 32 IS - 11 U1 -http://www.ncbi.nlm.nih.gov/pubmed/23899632?dopt=Abstract

ER - TY - JOUR T1 - Longitudinal Image Registration with Temporally-Dependent Image Similarity Measure JF - IEEE Transactions on Medical Imaging Y1 - 2013 A1 - I. Csapo A1 - Y. Shi A1 - B. Davis A1 - M. Sanchez A1 - Styner, M A1 - Niethammer, M AB -Longitudinal imaging studies are frequently used to investigate temporal changes in brain morphology and often require spatial correspondence between images achieved through image registration. Beside morphological changes, image intensity may also change over time, for example when studying brain maturation. However, such intensity changes are not accounted for in image similarity measures for standard image registration methods. Hence, (i) local similarity measures, (ii) methods estimating intensity transformations between images, and (iii) metamorphosis approaches have been developed to either achieve robustness with respect to intensity changes or to simultaneously capture spatial and intensity changes. For these methods, longitudinal intensity changes are not explicitly modeled and images are treated as independent static samples. Here, we propose a model-based image similarity measure for longitudinal image registration that estimates a temporal model of intensity change using all available images simultaneously.

N1 -accepted for publication

ER - TY - CONF T1 - Longitudinal three-label segmentation of knee cartilage T2 - Proceedings of the International Symposium on Biomedical Imaging (ISBI) Y1 - 2013 A1 - L. Shan A1 - C. Charles A1 - Niethammer, M AB - Automatic accurate segmentation methods are needed to assess longitudinal cartilage changes in osteoarthritis (OA). We propose a novel general spatio-temporal three-label segmentation method to encourage segmentation consistency across time in longitudinal image data. The segmentation is formulated as a convex optimization problem which allows for the computation of globally optimal solutions. The longitudinal segmentation is applied within an automatic knee cartilage segmentation pipeline. Experimental results demonstrate that the longitudinal segmentation improves the segmentation consistency in comparison to the temporally-independent segmentation. JF - Proceedings of the International Symposium on Biomedical Imaging (ISBI) N1 -accepted for publication

ER - TY - JOUR T1 - Multi-modal registration for correlative microscopy using image analogies. JF - Medical image analysis Y1 - 2013 A1 - Cao, Tian A1 - Zach, Christopher A1 - Modla, Shannon A1 - Powell, Debbie A1 - Czymmek, Kirk A1 - Niethammer, Marc AB -Correlative microscopy is a methodology combining the functionality of light microscopy with the high resolution of electron microscopy and other microscopy technologies for the same biological specimen. In this paper, we propose an image registration method for correlative microscopy, which is challenging due to the distinct appearance of biological structures when imaged with different modalities. Our method is based on image analogies and allows to transform images of a given modality into the appearance-space of another modality. Hence, the registration between two different types of microscopy images can be transformed to a mono-modality image registration. We use a sparse representation model to obtain image analogies. The method makes use of corresponding image training patches of two different imaging modalities to learn a dictionary capturing appearance relations. We test our approach on backscattered electron (BSE) scanning electron microscopy (SEM)/confocal and transmission electron microscopy (TEM)/confocal images. We perform rigid, affine, and deformable registration via B-splines and show improvements over direct registration using both mutual information and sum of squared differences similarity measures to account for differences in image appearance.

U1 -http://www.ncbi.nlm.nih.gov/pubmed/24387943?dopt=Abstract

ER - TY - JOUR T1 - A new tool improves diagnostic test performance for transmission EM evaluation of axonemal dynein arms. JF - Ultrastructural Pathology Y1 - 2013 A1 - W. K. Funkhouser A1 - Niethammer, M A1 - J. L. Carson A1 - K. A Burns A1 - M R. Knowles A1 - M. W. Leigh A1 - M. A. Zariwala A1 - W. K. Funkhouser AB -Abstract Diagnosis of primary ciliary dyskinesia (PCD) by identification of dynein arm loss in transmission electron microscopy (TEM) images can be confounded by high background noise due to random electron-dense material within the ciliary matrix, leading to diagnostic uncertainty even for experienced morphologists. The authors developed a novel image analysis tool to average the axonemal peripheral microtubular doublets, thereby increasing microtubular signal and reducing random background noise. In a randomized, double-blinded study that compared two experienced morphologists and three different diagnostic approaches, they found that use of this tool led to improvement in diagnostic TEM test performance.

UR - http://www.tandfonline.com/doi/full/10.3109/01913123.2013.815081 N1 -accepted for publication

ER - TY - CONF T1 - A Pediatric Airway Atlas and its Application to Subglottic Stenosis T2 - Proceedings of the International Symposium on Biomedical Imaging (ISBI) Y1 - 2013 A1 - Y. Hong A1 - Niethammer, M A1 - A. Johan A1 - J. Kimbell A1 - E. Pitkin A1 - R. Superfine A1 - S. Davis A1 - C. Zdanski A1 - B. Davis AB -Young children with upper airway problems are at risk for hypoxia, respiratory insufficiency and long term morbidity. Computational models and quantitative analysis would reveal airway growth patterns and benefit clinical care. To capture expected growth patterns we propose a method to build a pediatric airway atlas as a function of age. The atlas is based on a simplified airway model in combination with kernel regression. We show experimental results on children with subglottic stenosis to demonstrate that our method is able to track and measure the stenosis in pediatric airways.

JF - Proceedings of the International Symposium on Biomedical Imaging (ISBI) N1 -accepted for publication

ER - TY - CONF T1 - Riemannian metrics for statistics on shapes: parallel transport and scale invariance T2 - Proceedings of the 4th MICCAI workshop on Mathematical Foundations of Computational Anatomy (MFCA) Y1 - 2013 A1 - Niethammer, M A1 - F. X. Vialard AB - To be able to statistically compare evolutions of image timeseries data requires a method to express these evolutions in a common coordinate system. This requires a mechanism to transport evolutions between coordinate systems: e.g., parallel transport has been used for large displacement diffeomorphic metric mapping (LDDMM) approaches. A common purpose to study evolutions is to assess local tissue growth or decay as observed in the context of neurodevelopment or neurodegeneration. Hence, preserving this information under transport is important to allow for faithful statistical analysis in the common coordinate system. Most basically, we require scale invariance. Here, we show that a scale invariant metric does not exist in the LDDMM setting. We illustrate the impact of this non-invariance on parallel transport. We also propose a new class of Riemannian metrics on shapes which preserves the variation of a global indicator such as volume under parallel transport. JF - Proceedings of the 4th MICCAI workshop on Mathematical Foundations of Computational Anatomy (MFCA) ER - TY - CONF T1 - Robust Multimodal Dictionary Learning T2 - MICCAI Y1 - 2013 A1 - T. Cao A1 - V. Jojic A1 - S. Modla A1 - D. Powell A1 - K. Czymmek A1 - Niethammer, M AB - We propose a robust multimodal dictionary learning method for multimodal images. Joint dictionary learning for both modalities may be impaired by lack of correspondence between image modalities in training data, for example due to areas of low quality in one of the modalities. Dictionaries learned with such non-corresponding data will induce uncertainty about image representation. In this paper, we propose a probabilistic model that accounts for image areas that are poorly corresponding between the image modalities. We cast the problem of learning a dictionary in presence of problematic image patches as a likelihood maximization problem and solve it with a variant of the EM algorithm. Our algorithm iterates identification of poorly corresponding patches and refinements of the dictionary. We tested our method on synthetic and real data. We show improvements in image prediction quality and alignment accuracy when using the method for multimodal image registration. JF - MICCAI ER - TY - JOUR T1 - Segmentation with area constraints. JF - Medical image analysis Y1 - 2013 A1 - Niethammer, Marc A1 - Zach, Christopher AB -Image segmentation approaches typically incorporate weak regularity conditions such as boundary length or curvature terms, or use shape information. High-level information such as a desired area or volume, or a particular topology are only implicitly specified. In this paper we develop a segmentation method with explicit bounds on the segmented area. Area constraints allow for the soft selection of meaningful solutions, and can counteract the shrinking bias of length-based regularization. We analyze the intrinsic problems of convex relaxations proposed in the literature for segmentation with size constraints. Hence, we formulate the area-constrained segmentation task as a mixed integer program, propose a branch and bound method for exact minimization, and use convex relaxations to obtain the required lower energy bounds on candidate solutions. We also provide a numerical scheme to solve the convex subproblems. We demonstrate the method for segmentations of vesicles from electron tomography images.

VL - 17 IS - 1 U1 -http://www.ncbi.nlm.nih.gov/pubmed/23084504?dopt=Abstract

ER - TY - CONF T1 - Sparse Scale-Space Decomposition of Volume Changes in Deformation Fields T2 - MICCAI Y1 - 2013 A1 - M. Lorenzi A1 - B. Menze A1 - Niethammer, M A1 - N. Ayache A1 - X. Pennec AB - Anatomical changes like brain atrophy or growth are usually not homogeneous in space and across spatial scales, since they map differently depending on the anatomical structures. Thus, the accurate analysis of volume changes from medical images requires to reliably localize and distinguish the spatial changes occurring at different scales, from voxel to regional level. We propose here a framework for the sparse probabilistic scale-space analysis of volume changes encoded by deformations. Our framework is based on the Helmholtz decomposition of vector fields. By scale-space analysis of the scalar pressure map associated to the irrotational component of the deformation, we robustly identify the areas of maximal volume changes, and we define a consistent sparse decomposition of the irrotational component. We show the effectiveness of our framework in the challenging problem of detecting the progression of tumor growth, and in the group-wise analysis of the longitudinal atrophy in Alzheimer's disease. JF - MICCAI ER - TY - CONF T1 - Studying Cerebral Vasculature Using Structure Proximity and Graph Kernels T2 - MICCAI Y1 - 2013 A1 - R. Kwitt A1 - D. Pace A1 - Niethammer, M A1 - S. Aylward AB - An approach to study population differences in cerebral vasculature is proposed. This is done by 1) extending the concept of encoding cerebral blood vessel networks as spatial graphs and 2) quantifying graph similarity in a kernel-based discriminant classifier setup. We argue that augmenting graph vertices with information about their proximity to selected brain structures adds discriminative information and consequently leads to a more expressive encoding. Using graph-kernels then allows us to quantify graph similarity in a principled way. To demonstrate our approach, we assess the hypothesis that gender differences manifest as variations in the architecture of cerebral blood vessels, an observation that previously had only been tested and confirmed for the Circle of Willis. Our results strongly support this hypothesis, i.e, we can demonstrate non-trivial, statistically significant deviations from random gender classification in a cross-validation setup on 40 healthy patients. JF - MICCAI ER - TY - CONF T1 - Weighted Functional Boxplot with Application to Statistical Atlas Construction T2 - MICCAI Y1 - 2013 A1 - Y. Hong A1 - B. Davis A1 - J. Marron A1 - R. Kwitt A1 - Niethammer, M AB -Atlas-building from population data is widely used in medical imaging. However, the emphasis of atlas-building approaches is typically to compute a mean / median shape or image based on population data. In this work, we focus on the statistical characterization of the population data, once spatial alignment has been achieved. We introduce and propose the use of the weighted functional boxplot. This allows the generalization of concepts such as the median, percentiles, or outliers to spaces where the data objects are functions, shapes, or images, and allows spatio-temporal atlas-building based on kernel regression. In our experiments, we demonstrate the utility of the approach to construct statistical atlases for pediatric upper airways and corpora callosa revealing their growth patterns. Furthermore, we show how such atlas information can be used to assess the effect of airway surgery in children.

JF - MICCAI ER - TY - CONF T1 - Automatic Multi-Atlas-Based Cartilage Segmentation from Knee MR Images T2 - Proceedings of the International Symposium on Biomedical Imaging (ISBI) Y1 - 2012 A1 - L. Shan A1 - C. Charles A1 - Niethammer, M AB -In this paper, we propose a multi-atlas-based method to automatically segment the femoral and tibial cartilage from T1 weighted magnetic resonance (MR) knee images. The segmentation result is a joint decision of the spatial priors from a multi-atlas registration and the local likelihoods within a Bayesian framework. The cartilage likelihoods are obtained from a probabilistic k nearest neighbor classification. Validation results on 18 knee MR images against the manual expert segmentations from a dataset acquired for osteoarthritis research show good performance for the segmentation of femoral and tibial cartilage (mean Dice similarity coefficient of 75.2% and 81.7% respectively).

JF - Proceedings of the International Symposium on Biomedical Imaging (ISBI) ER - TY - JOUR T1 - Image and Statistical Analysis of Melanocytic Histology JF - Histopathology Y1 - 2012 A1 - J. Miedema A1 - J.S. Marron A1 - Niethammer, M A1 - D. Borland A1 - J. Woosley A1 - J. Coposky A1 - S. Wei A1 - N.E. Thomas AB -Aims: We apply digital image analysis techniques to study selected types of melanocytic lesions. Methods and Results: We use advanced digital image analysis to compare melanocytic lesions. All comparisons were statistically significant (p < 0.0001) and we highlight four: 1) melanoma to nevi, 2) melanoma subtypes to nevi, 3) severely dysplastic nevi to other nevi, and 4) melanoma to severely dysplastic nevi. We were successful in differentiating melanoma from nevi (ROC area 0.95) using image-derived features. Analysis revealed features related to nuclear size, shape, and distance between nuclei most important. Dividing melanoma into subtypes, even greater separation was obtained (ROC area 0.98 for superficial spreading melanoma; 0.95 for lentigo maligna melanoma; and 0.99 for unclassified). Severely dysplastic nevi were best differentiated from conventional and mildly dysplastic nevi by differences in cellular staining qualities (ROC area 0.84). We found that melanoma were separated from severely dysplastic nevi by features related to cell shape and cellular staining qualities (ROC area 0.95). Conclusions: We offer a unique perspective into the evaluation of melanocytic lesions and demonstrate a technological application with increasing prevalence, with potential use as an adjunct to traditional diagnosis in the future.

VL - 61 UR - http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3425719/ IS - 3 ER - TY - CONF T1 - Large Deformation Diffeomorphic Registration of Diffusion-Weighted Images T2 - MICCAI Y1 - 2012 A1 - P. Zhang A1 - Niethammer, M A1 - D. Shen A1 - P.-T. Yap AB -Registration of Diffusion-weighted imaging (DWI) data emerges as an important topic in magnetic resonance (MR) image analysis. As existing methods are often designed for specific diffusion models, it is difficult to fit to the registered data different models other than the one used for registration. In this paper we describe a diffeomorphic registration algorithm for DWI data under large deformation. Our method generates spatially normalized DWI data and it is thus possible to fit various diffusion models after registration for comparison purposes. Our algorithm includes (1) a reorientation component, where each diffusion profile (DWI signal as a function on a unit sphere) is decomposed, reoriented and recomposed to form the orientation-corrected DWI profile, and (2) a large deformation diffeomorphic registration component to ensure one-to-one mapping in a large-structural-variation scenario. In addition our algorithm uses a geodesic shooting mechanism to avoid the huge computational resources that are needed to register high-dimensional vector-valued data. We also incorporate into our algorithm a multi-kernel strategy where anatomical structures at different scales are considered simultaneously during registration. We demonstrate the efficacy of our method using in vivo data.

JF - MICCAI UR - http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3771077/ ER - TY - CONF T1 - Longitudinal Image Registration with Non-Uniform Appearance Change T2 - MICCAI Y1 - 2012 A1 - I. Csapo A1 - B. Davis A1 - Y. Shi A1 - M. Sanchez A1 - Styner, M A1 - Niethammer, M AB -Longitudinal imaging studies are frequently used to investigate temporal changes in brain morphology. Image intensity may also change over time, for example when studying brain maturation. However, such intensity changes are not accounted for in image similarity measures for standard image registration methods. Hence, (i) local similarity measures, (ii) methods estimating intensity transformations between images, and (iii) metamorphosis approaches have been developed to either achieve robustness with respect to intensity changes or to simultaneously capture spatial and intensity changes. For these methods, longitudinal intensity changes are not explicitly modeled and images are treated as independent static samples. Here, we propose a model-based image similarity measure for longitudinal image registration in the presence of spatially non-uniform intensity change.

JF - MICCAI ER - TY - CONF T1 - LQG-Obstacles: Feedback Control with Collision Avoidance for Mobile Robots with Motion and Sensing Uncertainty T2 - Proceedings of the International Conference on Robotics and Automation (ICRA) Y1 - 2012 A1 - J. van den Berg A1 - D. Wilkie A1 - S. J. Guy A1 - Niethammer, M A1 - D. Manocha AB -This paper presents LQG-Obstacles, a new concept that combines linear-quadratic feedback control of mobile robots with guaranteed avoidance of collisions with obstacles. Our approach generalizes the concept of Velocity Obstacles to any robotic system with a linear Gaussian dynamics model. We integrate a Kalman filter for state estimation and an LQR feedback controller into a closed-loop dynamics model of which a higher-level control objective is the ``control input''. We then define the LQG-Obstacle as the set of control objectives that result in a collision with high probability. Selecting a control objective outside the LQG-Obstacle then produces collision-free motion. We demonstrate the potential of LQG-Obstacles by safely and smoothly navigating a simulated quadrotor helicopter with complex non-linear dynamics and motion and sensing uncertainty through three-dimensional environments with obstacles and narrow passages.

JF - Proceedings of the International Conference on Robotics and Automation (ICRA) ER - TY - CONF T1 - Metamorphic Geodesic Regression T2 - MICCAI Y1 - 2012 A1 - Y. Hong A1 - S. Joshi A1 - M. Sanchez A1 - Styner, M A1 - Niethammer, M AB -We propose a metamorphic geodesic regression approach approximating spatial transformations for image time-series while simultaneously accounting for intensity changes. Such changes occur for example in magnetic resonance imaging (MRI) studies of the developing brain due to myelination. To simplify computations we propose an approximate metamorphic geodesic regression formulation that only requires pairwise computations of image metamorphoses. The approximated solution is an appropriately weighted average of initial momenta. To obtain initial momenta reliably, we develop a shooting method for image metamorphosis.

JF - MICCAI ER - TY - CONF T1 - Registration for Correlative Microscopy using Image Analogies T2 - Workshop on Biomedical Image Registration (WBIR) Y1 - 2012 A1 - T. Cao A1 - Zach, C A1 - S. Modla A1 - D. Powell A1 - K. Czymmek A1 - Niethammer, M AB -Correlative microscopy is a methodology combining the functionality of light microscopy with the high resolution of electron microscopy and other microscopy technologies for the same biological specimen. In this paper, we propose an image registration method for correlative microscopy, which is challenging due to the distinct appearance of biological structures when imaged with di↵erent modalities. Our method is based on image analogies and allows to transform images of a given modality into the appearance-space of another modality. Hence, the registration between two di↵erent types of microscopy images can be transformed to a mono-modality image registration. We use a sparse representation model to obtain image analogies. The method makes use of representative corresponding image training patches of two different imaging modalities to learn a dictionary capturing appearance relations. We test our approach on backscattered electron (BSE) Scanning Electron Microscopy (SEM)/confocal and Transmission Electron Microscopy (TEM)/confocal images and show improvements over direct registration using a mutual-information similarity measure to account for differences in image appearance.

JF - Workshop on Biomedical Image Registration (WBIR) ER - TY - CONF T1 - Simple Geodesic Regression for Image Time-Series T2 - Workshop on Biomedical Image Registration (WBIR) Y1 - 2012 A1 - Y. Hong A1 - M. Sanchez A1 - Styner, M A1 - Niethammer, M AB -Geodesic regression generalizes linear regression to general Riemannian manifolds. Applied to images, it allows for a compact approximation of an image time-series through an initial image and an initial momentum. Geodesic regression requires the definition of a squared residual (squared distance) between the regression geodesic and the measurement images. In principle, this squared distance should also be defined through a geodesic connecting an image on the regression geodesicto its respective measurement. However, in practice only standard registration distances (such as sum of squared distances) are used, to reduce computation time. This paper describes a simplified geodesic regression method which approximates the registration-based distances with respect to a fixed initial image. This results in dramatically simplified computations. In particular, the method becomes straightforward to implement using readily available large displacement diffeomorphic metric mapping (LDDMM) shooting algorithms and decouples the problem into pairwise image registrations allowing parallel computations. We evaluate the approach using 2D synthetic images and real 3D brain images.

JF - Workshop on Biomedical Image Registration (WBIR) ER - TY - JOUR T1 - Simulation-Based Joint Estimation of Body Deformation and Elasticity Parameters for Medical Image Analysis. JF - IEEE transactions on medical imaging Y1 - 2012 A1 - Lee, H A1 - M. Foskey A1 - Niethammer, M A1 - Krajcevski, P A1 - M. Lin AB -Estimation of tissue stiffness is an important means of noninvasive cancer detection. Existing elasticity reconstruction methods usually depend on a dense displacement field (inferred from ultrasound orMR images) and known external forces.Many imaging modalities, however, cannot provide details within an organ and therefore cannot provide such a displacement field. Furthermore, force exertion and measurement can be difficult for some internal organs, making boundary forces another missing parameter. We propose a general method for estimating elasticity and boundary forces automatically using an iterative optimization framework, given the desired (target) output surface. During the optimization, the input model is deformed by the simulator, and an objective function based on the distance between the deformed surface and the target surface is minimized numerically. The optimization framework does not depend on a particular simulation method and is therefore suitable for different physical models. We show a positive correlation between clinical prostate cancer stage (a clinical measure of severity) and the recovered elasticity of the organ. Since the surface correspondence is established, our method also provides a non-rigid image registration, where the quality of the deformation fields is guaranteed, as they are computed using a physics-based simulation.

U1 -http://www.ncbi.nlm.nih.gov/pubmed/22893381?dopt=Abstract

ER - TY - Generic T1 - Spatio-temporal Image Analysis for Longitudinal and Time-Series Image Data T2 - Second International Workshop, STIA 2012, Held in Conjunction with MICCAI 2012, Nice, France Y1 - 2012 ED - S. Durrleman ED - Fletcher, T ED - G. Gerig ED - Niethammer, M AB -This book constitutes the refereed proceedings of the Second International Workshop on Spatio-temporal Image Analysis for Longitudinal and Time-Series Image Data, STIA 2012, held in conjunction with MICCAI 2012 in Nice, France, in October 2012.

JF - Second International Workshop, STIA 2012, Held in Conjunction with MICCAI 2012, Nice, France T3 - Lecture Notes in Computer Science PB - Springer VL - 7570 UR - http://www.springer.com/computer/image+processing/book/978-3-642-33554-9 ER - TY - CONF T1 - Temporally-Dependent Image Similarity Measure for Longitudinal Analysis T2 - Workshop on Biomedical Image Registration (WBIR) Y1 - 2012 A1 - I. Csapo A1 - Y. Shi A1 - M. Sanchez A1 - Styner, M A1 - Niethammer, M AB -Current longitudinal image registration methods rely on the assumption that image appearance between time-points remains constant or changes uniformly within intensity classes. This assumption, however, is not valid for magnetic resonance imaging of brain development. Registration methods developed to align images with non-uniform appearance change either (i) locally minimize some global similarity measure, or (ii) iteratively estimate an intensity transformation that makes the images similar. However, these methods treat the individual images as independent static samples and are inadequate for the strong non-uniform appearance changes seen in neurodevelopmental data. Here, we propose a model-based similarity measure intended for aligning longitudinal images that locally estimates a temporal model of intensity change. Unlike previous approaches, the model-based formulation is able to capture complex appearance changes between time-points and we demonstrate that it is critical when using a deformable transformation model.

JF - Workshop on Biomedical Image Registration (WBIR) ER - TY - CONF T1 - An automated pipeline for cortical surface generation and registration of the cerebral cortex T2 - Proceedings of SPIE Y1 - 2011 A1 - Li, W. A1 - Ibanez, L. A1 - Gelas, A. A1 - Yeo, B.T.T. A1 - Niethammer, M A1 - Andreasen, N.C. A1 - Magnotta, V.A. AB -The human cerebral cortex is one of the most complicated structures in the body. It has a highly convoluted structure with much of the cortical sheet buried in sulci. Based on cytoarchitectural and functional imaging studies, it is possible to segment the cerebral cortex into several subregions. While it is only possible to differentiate the true anatomical subregions based on cytoarchitecture, the surface morphometry aligns closely with the underlying cytoarchitecture and provides features that allow the surface of the cortex to be parcellated based on the sulcal and gyral patterns that are readily visible on the MR images. We have developed a fully automated pipeline for the generation and registration of cortical surfaces in the spherical domain. The pipeline initiates with the BRAINS AutoWorkup pipeline. Subsequently, topology correction and surface generation is performed to generate a genus zero surface and mapped to a sphere. Several surface features are then calculated to drive the registration between the atlas surface and other datasets. A spherical diffeomorphic demons algorithm is used to co-register an atlas surface onto a subject surface. A lobar based atlas of the cerebral cortex was created from a manual parcellation of the cortex. The atlas surface was then co-registered to five additional subjects using a spherical diffeomorphic demons algorithm. The labels from the atlas surface were warped on the subject surface and compared to the manual raters. The average Dice overlap index was 0.89 across all regions.

JF - Proceedings of SPIE VL - 7962 ER - TY - CONF T1 - Automatic Atlas-based Three-label Cartilage Segmentation from MR Knee Images T2 - Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA) Y1 - 2011 A1 - L. Shan A1 - C. Charles A1 - Niethammer, M AB -This paper proposes a method to build a bone-cartilage atlas of the knee and to use it to automatically segment femoral and tibial cartilage from T1 weighted magnetic resonance (MR) images. Anisotropic spatial regularization is incorporated into a three-label segmentation framework to improve segmentation results for the thin cartilage layers. We jointly use the atlas information and the output of a probabilistic k nearest neighbor classifier within the segmentation method. The resulting cartilage segmentation method is fully automatic. Validation results on 18 knee MR images against manual expert segmentations from a dataset acquired for osteoarthritis research show good performance for the segmentation of femoral and tibial cartilage (mean Dice similarity coefficient of 79.2% and 83.5% respectively).

JF - Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA) ER - TY - CONF T1 - Automatic cortical thickness analysis on rodent brain T2 - Proceedings of SPIE Y1 - 2011 A1 - Lee, J. A1 - Ehlers, C. A1 - Crews, F. A1 - Niethammer, M A1 - Budin, F. A1 - Paniagua, B. A1 - Sulik, K. A1 - Johns, J. A1 - Styner, M A1 - Oguz, I AB -Localized difference in the cortex is one of the most useful morphometric traits in human and animal brain studies. There are many tools and methods already developed to automatically measure and analyze cortical thickness for the human brain. However, these tools cannot be directly applied to rodent brains due to the different scales; even adult rodent brains are 50 to 100 times smaller than humans. This paper describes an algorithm for automatically measuring the cortical thickness of mouse and rat brains. The algorithm consists of three steps: segmentation, thickness measurement, and statistical analysis among experimental groups. The segmentation step provides the neocortex separation from other brain structures and thus is a preprocessing step for the thickness measurement. In the thickness measurement step, the thickness is computed by solving a Laplacian PDE and a transport equation. The Laplacian PDE first creates streamlines as an analogy of cortical columns; the transport equation computes the length of the streamlines. The result is stored as a thickness map over the neocortex surface. For the statistical analysis, it is important to sample thickness at corresponding points. This is achieved by the particle correspondence algorithm which minimizes entropy between dynamically moving sample points called particles. Since the computational cost of the correspondence algorithm may limit the number of corresponding points, we use thin-plate spline based interpolation to increase the number of corresponding sample points. As a driving application, we measured the thickness difference to assess the effects of adolescent intermittent ethanol exposure that persist into adulthood and performed t-test between the control and exposed rat groups. We found significantly differing regions in both hemispheres.

JF - Proceedings of SPIE VL - 7962 ER - TY - CHAP T1 - Deformable image registration of sliding organs using anisotropic diffusive regularization T2 - 2011 IEEE International Symposium on Biomedical Imaging From Nano to Macro Y1 - 2011 A1 - Pace, Danielle F A1 - Enquobahrie, Andinet A1 - Yang, Hua A1 - Aylward, Stephen R A1 - Niethammer, Marc AB -Traditional deformable image registration imposes a uniform smoothness constraint on the deformation field. This is not appropriate when registering images visualizing organs that slide relative to each other, and therefore leads to registration inaccuracies. In this paper, we present a deformation field regularization term that is based on anisotropic diffusion and accommodates the deformation field discontinuities that are expected when considering sliding motion. The registration algorithm was assessed first using artificial images of geometric objects. In a second validation, monomodal chest images depicting both respiratory and cardiac motion were generated using an anatomically-realistic software phantom and then registered. Registration accuracywas assessed based on the distances between corresponding segmented organ surfaces. Compared to an established diffusive regularization approach, the anisotropic diffusive regularization gave deformation fields that represented more plausible image correspondences, while giving rise to similar transformed moving images and comparable registration accuracy.

JF - 2011 IEEE International Symposium on Biomedical Imaging From Nano to Macro UR - http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3141338/ ER - TY - CONF T1 - Geodesic Regression T2 - MICCAI Y1 - 2011 A1 - Niethammer, M A1 - Y. Huang A1 - F.-X. Vialard AB - Registration of image-time series has so far been accomplished (i) by concatenating registrations between image pairs, (ii) by solving a joint estimation problem resulting in piecewise geodesic paths between image pairs, (iii) by kernel based local averaging or (iv) by augmenting the joint estimation with additional temporal irregularity penalties. Here, we propose a *generative model* extending least squares linear regression to the space of images by using a second-order dynamic formulation for image registration. Unlike previous approaches, the formulation allows for a compact representation of an approximation to the full spatio-temporal trajectory through its initial values. The method also opens up possibilities to design image-based approximation algorithms. The resulting optimization problem is solved using an adjoint method.

accepted for publication

ER - TY - CONF T1 - Geometric Metamorphosis T2 - MICCAI Y1 - 2011 A1 - Niethammer, M A1 - G. Hart A1 - D. Pace A1 - S. Aylward AB - Standard image registration methods do not account for changes in image appearance. Hence, metamorphosis approaches have been developed which jointly estimate a space deformation and a change in image appearance to construct a spatio-temporal trajectory smoothly transforming a source to a target image. For standard metamorphosis, geometric changes are not explicitly modeled. We propose a *geometric metamorphosis* formulation, which explains changes in image appearance by a global deformation, a deformation of a geometric model, and an image composition model. This work is motivated by the clinical challenge of predicting the long-term effects of traumatic brain injuries based on time-series images. This work is also applicable to the quantification of tumor progression (e.g., estimating its infiltrating and displacing components) and predicting chronic blood perfusion changes after stroke. We demonstrate the utility of the method using simulated data as well as scans from a clinical traumatic brain injury patient.

accepted for publication

ER - TY - CONF T1 - Group-wise automatic mesh-based analysis of cortical thickness T2 - Proceedings of SPIE Y1 - 2011 A1 - Vachet, C A1 - Hazlett, H.C. A1 - Niethammer, M A1 - Oguz, I A1 - Cates, J A1 - Whitaker, R A1 - Piven, J. A1 - Styner, M AB -The analysis of neuroimaging data from pediatric populations presents several challenges. There are normal variations in brain shape from infancy to adulthood and normal developmental changes related to tissue maturation. Measurement of cortical thickness is one important way to analyze such developmental tissue changes. We developed a novel framework that allows group-wise automatic mesh-based analysis of cortical thickness. Our approach is divided into four main parts. First an individual pre-processing pipeline is applied on each subject to create genus-zero inflated white matter cortical surfaces with cortical thickness measurements. The second part performs an entropy-based group-wise shape correspondence on these meshes using a particle system, which establishes a trade-off between an even sampling of the cortical surfaces and the similarity of corresponding points across the population using sulcal depth information and spatial proximity. A novel automatic initial particle sampling is performed using a matched 98-lobe parcellation map prior to a particle-splitting phase. Third, corresponding re-sampled surfaces are computed with interpolated cortical thickness measurements, which are finally analyzed via a statistical vertex-wise analysis module. This framework consists of a pipeline of automated 3D Slicer compatible modules. It has been tested on a small pediatric dataset and incorporated in an open-source C++ based high-level module called GAMBIT. GAMBIT's setup allows efficient batch processing, grid computing and quality control. The current research focuses on the use of an average template for correspondence and surface re-sampling, as well as thorough validation of the framework and its application to clinical pediatric studies.

JF - Proceedings of SPIE VL - 7962 ER - TY - JOUR T1 - An Optimal Control Approach for Texture Metamorphosis JF - Computer Graphics Forum Y1 - 2011 A1 - I. Kabul A1 - S. M. Pizer A1 - J. Rosenman A1 - Niethammer, M AB -In this paper, we introduce a new texture metamorphosis approach for interpolating texture samples from a source texture into a target texture. We use a new energy optimization scheme derived from optimal control principles which exploits the structure of the metamorphosis optimality conditions. Our approach considers the change in pixel position and pixel appearance in a single framework. In contrast to previous techniques that compute a global warping based on feature masks of textures, our approach allows to transform one texture into another by considering both intensity values and structural features of textures simultaneously. We demonstrate the usefulness of our approach for different textures, such as stochastic, semi-structural and regular textures, with different levels of complexities. Our method produces visually appealing transformation sequences with no user interaction.

N1 -accepted for publication

ER - TY - JOUR T1 - The power of correlative microscopy: multi-modal, multi-scale, multi-dimensional JF - Current Opinion in Structural Biology Y1 - 2011 A1 - Jeffrey Caplan A1 - Niethammer, Marc A1 - Russell M Taylor II A1 - Kirk J Czymmek AB -Correlative microscopy is a sophisticated approach that combines the capabilities of typically separate, but powerful microscopy platforms: often including, but not limited, to conventional light, confocal and super-resolution microscopy, atomic force microscopy, transmission and scanning electron microscopy, magnetic resonance imaging and micro/nano CT (computed tomography). When targeting rare or specific events within large populations or tissues, correlative microscopy is increasingly being recognized as the method of choice. Furthermore, this multi-modal assimilation of technologies provides complementary and often unique information, such as internal and external spatial, structural, biochemical and biophysical details from the *same* targeted sample. The development of a continuous stream of cutting-edge applications, probes, preparation methodologies, hardware and software developments will enable realization of the full potential of correlative microscopy.

Chorea-acanthocytosis (ChAc) is an uncommon autosomal recessive disorder due to mutations of the VPS13A gene, which encodes for the membrane protein chorein. ChAc presents with progressive limb and orobuccal chorea, but there is often a marked dysexecutive syndrome. ChAc may first present with neuropsychiatric disturbance such as obsessive-compulsive disorder (OCD), suggesting a particular role for disruption to striatal structures involved in non-motor frontostriatal loops, such as the head of the caudate nucleus. Two previous studies have suggested a marked reduction in volume in the caudate nucleus and putamen, but did not examine morphometric change. We investigated morphometric change in 13 patients with genetically or biochemically confirmed ChAc and 26 age- and gender-matched controls. Subjects underwent magnetic resonance imaging and manual segmentation of the caudate nucleus and putamen, and shape analysis using a non-parametric spherical harmonic technique. Both structures showed significant and marked reductions in volume compared with controls, with reduction greatest in the caudate nucleus. Both structures showed significant shape differences, particularly in the head of the caudate nucleus. No significant correlation was shown between duration of illness and striatal volume or shape, suggesting that much structural change may have already taken place at the time of symptom onset. Our results suggest that striatal neuron loss may occur early in the disease process, and follows a dorsal-ventral gradient that may correlate with early neuropsychiatric and cognitive presentations of the disease.

VL - 192 ER - TY - CONF T1 - Sliding Geometries in Deformable Image Registration T2 - MICCAI, Workshop on Computational and Clinical Applications in Abdominal Imaging Y1 - 2011 A1 - D. Pace A1 - Niethammer, M A1 - S. Aylward AB -

Regularization is used in deformable image registration to encourage plausible displacement fields, and significantly impacts the derived correspondences. Sliding motion, such as that between the lungs and chest wall and between the abdominal organs, complicates regis- tration because many regularizations are global smoothness constraints that produce errors at object boundaries. We present locally adaptive regularizations that handle sliding objects with locally planar and tubu- lar geometries. These regularizations allow discontinuities to develop in the displacement field at sliding interfaces and increase the independence with which regions surrounding distinct geometric structures can behave. Validation is performed by registering inhale and exhale abdominal com- puted tomography (CT) images and artificial images of a sliding tube. The sliding registration methods produce more realistic correspondences that may better reflect the underlying physical motion, while performing as well as the diffusive regularization with respect to image match.

JF - MICCAI, Workshop on Computational and Clinical Applications in Abdominal Imaging ER - TY - CONF T1 - Appearance Normalization of Histology Slides T2 - MICCAI, International Workshop Machine Learning in Medical Imaging Y1 - 2010 A1 - Niethammer, M A1 - D. Borland A1 - J.S. Marron A1 - J. Woolsey A1 - N.E. Thomas AB -This paper presents a method for automatic color and intensity normalization of digitized histology slides stained with two different agents. In comparison to previous approaches, prior information on the stain vectors is used in the estimation process, resulting in improved stability of the estimates. Due to the prevalence of hematoxylin and eosin staining for histology slides, the proposed method has signicant practical utility. In particular, it can be used as a first step to standardize appearances across slides, that is very effective at countering effects due to differing stain amounts and protocols, and to slide fading. The approach is validated using synthetic experiments and 13 real datasets.

JF - MICCAI, International Workshop Machine Learning in Medical Imaging ER - TY - JOUR T1 - Attenuation analysis of Lamb waves using the chirplet transform JF - EURASIP: Journal on Advances in Signal Processing Y1 - 2010 A1 - F. Kerber A1 - H. Sprenger A1 - Niethammer, M A1 - K. Luangvilai A1 - L. Jacobs AB -Guided Lamb waves are commonly used in nondestructive evaluation to monitor plate-like structures or to characterize properties of composite or layered materials. However, the dispersive propagation and multimode excitability of Lamb waves complicate their analysis. Advanced signal processing techniques are therefore required to resolve both the time and frequency content of the time-domain wave signals. The chirplet transform (CT) has been introduced as a generalized time-frequency representation (TFR) incorporating more flexibility to adjust the window function to the group delay of the signal when compared to the more classical short-time Fourier transform (STFT). Exploiting this additional degree of freedom, this paper applies an adaptive algorithm based on the CT to calculate mode displacement ratios and attenuation of Lamb waves in elastic plate structures. The CT-based algorithm has a clear performance advantage when calculating mode displacement ratios and attenuation for numerically-simulated Lamb wave signals. For experimental data, the CT retains an advantage over the STFT although measurement noise and parameter uncertainties lead to larger overall deviations from the theoretically expected solutions.

UR - http://asp.eurasipjournals.springeropen.com/articles/10.1155/2010/375171 ER - TY - CONF T1 - Automatic Bone Segmentation and Alignment from MR knee images T2 - SPIE Medical Imaging Y1 - 2010 A1 - L. Shan A1 - Zach, C A1 - Styner, M A1 - C. Charles A1 - Niethammer, M AB -Automatic image analysis of magnetic resonance (MR) images of the knee is simplified by bringing the knee into a reference position. While the knee is typically put into a reference position during image acquisition, this alignment will generally not be perfect. To correct for imperfections, we propose a two-step process of bone segmentation followed by elastic tissue deformation. The approach makes use of a fully-automatic segmentation of femur and tibia from T1 and T2* images. The segmentation algorithm is based on a continuous convex optimization problem, incorporating regional, and shape information. The regional terms are included from a probabilistic viewpoint, which readily allows the inclusion of shape information. Segmentation of the outer boundary of the cortical bone is encouraged by adding simple appearance-based information to the optimization problem. The resulting segmentation without the shape alignment step is globally optimal.

Standard registration is problematic for knee alignment due to the distinct physical properties of the tissues constituting the knee (bone, muscle, etc.). We therefore develop an alternative alignment approach based on a simple elastic deformation model combined with strict enforcement of similarity transforms for femur and tibia based on the obtained segmentations.

JF - SPIE Medical Imaging N1 -in press; Proceedings of SPIE Medical Imaging

ER - TY - CONF T1 - Automatic three-label bone segmentation from knee MR images T2 - International Symposium on Biomedical Imaging (ISBI) Y1 - 2010 A1 - L. Shan A1 - Zach, C A1 - Niethammer, M AB -We propose a novel fully automatic three-label bone segmentation approach applied to knee segmentation (femur and tibia) from T1 and T2* magnetic resonance (MR) images. The three-label segmentation approach guarantees separate segmentations of femur and tibia which cannot be assured by general binary segmentation methods. The proposed approach is based on a convex optimization problem by embedding label assignment into higher dimensions . Appearance information is used in the segmentation to favor the segmentation of the cortical bone. We validate the proposed three label segmentation method on nine knee MR images against manual segmentations for femur and tibia.

JF - International Symposium on Biomedical Imaging (ISBI) N1 -Proceedings of the International Symposium on Biomedical Imaging (ISBI)

ER - TY - CONF T1 - DTI Connectivity by Segmentation T2 - MICCAI, International Workshop on Medical Imaging and Augmented Reality (MIAR) Y1 - 2010 A1 - Niethammer, M A1 - A. Boucharin A1 - Zach, C A1 - E. Maltbie A1 - Y. Shi A1 - Styner, M AB -This paper proposes a new method to compute connectivity information from diffusion weighted images. It is inspired by graph-based approaches to connectivity definition, but formulates the estimation problem in the continuum. In particular, it defines the connectivity through the minimum cut in tensor-weighted space. It is therefore closely related to prior work on segmentation using continuous versions of graph cuts. A numerical solution based on a staggered grid is proposed which allows for the computation of flux directly through diffusion tensors. The resulting global connectivity measure is the maximum diffusive flow supported between two regions of interest.

JF - MICCAI, International Workshop on Medical Imaging and Augmented Reality (MIAR) ER - TY - CONF T1 - DTI Longitudinal Atlas Construction as an Average of Growth Models T2 - MICCAI, International Workshop on Spatio-Temporal Image Analysis for Longitudinal and Time-Series Image Data Y1 - 2010 A1 - G. Hart A1 - Y. Shi A1 - H. Zhu A1 - M. Sanchez A1 - Styner, M A1 - Niethammer, M AB -Existing atlas-building methods for diusion-tensor images are not designed for longitudinal data. This paper proposes a novel longitudinal atlas-building framework explicitly accounting for temporal dependencies of longitudinal MRI data. Subject-specic growth modeling, cross-sectional atlas-building and growth modeling in atlas space are combined with statistical longitudinal modeling, resulting in a longitudinal diffusion tensor atlas. The method captures changes in morphology, while modeling temporal changes and allowing to account for covariates. The component algorithms are based on large-displacement metric mapping formulations. To effectively account for measurements sparse in time, a continuous-discrete growth model is proposed. The method is applied to a longitudinal dataset of diffusion-tensor magnetic resonance brain images of developing macaque monkeys with time-points at ages 2 weeks, 3 months, and 6 months.

JF - MICCAI, International Workshop on Spatio-Temporal Image Analysis for Longitudinal and Time-Series Image Data ER - TY - CONF T1 - Physically-based deformable image registration with material property and boundary condition estimation T2 - International Symposium of Biomedical Imaging (ISBI) Y1 - 2010 A1 - H. P. Lee A1 - M. Foskey A1 - Niethammer, M A1 - M. Lin AB -We propose a new deformable medical image registration method that uses a physically-based simulator and an iterative optimizer to estimate the simulation parameters determining the deformation field between the two images. Although a simulation-based registration method can enforce physical constraints exactly and considers different material properties, it requires hand adjustment of material properties, and boundary conditions cannot be acquired directly from the images. We treat the material properties and boundary conditions as parameters for the optimizer, and integrate the physically-based simulation into the optimization loop to generate a physically accurate deformation automatically.

JF - International Symposium of Biomedical Imaging (ISBI) N1 -Proceedings of the International Symposium on Biomedical Imaging (ISBI)

ER - TY - CONF T1 - Prediction-driven Respiratory Motion Atlas Formation for 4D Image-guided Radiation Therapy in Lung T2 - MICCAI, International Workshop on Pulmonary Image Analysis Y1 - 2010 A1 - X. Liu A1 - B. C. Davis A1 - Niethammer, M A1 - S. M. Pizer A1 - G. S. Mageras AB -Respiratory motion challenges lung radiation therapy with uncertainties of the location of important anatomical structures in the thorax. To capture the trajectory of the motion, dense image matching methods and learning-based motion prediction methods have been commonly used. However, both methods have limitations. Serious motion artifacts in treatment-guidance images, such as streak artifacts in respiration-correlated cone-beam CT, challenge the intensity-based image matching; the learning-based prediction methods require consistency between the training data for planning and the data for treatment. This paper proposes a prediction-driven motion atlas framework for motion estimation with artifact-laden images, using a Frechet-mean-image matching scheme that is softly constrained by deformation predictions. In this framework, all the respiration phase-stamped images within a breathing cycle are dieomorphically deformed to their Frechet mean. The iterative optimization is driven by both intensity matching forces and the prediction forces trained from patient-specic planning images. The effectiveness of the framework is demonstrated with computational phantom and real cone-beam CT images.

JF - MICCAI, International Workshop on Pulmonary Image Analysis ER - TY - CONF T1 - Robust model-based transformation and averaging of diffusion weighted images – applied to diffusion weighted atlas construction T2 - MICCAI, International Workshop on Computational Diffusion MRI (CDMRI' 10) Y1 - 2010 A1 - Niethammer, M A1 - Y. Shi A1 - S. Benzaid A1 - M. Sanchez A1 - Styner, M AB -This paper describes a method for model-based averaging of sets of diusion weighted magnetic resonance images (DW-MRI) under space transformations (resulting for example from registration methods). A robust weighted least squares method is developed. Synthetic validation experiments show the improvement of the proposed estimation method in comparison to standard least squares estimation. The developed method is applied to construct an atlas of diffusion weighted images for a set of macaques, allowing for a more exible representation of average diffusion information compared to standard diffusion tensor atlases.

JF - MICCAI, International Workshop on Computational Diffusion MRI (CDMRI' 10) ER - TY - JOUR T1 - Shape analysis of the neostriatum in subtypes of frontotemporal lobar degeneration: neuroanatomically significant regional morphologic change JF - Psychiatry Research – Neuroimaging Y1 - 2010 A1 - J. C. L. Looi A1 - M. Walterfang A1 - Styner, M A1 - Niethammer, M A1 - L. Svensson A1 - O. Lindberg A1 - P. Ostberg A1 - L. Botes A1 - E. Orndahl A1 - P. Chua A1 - D. Velakoulis A1 - L.-O. Wahlund AB - Frontostriatal circuit mediated cognitive dysfunction has been implicated in frontotemporal lobar degeneration (FTLD) and may differ across subtypes of FTLD. We manually segmented the neostriatum (caudate nucleus and putamen) in FTLD subtypes: behavioral variant frontotemporal dementia, FTD, n=12; semantic dementia, SD, n=13; and progressive nonfluent aphasia, PNFA, n=9); in comparison with controls (n=27). Diagnoses were based on international consensus criteria. Manual bilateral segmentation of the caudate nucleus and putamen was conducted blind to diagnosis by a single analyst, on MRI scans using a standardized protocol. Intra-cranial volume was calculated via a stereological point counting technique and was used for normalizing the shape analysis. Segmented binaries were analyzed using the SPHARM Shape Analysis tools (University of North Carolina) to perform comparisons between FTLD subtypes and controls for global shape difference, local significance maps and mean magnitude maps of shape displacement. Shape analysis revealed that there was significant shape difference between FTLD subtypes and controls, consistent with the predicted frontostriatal dysfunction and of significant magnitude, as measured by displacement maps. These differences were not significant for SD compared to controls; lesser for PNFA compared to controls; whilst FTD showed a more specific pattern in regions relaying fronto- and cortico-striatal circuits. Shape analysis shows regional specificity of atrophy, manifest as shape deflation, with a differential between FTLD subtypes, compared to controls.

accepted for publication

ER - TY - CONF T1 - User-driven 3D mesh region targeting Y1 - 2010 A1 - P. Karasev A1 - J. Malcolm A1 - Niethammer, M A1 - Kikinis, R A1 - Tannenbaum, A AB -We present a method for the fast selection of a region on a 3D mesh using geometric information. This is done using a weighted arc length minimization with a conformal factor based on the mean curvature of the 3D surface. A careful analysis of the geometric estimation process enables our geometric curve shortening to use a reliable smooth estimate of curvature and its gradient. The result is a robust way for a user to easily interact with particular regions of a 3D mesh construced from medical imaging. We describe the applicability of the method for real-time clinician use. In this study, we focus on building a robust and semi-automatic method for extracting selected folds on the cortical surface, specically for isolating gyri by drawing a curve along the surrounding sulci. It is desirable to make this process semi-automatic because manually drawing a curve through the complex 3D mesh is extremely tedious, while automatic methods cannot realistically be expected to select the exact closed contour a user desires for a given dataset. In the technique described here, a user places a handful of seed points surrounding the gyri of interest; an initial curve is made from these points which then evolves to capture the region. We refer to this user-driven procedure as targeting or selection interchangeably.

N1 -in press; Proceedings of SPIE Medical Imaging

ER - TY - JOUR T1 - Calcium and cyclic nucleotides affect TNF-alpha-induced stem cell migration. JF - Biochemical and biophysical research communications Y1 - 2009 A1 - Kaplan, Emel A1 - Min, Jiang-Yong A1 - Ke, Qingen A1 - Chen, Yu A1 - Niethammer, Marc A1 - Rana, Jamal S A1 - Malek, Sohail A1 - Verheugt, Freek W A A1 - Morgan, James P AB -The purpose of this study was to study the effect of calcium, cyclic AMP (cAMP) and cyclic GMP (cGMP) on embryonic stem cell (ESC) motility during TNF-alpha-induced chemotaxis. ESCs were monitored using a chemotaxis chamber, with different concentrations of calcium or cAMP or cGMP added to the medium. Changes in intracellular calcium ([Ca(2+)](i)) were measured with the fluorescent dye fura-2/AM. We combined migratory parameters in a mathematical model and described it as "mobility". After adding calcium, a dose-dependant increase in cell speed was found. Cyclic AMP increased mobility as well as the [Ca(2+)](i). In contrast, adding dbcGMP resulted in a significant decrease in the mobility of the ESCs. During migration ESCs showed an increase in [Ca(2+)](i). Furthermore, TNF-alpha dramatically increased the movement as well as the directionality of ESCs. These results demonstrate that ESCs are highly motile and respond to different concentrations of calcium in a dose-related manner.

VL - 382 IS - 2 U1 -http://www.ncbi.nlm.nih.gov/pubmed/19233128?dopt=Abstract

ER - TY - CONF T1 - Continuous Maximal Flows and Wulff Shapes: Application to MRFs T2 - Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) Y1 - 2009 A1 - Zach, C A1 - Niethammer, M A1 - J.-M. Frahm AB -Convex and continuous energy formulations for low level vision problems enable efficient search procedures for the corresponding globally optimal solutions. In this work we extend the well-established continuous, isotropic capacity based maximal flow framework to the anisotropic setting. By using powerful results from convex analysis, a very simple and efficient minimization procedure is derived. Further, we show that many important properties carry over to the new anisotropic framework, e.g. globally optimal binary results can be achieved simply by thresholding the continuous solution. In addition, we unify the anisotropic continuous maximal flow approach with a recently proposed convex and continuous formulation for Markov random fields, thereby allowing more general smoothness priors to be incorporated. Dense stereo results are included to illustrate the capabilities of the proposed approach.

JF - Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) ER - TY - CONF T1 - Cortical Correspondence with Probabilistic Fiber Connectivity T2 - Proceedings of the Conference on Information Processing in Medical Imaging (IPMI) Y1 - 2009 A1 - Oguz, I A1 - Niethammer, M A1 - Cates, J A1 - Whitaker, R A1 - Fletcher, T A1 - Styner, M AB -This paper presents a novel method of optimizing pointbased correspondence among populations of human cortical surfaces by combining structural cues with probabilistic connectivity maps. The proposed method establishes a tradeo between an even sampling of the cortical surfaces (a low surface entropy) and the similarity of corresponding points across the population (a low ensemble entropy). The similarity metric, however, isn't constrained to be just spatial proximity, but uses local sulcal depth measurements as well as probabilistic connectivity maps, computed from DWI scans via a stochastic tractography algorithm, to enhance the correspondence denition. We propose a novel method for projecting this ber connectivity information on the cortical surface, using a surface evolution technique. Our cortical correspondence method does not require a spherical parameterization. Experimental results are presented, showing improved correspondence quality demonstrated by a cortical thickness analysis, as compared to correspondence methods using spatial metrics as the sole correspondence criterion.

JF - Proceedings of the Conference on Information Processing in Medical Imaging (IPMI) ER - TY - CONF T1 - Globally Optimal Finsler Active Contours T2 - DAGM Y1 - 2009 A1 - Zach, C A1 - L. Shan A1 - J.-M. Frahm A1 - Niethammer, M AB -We present a continuous and convex formulation for Finsler active contours using seed regions or utilizing a regional bias term. The utilization of general Finsler metrics instead of Riemannian metrics allows the segmentation boundary to favor appropriate locations (e.g. with strong image discontinuities) and suitable directions (e.g. aligned with dark to bright image gradients). Strong edges are not required everywhere along the desired segmentation boundary due to incorporation of a regional bias. The resulting optimization procedure is simple and efficient, and leads to binary segmentation results regardless of the underlying continuous formulation. We demonstrate the proposed method in several examples.

JF - DAGM N1 -DAGM-Symposium

ER - TY - JOUR T1 - Laplace-Beltrami Eigenvalues and Topological Features of Eigenfunctions for Statistical Shape Analysis. JF - Computer aided design Y1 - 2009 A1 - Reuter, M A1 - Wolter, FE A1 - Shenton, M A1 - Niethammer, M AB -This paper proposes the use of the surface based Laplace-Beltrami and the volumetric Laplace eigenvalues and -functions as shape descriptors for the comparison and analysis of shapes. These spectral measures are isometry invariant and therefore allow for shape comparisons with minimal shape pre-processing. In particular, no registration, mapping, or remeshing is necessary. The discriminatory power of the 2D surface and 3D solid methods is demonstrated on a population of female caudate nuclei (a subcortical gray matter structure of the brain, involved in memory function, emotion processing, and learning) of normal control subjects and of subjects with schizotypal personality disorder. The behavior and properties of the Laplace-Beltrami eigenvalues and -functions are discussed extensively for both the Dirichlet and Neumann boundary condition showing advantages of the Neumann vs. the Dirichlet spectra in 3D. Furthermore, topological analyses employing the Morse-Smale complex (on the surfaces) and the Reeb graph (in the solids) are performed on selected eigenfunctions, yielding shape descriptors, that are capable of localizing geometric properties and detecting shape differences by indirectly registering topological features such as critical points, level sets and integral lines of the gradient field across subjects. The use of these topological features of the Laplace-Beltrami eigenfunctions in 2D and 3D for statistical shape analysis is novel.

VL - 41 IS - 10 U1 -http://www.ncbi.nlm.nih.gov/pubmed/20161035?dopt=Abstract

U3 -20161035

U4 -2009-10-01 12:00:00

JO - Comput Aided Des ER - TY - CONF T1 - A method for normalizing histology slides for quantitiative analysis T2 - Proceedings of the International Symposium on Biomedical Imaging (ISBI) Y1 - 2009 A1 - M. Macenko A1 - Niethammer, M A1 - J.S. Marron A1 - D. Borland A1 - J.T. Woosley A1 - X. Guan A1 - C. Schmitt A1 - N.E. Thomas AB -Inconsistencies in the preparation of histology slides make it difficult to perform quantitative analysis on their results. In this paper we provide two mechanisms for overcoming many of the known inconsistencies in the staining process, thereby bringing slides that were processed or stored under very different conditions into a common, normalized space to enable improved quantitative analysis.

JF - Proceedings of the International Symposium on Biomedical Imaging (ISBI) ER - TY - JOUR T1 - Multidimensional classification of hippocampal shape features discriminates Alzheimer's disease and mild cognitive impairment from normal aging. JF - NeuroImage Y1 - 2009 A1 - Gerardin, E A1 - Chételat, G A1 - Chupin, M A1 - Cuingnet, R A1 - Desgranges, B A1 - Kim, HS A1 - Niethammer, M A1 - Dubois, B A1 - Lehéricy, S A1 - Garnero, L A1 - Eustache, F A1 - Colliot, O AB -We describe a new method to automatically discriminate between patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and elderly controls, based on multidimensional classification of hippocampal shape features. This approach uses spherical harmonics (SPHARM) coefficients to model the shape of the hippocampi, which are segmented from magnetic resonance images (MRI) using a fully automatic method that we previously developed. SPHARM coefficients are used as features in a classification procedure based on support vector machines (SVM). The most relevant features for classification are selected using a bagging strategy. We evaluate the accuracy of our method in a group of 23 patients with AD (10 males, 13 females, age+/-standard-deviation (SD)=73+/-6 years, mini-mental score (MMS)=24.4+/-2.8), 23 patients with amnestic MCI (10 males, 13 females, age+/-SD=74+/-8 years, MMS=27.3+/-1.4) and 25 elderly healthy controls (13 males, 12 females, age+/-SD=64+/-8 years), using leave-one-out cross-validation. For AD vs controls, we obtain a correct classification rate of 94%, a sensitivity of 96%, and a specificity of 92%. For MCI vs controls, we obtain a classification rate of 83%, a sensitivity of 83%, and a specificity of 84%. This accuracy is superior to that of hippocampal volumetry and is comparable to recently published SVM-based whole-brain classification methods, which relied on a different strategy. This new method may become a useful tool to assist in the diagnosis of Alzheimer's disease.

VL - 47 UR - http://linkinghub.elsevier.com/retrieve/pii/S1053-8119(09)00548-5 IS - 4 U1 -http://www.ncbi.nlm.nih.gov/pubmed/19463957?dopt=Abstract

U3 -19463957

U4 -2009-10-01 12:00:00

JO - Neuroimage ER - TY - JOUR T1 - Near-tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation. JF - NeuroImage Y1 - 2009 A1 - Niethammer, M A1 - Zach, C A1 - Melonakos, J A1 - Tannenbaum, A AB -This paper proposes a methodology to segment near-tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. Segmentation is achieved through simple global statistical modeling of diffusion orientation. Utilizing a modification of a recent segmentation approach by Bresson et al. allows for a convex optimization formulation of the segmentation problem, combining orientation statistics and spatial regularization. The approach compares favorably with segmentation by full-brain streamline tractography.

VL - 45 UR - http://linkinghub.elsevier.com/retrieve/pii/S1053-8119(08)01198-1 IS - 1 Suppl U1 -http://www.ncbi.nlm.nih.gov/pubmed/19101640?dopt=Abstract

U3 -19101640

U4 -2009-03-01 12:00:00

JO - Neuroimage ER - TY - CONF T1 - An optimal control approach for deformable registration T2 - Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA) Y1 - 2009 A1 - G. Hart A1 - Zach, C A1 - Niethammer, M AB -This paper addresses large-displacement-diffeomorphic mapping registration from an optimal control perspective. This viewpoint leads to two complementary formulations. One approach requires the explicit computation of coordinate maps, whereas the other is formulated strictly in the image domain (thus making it also applicable to manifolds which require multiple coordinate charts). We discuss their intrinsic relation as well as the advantages and disadvantages of the two approaches. Further, we propose a novel formulation for unbiased image registration, which naturally extends to the case of time-series of images. We discuss numerical implementation details and carefully evaluate the properties of the alternative algorithms.

JF - Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA) ER - TY - CONF T1 - An Optimal Control Approach for the Registration of Image Time Series Y1 - 2009 A1 - Niethammer, M A1 - G. Hart A1 - Zach, C AB -This paper discusses an optimal control approach for the registration of image time-series (growth modeling). It combines and augments work on an optimal control formulation to optical flow with theory from large-displacement diffeomorphic image registration. The unification of the two viewpoints leads to (i) a more efficient computation of the gradient of the optimization problem, (ii) an easier numerical implementation, and (iii) an intuitive interpretation of the adjoint equation underlying the optimization problem. Further, a novel formulation for the unbiased estimation of image correspondences across time is proposed.

N1 -Proceedings of the Conference on Decision and Control (CDC)

ER - TY - JOUR T1 - Quantitative examination of a novel clustering method using magnetic resonance diffusion tensor tractography. JF - NeuroImage Y1 - 2009 A1 - Voineskos, AN A1 - O'Donnell, LJ A1 - Lobaugh, NJ A1 - Markant, D A1 - Ameis, SH A1 - Niethammer, M A1 - Mulsant, BH A1 - Pollock, BG A1 - Kennedy, JL A1 - Westin, CF A1 - Shenton, ME AB - MR diffusion tensor imaging (DTI) can measure and visualize organization of white matter fibre tracts in vivo. DTI is a relatively new imaging technique, and new tools developed for quantifying fibre tracts require evaluation. The purpose of this study was to compare the reliability of a novel clustering approach with a multiple region of interest (MROI) approach in both healthy and disease (schizophrenia) populations. DTI images were acquired in 20 participants (n=10 patients with schizophrenia: 56+/-15 years; n=10 controls: 51+/-20 years) (1.5 T GE system) with diffusion gradients applied in 23 non-collinear directions, repeated three times. Whole brain seeding and creation of fibre tracts were then performed. Interrater reliability of the clustering approach, and the MROI approach, were each evaluated and the methods compared. There was high spatial (voxel-based) agreement within and between the clustering and MROI methods. Fractional anisotropy, trace, and radial and axial diffusivity values showed high intraclass correlation (p<0.001 for all tracts) for each approach. Differences in scalar indices of diffusion between the clustering and MROI approach were minimal. The excellent interrater reliability of the clustering method and high agreement with the MROI method, quantitatively and spatially, indicates that the clustering method can be used with confidence. The clustering method avoids biases of ROI drawing and placement, and, not limited by a priori predictions, may be a more robust and efficient way to identify and measure white matter tracts of interest. VL - 45 UR - http://linkinghub.elsevier.com/retrieve/pii/S1053-8119(08)01281-0 IS - 2 U1 - http://www.ncbi.nlm.nih.gov/pubmed/19159690?dopt=Abstract U3 - 19159690 U4 - 2009-04-01 12:00:00 JO - Neuroimage ER - TY - JOUR T1 - Shape abnormalities of caudate nucleus in schizotypal personality disorder. JF - Schizophrenia research Y1 - 2009 A1 - Levitt, James J A1 - Styner, Martin A1 - Niethammer, Marc A1 - Bouix, Sylvain A1 - Koo, Min-Seong A1 - Voglmaier, Martina M A1 - Dickey, Chandlee C A1 - Niznikiewicz, Margaret A A1 - Kikinis, Ron A1 - McCarley, Robert W A1 - Shenton, Martha E AB -BACKGROUND: Previously, we reported abnormal volume and global shape in the caudate nucleus in schizotypal personality disorder (SPD). Here, we use a new shape measure which importantly permits local in addition to global shape analysis, as well as local correlations with behavioral measures. METHODS: Thirty-two female and 15 male SPDs, and 29 female and 14 male normal controls (NCLs), underwent brain magnetic resonance imaging (MRI). We assessed caudate shape measures using spherical harmonic-point distribution model (SPHARM-PDM) methodology. RESULTS: We found more pronounced global shape differences in the right caudate in male and female SPD, compared with NCLs. Local shape differences, principally in the caudate head, survived statistical correction on the right. Also, we performed correlations between local surface deformations with clinical measures and found significant correlations between local shape deflated deformations in the anterior medial surface of the caudate with verbal learning capacity in female SPD. CONCLUSIONS: Using SPHARM-PDM methodology, we found both global and local caudate shape abnormalities in male and female SPD, particularly right-sided, and largely restricted to limbic and cognitive anterior caudate. The most important and novel findings were bilateral statistically significant correlations between local surface deflations in the anterior medial surface of the head of the caudate and verbal learning capacity in female SPD. By extension, these local caudate correlation findings implicate the ventromedial prefrontal cortex (vmPFC), which innervates that area of the caudate, and demonstrate the utility of local shape analysis to investigate the relationship between specific subcortical and cortical brain structures in neuropsychiatric conditions.

VL - 110 IS - 1-3 U1 -http://www.ncbi.nlm.nih.gov/pubmed/19328654?dopt=Abstract

ER - TY - CONF T1 - Fast Global Labeling for Real-Time Stereo Using Multiple Plane Sweeps T2 - Vision, Modeling and Visualization Workshop (VMV) Y1 - 2008 A1 - Zach, C A1 - D. Gallup A1 - J.-M. Frahm A1 - Niethammer, M AB -This work presents a real-time, data-parallel approach for global label assignment on regular grids. The labels are selected according to a Markov random field energy with a Potts prior term for binary interactions. We apply the proposed method to accelerate the cleanup step of a real-time dense stereo method based on plane sweeping with multiple sweeping directions, where the label set directly corresponds to the employed directions. In this setting the Potts smoothness model is suitable, since the set of labels does not possess an intrinsic metric or total order. The observed run-times are approximately 30 times faster than the ones obtained by graph cut approaches.

JF - Vision, Modeling and Visualization Workshop (VMV) ER - TY - JOUR T1 - Geometric observers for dynamically evolving curves. JF - IEEE transactions on pattern analysis and machine intelligence Y1 - 2008 A1 - Niethammer, M A1 - Vela, PA A1 - Tannenbaum, A AB -This paper proposes a deterministic observer framework for visual tracking based on non-parametric implicit (level-set) curve descriptions. The observer is continuous-discrete, with continuous-time system dynamics and discrete-time measurements. Its state-space consists of an estimated curve position augmented by additional states (e.g., velocities) associated with every point on the estimated curve. Multiple simulation models are proposed for state prediction. Measurements are performed through standard static segmentation algorithms and optical-flow computations. Special emphasis is given to the geometric formulation of the overall dynamical system. The discrete-time measurements lead to the problem of geometric curve interpolation and the discrete-time filtering of quantities propagated along with the estimated curve. Interpolation and filtering are intimately linked to the correspondence problem between curves. Correspondences are established by a Laplace-equation approach. The proposed scheme is implemented completely implicitly (by Eulerian numerical solutions of transport equations) and thus naturally allows for topological changes and subpixel accuracy on the computational grid.

VL - 30 UR - http://doi.ieeecomputersociety.org/10.1109/TPAMI.2008.28 IS - 6 U1 -http://www.ncbi.nlm.nih.gov/pubmed/18421113?dopt=Abstract

U3 -18421113

U4 -2008-06-01 12:00:00

JO - IEEE Trans Pattern Anal Mach Intell ER - TY - JOUR T1 - Knowledge-Based Segmentation for Tracking Through Deep Turbulence JF - IEEE Transactions on Control Systems Technology Y1 - 2008 A1 - Vela, PA A1 - Niethammer, M A1 - G. D. Pryor A1 - A. R. Tannenbaum A1 - R. Butts A1 - D. Washburn AB -A combined knowledge-based segmentation/active contour algorithm is used for target tracking through turbulence. The algorithm utilizes Bayesian modeling for segmentation of noisy imagery obtained through longrange, laser imaging of a distance target, and active contours for tip tracking. The algorithm demonstrates improved target tracking performance when compared to weighted centroiding. Open-loop and closed-loop comparisons of the algorithms using simulated imagery validate the hypothesis.

VL - 16 UR - https://smartech.gatech.edu/bitstream/handle/1853/29151/2006_IEEE_08.pdf?... ER - TY - JOUR T1 - Restoration of DWI data using a Rician LMMSE estimator. JF - IEEE transactions on medical imaging Y1 - 2008 A1 - Aja-Fernandez, S A1 - Niethammer, M A1 - Kubicki, M A1 - Shenton, ME A1 - Westin, CF AB -This paper introduces and analyzes a linear minimum mean square error (LMMSE) estimator using a Rician noise model and its recursive version (RLMMSE) for the restoration of diffusion weighted images. A method to estimate the noise level based on local estimations of mean or variance is used to automatically parametrize the estimator. The restoration performance is evaluated using quality indexes and compared to alternative estimation schemes. The overall scheme is simple, robust, fast, and improves estimations. Filtering diffusion weighted magnetic resonance imaging (DW-MRI) with the proposed methodology leads to more accurate tensor estimations. Real and synthetic datasets are analyzed.

VL - 27 UR - http://dx.doi.org/10.1109/TMI.2008.920609 IS - 10 U1 -http://www.ncbi.nlm.nih.gov/pubmed/18815091?dopt=Abstract

U3 -18815091

U4 -2008-10-01 12:00:00

JO - IEEE Trans Med Imaging ER - TY - CONF T1 - SPHARM detects hippocampal subfield pathology in temporal lobe epilepsy T2 - Proceedings of the ISMRM Y1 - 2008 A1 - H. Kim A1 - Niethammer, M A1 - B. C. Bernhardt A1 - Bouix, S A1 - N. Bernasconi A1 - A. Bernasconi AB -Our purpose was to detect volume changes in the hippocampal subfields of patients with pharmacoresistant temporal lobe epilepsy (TLE) using SPHARM, a surface-based shape analysis method. We studied 95 TLE patients with unilateral hippocampal atrophy on MR volumetry and 46 controls. SPHARM applied to manual hippocampal labels measured a distance at each vertex between groups. In more than 40% of patients, we found a bilateral CA1 inward deformation more marked ipsilateral to the focus. These changes were negatively correlated with disease duration. Predominant CA1 atrophy with relative sparing of other subfields is in agreement with histopathological hippocampal sclerosis.

JF - Proceedings of the ISMRM ER - TY - CONF T1 - Tubular Fiber Bundle Segmentation for Diffusion Weighted Imaging T2 - Diffusion Weighted Imaging Workshop, MICCAI Y1 - 2008 A1 - Niethammer, M A1 - Zach, C A1 - Melonakos, J A1 - Tannenbaum, A AB -This paper proposes a methodology to segment tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. Segmentation is achieved through simple global statistical modeling of diffusion orientation. Utilizing a modification of a recent segmentation approach by Bresson et al. [19] allows for a convex optimization formulation of the segmentation problem, combining orientation statistics and spatial regularization. The approach compares favorably with segmentation by full-brain streamline tractography.

JF - Diffusion Weighted Imaging Workshop, MICCAI ER - TY - CONF T1 - Tubular Surface Evolution for Segmentation of the Cingulum Bundle from DW-MRI T2 - Foundations of Computational Anatomy Workshop, MICCAI Y1 - 2008 A1 - Mohan, V A1 - G. Sundaramoorthi A1 - Melonakos, J A1 - Niethammer, M A1 - Kubicki, M A1 - Tannenbaum, A AB -This work provides a framework for modeling and extracting the Cingulum Bundle (CB) from Diffusion-Weighted Imagery (DW-MRI) of the brain. The CB is a tube-like structure in the brain that is of potentially of tremendous importance to clinicians since it may be helpful in diagnosing Schizophrenia. This structure consists of a collection of fibers in the brain that have locally similar diffusion patterns, but vary globally. Standard region-based segmentation techniques adapted to DW-MRI are not suitable here because the diffusion pattern of the CB cannot be described by a global set of simple statistics. Active surface models extended to DW-MRI are not suitable since they allow for arbitrary deformations that give rise to unlikely shapes, which do not respect the tubular geometry of the CB. In this work, we explicitly model the CB as a tube-like surface and construct a general class of energies defined on tube-like surfaces. An example energy of our framework is optimized by a tube that encloses a region that has locally similar diffusion patterns, which differ from the diffusion patterns immediately outside. Modeling the CB as a tube-like surface is a natural shape prior. Since a tube is characterized by a center-line and a radius function, the method is reduced to a 4D (center-line plus radius) curve evolution that is computationally much less costly than an arbitrary surface evolution. The method also provides the center-line of CB, which is potentially of clinical significance.

JF - Foundations of Computational Anatomy Workshop, MICCAI UR - https://hal.inria.fr/inria-00632883 ER - TY - CONF T1 - Finsler Level Set Segmentation for Imagery in Oriented Domains Y1 - 2007 A1 - Mohan, V A1 - Melonakos, J A1 - Niethammer, M A1 - Kubicki, M A1 - Tannenbaum, A AB -In this paper, we present a novel directional level set segmentation framework employing the theory of Finsler active contours. The framework provides a natural way to perform segmentation of image data in oriented domains. We share examples of this technique on diffusion-weighted magnetic resonance imagery (DW-MRI) for the segmentation of neural fiber bundles and we show examples of texture based segmentation using structure tensors. We also demonstrate that for some applications higher accuracy is achieved by the proposed framework than by level set methods that employ Riemannian metrics. This gain is attributed to the relaxation of the tensor model constraint which is imposed upon the metric in the Riemannian case.

N1 -British Machine Vision Conference

ER - TY - CONF T1 - Finsler Tractography for White Matter Connectivity Analysis of the Cingulum Bundle T2 - Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2007 A1 - Melonakos, J A1 - Mohan, V A1 - Niethammer, M A1 - Smith, K A1 - Kubicki, M A1 - Tannenbaum, A AB -In this paper, we present a novel approach for the segmentation of white matter tracts based on Finsler active contours. This technique provides an optimal measure of connectivity, explicitly segments the connecting fiber bundle, and is equipped with a metric which is able to utilize the directional information of high angular resolution data. We demonstrate the effectiveness of the algorithm for segmenting the cingulum bundle.

JF - Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - CONF T1 - Geodesic-loxodromes for diffusion tensor interpolation and difference measurement. T2 - Medical image computing and computer-assisted intervention : MICCAI Y1 - 2007 A1 - Kindlmann, G A1 - Estépar, RS A1 - Niethammer, M A1 - Haker, S A1 - Westin, CF AB -In algorithms for processing diffusion tensor images, two common ingredients are interpolating tensors, and measuring the distance between them. We propose a new class of interpolation paths for tensors, termed geodesic-loxodromes, which explicitly preserve clinically important tensor attributes, such as mean diffusivity or fractional anisotropy, while using basic differential geometry to interpolate tensor orientation. This contrasts with previous Riemannian and Log-Euclidean methods that preserve the determinant. Path integrals of tangents of geodesic-loxodromes generate novel measures of over-all difference between two tensors, and of difference in shape and in orientation.

JF - Medical image computing and computer-assisted intervention : MICCAI VL - 10 IS - Pt 1 U1 -http://www.ncbi.nlm.nih.gov/pubmed/18051037?dopt=Abstract

U3 -18051037

U4 -2010-08-16 08:07:00

JO - Med Image Comput Comput Assist Interv ER - TY - CONF T1 - Global Medical Shape Analysis Using the Laplace-Beltrami Spectrum T2 - Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2007 A1 - Niethammer, M A1 - Reuter, M A1 - F.-E. Wolter A1 - Bouix, S A1 - Peinecke, N A1 - M.-S. Koo A1 - Shenton, ME AB -This paper proposes to use the Laplace-Beltrami spectrum (LBS) as a global shape descriptor for medical shape analysis, allowing for shape comparisons using minimal shape preprocessing: no registration, mapping, or remeshing is necessary. The discriminatory power of the method is tested on a population of female caudate shapes of normal control subjects and of subjects with schizotypal personality disorder.

JF - Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - CONF T1 - Global Medical Shape Analysis Using the Volumetric Laplace Spectrum T2 - Proceedings of the Cyberword Conference Y1 - 2007 A1 - Reuter, M A1 - Niethammer, M A1 - F.-E. Wolter A1 - Bouix, S A1 - Shenton, ME AB -This paper proposes to use the volumetric Laplace spectrum as a global shape descriptor for medical shape analysis. The approach allows for shape comparisons using minimal shape preprocessing. In particular, no registration, mapping, or remeshing is necessary. All computations can be performed directly on the voxel representations of the shapes. The discriminatory power of the method is tested on a population of female caudate shapes (brain structure) of normal control subjects and of subjects with schizotypal personality disorder. The behavior and properties of the volumetric Laplace spectrum are discussed extensively for both the Dirichlet and Neumann boundary condition showing advantages of the Neumann spectra. Both, the computations of spectra on 3D voxel data for shape matching as well as the use of the Neumann spectrum for shape analysis are completely new.

JF - Proceedings of the Cyberword Conference ER - TY - CONF T1 - Locally-Constrained Region-Based Methods for DW-MRI Segmentation Y1 - 2007 A1 - Melonakos, J A1 - Niethammer, M A1 - Mohan, V A1 - Kubicki, M A1 - J. Miller A1 - Tannenbaum, A AB -In this paper, we describe a method for segmenting fiber bundles from diffusion-weighted magnetic resonance images using a locally-constrained region based approach. From a pre-computed optimal path, the algorithm propagates outwardcapturing only those voxels whicharelocally connectedtothefiberbundle. Ratherthan attemptingtofind large numbers of open curves or single fibers, which individually have questionable meaning, this method segments the full fiberbundleregion. The strengthsof this approach include its ease-of-use, computational speed, and applicabilitytoawiderangeof fiberbundles.Inthiswork,weshow results for segmenting the cingulumbundle.Finally, weexplain how this approach and extensions thereto overcome a major problem that typical region-based flows experience when attempting to segment neural fiberbundles.

UR - http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3646532/ N1 -Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA)

ER - TY - CONF T1 - Outlier Rejection for Diffusion Weighted Imaging T2 - Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2007 A1 - Niethammer, M A1 - Bouix, S A1 - C.-F. Westin A1 - Shenton, ME AB -This paper introduces an outlier rejection and signal reconstruction method for high angular resolution diffusion weighted imaging. The approach is based on the thresholding of Laplacian measurements over the sphere of the apparent diffusion coefficient profiles defined for a given set of gradient directions. Exemplary results are presented.

JF - Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - CONF T1 - Segmenting Images Analytically in Shape Space T2 - Proceedings of the SPIE Medical Imaging Conference Y1 - 2007 A1 - Y. Rathi A1 - S. Dambreville A1 - Niethammer, M A1 - Tannenbaum, A A1 - Shenton, M AB -This paper presents a novel analytic technique to perform shape-driven segmentation. In our approach, shapes are represented using binary maps, and linear PCA is utilized to provide shape priors for segmentation. Intensity based probability distributions are then employed to convert a given test volume into a binary map representation, and a novel energy functional is proposed whose minimum can be analytically computed to obtain the desired segmentation in the shape space. We compare the proposed method with the log-likelihood based energy to elucidate some key differences. Our algorithm is applied to the segmentation of brain caudate nucleus and hippocampus from MRI data, which is of interest in the study of schizophrenia and Alzheimerâ€™s disease. Our validation (we compute the Hausdorff distance and the DICE coefficient between the automatic segmentation and ground-truth) shows that the proposed algorithm is very fast, requires no initialization and outperforms the log-likelihood based energy.

JF - Proceedings of the SPIE Medical Imaging Conference VL - 6914 ER - TY - CONF T1 - A variational framework combining level-sets and thresholding Y1 - 2007 A1 - S. Dambreville A1 - Niethammer, M A1 - A. Yezzi A1 - Tannenbaum, A AB -Segmentation involves separating distinct regions in an image. In this note, we present a novel variational approach to perform this task within the level-sets framework. We propose an energy functional that naturally combines two segmentation techniques usually applied separately: intensity thresholding and geometric active contours. Although our method can deal with more complex statistics, we assume that the pixel intensities of the regions have Gaussian distributions, in this work. The proposed approach affords interesting properties that can lead to sensible segmentation results.

N1 -British Machine Vision Conference

ER - TY - CONF T1 - A Variational Segmentation Framework Using Active Contours and Thresholding T2 - Proceedings of the International Conference on Signal and Image Processing (SIP) Y1 - 2007 A1 - S. Dambreville A1 - Niethammer, M A1 - A. Yezzi A1 - Tannenbaum, A AB -Segmentation involves separating distinct regions in an image. In this note, we present a novel variational approach to perform this task. We propose an energy functional that naturally combines two segmentation techniques usually applied separately: intensity thresholding and geometric active contours. Although our method can deal with more complex image statistics, intensity averages are used to separate regions, in this present work. The proposed approach affords interesting properties that can lead to sensible segmentation results.

JF - Proceedings of the International Conference on Signal and Image Processing (SIP) ER - TY - JOUR T1 - On the detection of simple points in higher dimensions using cubical homology. JF - IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Y1 - 2006 A1 - Niethammer, M A1 - Kalies, WD A1 - Mischaikow, K A1 - Tannenbaum, A AB -Simple point detection is an important task for several problems in discrete geometry, such as topology preserving thinning in image processing to compute discrete skeletons. In this paper, the approach to simple point detection is based on techniques from cubical homology, a framework ideally suited for problems in image processing. A (d-dimensional) unitary cube (for a d-dimensional digital image) is associated with every discrete picture element, instead of a point in epsilon(d) (the d-dimensional Euclidean space) as has been done previously. A simple point in this setting then refers to the removal of a unitary cube without changing the topology of the cubical complex induced by the digital image. The main result is a characterization of a simple point p (i.e., simple unitary cube) in terms of the homology groups of the (3d - 1) neighborhood of p for arbitrary, finite dimensions

VL - 15 IS - 8 U1 -http://www.ncbi.nlm.nih.gov/pubmed/16900699?dopt=Abstract

U3 -16900699

U4 -2006-08-01 12:00:00

JO - IEEE Trans Image Process ER - TY - CONF T1 - On Diffusion Tensor Estimation T2 - Proceedings of the International Engineering in Medicine and Biology Conference (EMBC) Y1 - 2006 A1 - Niethammer, M A1 - R. San Jose Estepar A1 - Bouix, S A1 - Shenton, M A1 - C.-F. Westin AB -In this paper we propose a formal formulation for the estimation of Diffusion Tensors in the space of symmetric positive semidefinite (PSD) tensors. Traditionally, diffusion tensor model estimation has been carried out imposing tensor symmetry without constraints for negative eigenvalues. When diffusion weighted data does not follow the diffusion model, due to noise or signal drop, negative eigenvalues may arise. An estimation method that accounts for the positive definiteness is desirable to respect the underlying principle of diffusion. This paper proposes such an estimation method and provides a theoretical interpretation of the result. A closed-form solution is derived that is the optimal data-fit in the matrix 2-norm sense, removing the need for optimization-based tensor estimation.

JF - Proceedings of the International Engineering in Medicine and Biology Conference (EMBC) ER - TY - JOUR T1 - Dynamic Active Contours for Visual Tracking JF - IEEE Transactions on Automatic Control Y1 - 2006 A1 - Niethammer, M A1 - Tannenbaum, A A1 - S. Angenent AB -Visual tracking using active contours is usually set in a static framework. The active contour tracks the object of interest in a given frame of an image sequence. A subsequent prediction step ensures good initial placement for the next frame. This approach is unnatural; the curve evolution gets decoupled from the actual dynamics of the objects to be tracked. True dynamical approaches exist, all being marker particle based and thus prone to the shortcomings of such particle-based implementations. In particular, topological changes are not handled naturally in this framework. The now classical level set approach is tailored for evolutions of manifolds of codimension one. However, dynamic curve evolution is at least a codimension two problem. We propose an efficient, level set based approach for dynamic curve evolution, which addresses the artificial separation of segmentation and prediction while retaining all the desirable properties of the level set formulation. It is based on a new energy minimization functional which, for the first time, puts dynamics into the geodesic active contour framework.

VL - 51 ER - TY - CONF T1 - Fiber Bundle Estimation and Parameterization T2 - Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2006 A1 - Niethammer, M A1 - Bouix, S A1 - C.-F. Westin A1 - Shenton, M AB -Individual white matter fibers cannot be resolved by current magnetic resonance (MR) technology. Many fibers of a fiber bundle will pass through an individual volume element (voxel). Individual visualized fiber tracts are thus the result of interpolation on a relatively coarse voxel grid, and an infinite number of them may be generated in a given volume by interpolation. This paper aims at creating a level set representation of a fiber bundle to describe this apparent continuum of fibers. It further introduces a coordinate system warped to the fiber bundle geometry, allowing for the definition of geometrically meaningful fiber bundle measures.

JF - Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) ER - TY - JOUR T1 - Lamb Wave Characterization by Differential Reassignment and Nonlinear Anisotropic Diffusion JF - NDT & E International Y1 - 2006 A1 - O. Kotte A1 - Niethammer, M A1 - Jacobs, LJ AB -This research develops an algorithm which provides excellent localization of Lamb wave dispersion curves while eliminating spurious components. This result is achieved by combining a differential reassignment procedure with non-linear anisotropic diffusion. This study examines the reassignment and diffusion components individually, before developing a combined algorithm. This combined algorithm is then applied to experimentally measured Lamb waves to develop an image of the dispersion curves of a plate with excellent clarity and definition. These dispersion curves are then used to increase the accuracy of a previously developed procedure to locate a notch.

VL - 39 ER - TY - CONF T1 - A Laplace Equation Approach for Shape Comparison T2 - Proceedings of the {SPIE} Medical Imaging Y1 - 2006 A1 - E. Pichon A1 - D. Nain A1 - Niethammer, M AB -In this paper we propose a principled approach for shape comparison. Given two surfaces, one to one correspondences are determined using the Laplace equation. The distance between corresponding points is then used to define both global and local dissimilarity statistics between the surfaces. This technique provides a powerful method to compare shapes both locally and globally for the purpose of segmentation, registration or shape analysis. For improved accuracy, we propose a Boundary Element Method. Our approach is applicable to datasets of any dimension and offers subpixel resolution. We illustrate the usefulness of the technique for validation of segmentation, by defining global dissimilarity statistics and visualizing errors locally on color-coded surfaces. We also show how our technique can be applied to multiple shapes comparison.

JF - Proceedings of the {SPIE} Medical Imaging VL - 6141 ER - TY - JOUR T1 - Model-based analysis of dispersion curves using chirplets. JF - The Journal of the Acoustical Society of America Y1 - 2006 A1 - Kuttig, H A1 - Niethammer, M A1 - Hurlebaus, S A1 - Jacobs, LJ AB -Time-frequency representations, like the spectrogram or the scalogram, are widely used to characterize dispersive waves. The resulting energy distributions, however, suffer from the uncertainty principle, which complicates the allocation of energy to individual propagation modes (especially when the dispersion curves of these modes are close to each other in the time-frequency domain). This research applies the chirplet as a tool to analyze dispersive wave signals based on a dispersion model. The chirplet transform, a generalization of both the wavelet and the short-time Fourier transform, enables the extraction of components of a signal with a particular instantaneous frequency and group delay. An adaptive algorithm identifies frequency regions for which quantitative statements can be made about an individual mode's energy, and employs chirplets (locally adapted to a dispersion curve model) to extract the (proportional) energy distribution of that single mode from a multimode dispersive wave signal. The effectiveness of this algorithm is demonstrated on a multimode synthetic Lamb wave signal for which the ground-truth energy distribution is known for each mode. Finally, the robustness of this algorithm is demonstrated on real, experimentally measured Lamb wave signals by an adaption of a correlation technique developed in previous research.

VL - 119 UR - http://link.aip.org/link/?jas/119/2122&agg=MEDLINE_JAS IS - 4 U1 -http://www.ncbi.nlm.nih.gov/pubmed/16642827?dopt=Abstract

U3 -16642827

U4 -2006-04-01 12:00:00

JO - J Acoust Soc Am ER - TY - CONF T1 - Statistical Shape Analysis of Brain Structures using Spherical Wavelets T2 - Proceedings of the Fourth IEEE International Symposium on Biomedical Imaging. Y1 - 2006 A1 - D. Nain A1 - Styner, M A1 - Niethammer, M A1 - Levitt, JJ A1 - Shenton, M A1 - G. Gerig A1 - Tannenbaum, A AB -We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests and a spherical wavelet (SWC) shape representation. As an application, we analyze two brain structures, the caudate nucleus and the hippocampus,and compare the results obtained to shape analysis using a sampled point representation. Our results show that the SWC representation indicates new areas of significance preserved under the FDR correction for both the left caudate nucleus and left hippocampus. Additionally, the spherical wavelet representation provides a natural way to interpret the significance results in terms of scale in addition to knowing the spatial location of the regions.

JF - Proceedings of the Fourth IEEE International Symposium on Biomedical Imaging. ER - TY - CONF T1 - Closed Loop Visual Tracking Using Observer-Based Dynamic Active Contours T2 - Proceedings of the Conference on Guidance Navigation and Control Y1 - 2005 A1 - Vela, PA A1 - Niethammer, M A1 - J. Malcolm A1 - Tannenbaum, A AB -This paper describes and demonstrates an algorithm to visually track ying vehicles in a leader-follower scenario. The algorithm consists of two nested control loops. One that assures a proper position estimation for the object(s) to be followed (the visual observer) and one that exploits this position estimation to control the maneuvers of the follower such that it pursues the leader. The visual observer is based on some novel geometric principles tailored to controlled active vision. In particular, we describe the use of dynamic active contours as motion priors for such geometrically motivated observers.

JF - Proceedings of the Conference on Guidance Navigation and Control ER - TY - JOUR T1 - On the Evolution of Vector Distance Functions of Closed Curves JF - International Journal of Computer Vision Y1 - 2005 A1 - Niethammer, M A1 - Vela, PA A1 - Tannenbaum, A AB -Inspired by the work by Gomes et al., we describe and analyze a vector distance function approach for the implicit evolution of closed curves of codimension larger than one. The approach is set up in complete generality, and then applied to the evolution of dynamic geometric active contours in R^4 (codimension three case).In order to carry this out one needs an explicit expression for the zero level set for which we propose a discrete connectivity method. This leads us to make connections with the new theory of cubical homology. We provide some explicit simulation results in order to illustrate the methodology.

This paper proposes a deterministic observer framework for visual tracking based on non-parametric implicit (level-set) curve descriptions. The observer is continuousdiscrete, with continuous-time system dynamics and discretetime measurements. Its state-space consists of an estimated curve position augmented by additional states (e.g., velocities) associated with every point on the estimated curve. Multiple simulation models are proposed for state prediction. Measurements are performed through standard static segmentation algorithms and optical-flow computations. Special emphasis is given to the geometric formulation of the overall dynamical system. The discrete-time measurements lead to the problem of geometric curve interpolation and the discrete-time filtering of quantities propagated along with the estimated curve. Interpolation and filtering are intimately linked to the correspondence problem between curves. Correspondences are established by a Laplace-equation approach. The proposed scheme is implemented completely implicitly (by Eulerian numerical solutions of transport equations) and thus naturally allows for topological changes and subpixel accuracy on the computational grid.

JF - Proceedings of the Conference on Decision and Control ER - TY - CONF T1 - Active Contours and Optical Flow for Automatic Tracking of Flying Vehicles T2 - Proceedings of the American Control Conference Y1 - 2004 A1 - J. Ha A1 - C. Alvino A1 - G. Pryor A1 - Niethammer, M A1 - E. Johnson A1 - Tannenbaum, A AB -In this paper, we describe fast implementations of optical flow and geometric active contours to reliably track flying vehicles. Given the position of the vehicle at time t - 1, optical flow information is used to initially place an active contour in the basin of attraction of a region of interest in a given dynamical image at time t. For real-time tracking, fast convergence of the active contour as wen as rapid computation of the optical flow are crucial. In this note, we will describe algorithms that make fast tracking possible in this framework using only standard computing platforms.

JF - Proceedings of the American Control Conference VL - 4 ER - TY - JOUR T1 - Area-based medial axis of planar curves JF - International Journal of Computer Vision Y1 - 2004 A1 - Niethammer, M A1 - S. Betelu A1 - G. Sapiro A1 - Tannenbaum, A A1 - P. J. Giblin AB -A new definition of affine invariant medial axis of planar closed curves is introduced. A point belongs to the affine medial axis if and only if it is equidistant from at least two points of the curve, with the distance being a minimum and given by the areas between the curve and its corresponding chords. The medial axis is robust, eliminating the need for curve denoising. In a dynamical interpretation of this affine medial axis, the medial axis points are the affine shock positions of the affine erosion of the curve. We propose a simple method to compute the medial axis and give examples. We also demonstrate how to use this method to detect affine skew symmetry in real images.

Visual tracking using active contours is usually accomplished in a static framework. The active contour tracks the object of interest in a given frame of an image sequence, and then a subsequent prediction step ensures good initial placement for the next frame. This approach is unnatural; the curve evolution gets decoupled from the actual dynamics of the objects to be tracked. True dynamic approaches exist, all being marker particle based, and thus prone to the shortcomings of such particle-based implementations. In particular, topological changes are not handled naturally in this framework. The now classical level set approach is tailored for codimension one evolutions. However, dynamic curve evolution is at least of codimension two. We propose a natural, efficient, level set based approach for dynamic curve evolution which removes the artificial separation of segmentation and prediction, while retaining all the desirable properties of level set formulations. This is based on a new energy minimization functional which for the first time puts dynamics into the geodesic active contour framework.

JF - Proceedings of the Conference on Computer Vision and Pattern Recognition. VL - 1 ER - TY - CONF T1 - Color histogram equalization through mesh deformation T2 - Proceedings of the International Conference on Image Processing Y1 - 2003 A1 - E. Pichon A1 - Niethammer, M A1 - G. Sapiro AB -In this paper we propose an extension of grayscale histogram equalization for color images. For aesthetic reasons, previously proposed color histogram equalization techniques do not generate uniform color histograms. Our method will always generate an almost uniform color histogram thus making an optimal use of the color space. This is particularly interesting for pseudo-color scientific visualization. The method is based on deforming a mesh in color space to fit the existing histogram and then map it to a uniform histogram. It is a natural extension of grayscale histogram equalization and it can be applied to spatial and color space of any dimension.

JF - Proceedings of the International Conference on Image Processing ER - TY - CONF T1 - Dynamic level sets for visual tracking T2 - Proceedings of the Conference on Decision and Control Y1 - 2003 A1 - Niethammer, M A1 - Tannenbaum, A AB -In this paper we describe two methods for tracking planar curves which are allowed to change topology. In contrast to previous approaches a level set formulation is used that allows for the propagation of state information (here a velocity vector) with every point on a curve. The curve dynamics are derived by minimizing an action integral (based on Hamilton's principle). Incorporating velocity information for every point on a curve lifts the originally two dimensional problem to four dimensions, and thus to a codimeusion three problem. Since basic level set approaches implicitly describe codimension one hypersurfaces, we introduce two methods suitable for codimension three problems within a level set framework. The partial level set approach, which propagates velocity information along with the curve by solving two additional transport equations, and the full level set approach, which is formulated by means of a vector distance function evolution equation. The full level set approach allow for complete topological flexibility (including intersecting curves in the image plane). However, it is computationally expensive. The partial level set approach compromises the topological flexibility for computational efficiency. In particular, the full level set ap proacb has the potential for tracking objects throughout occlusions, when combined with a suitable collision detection algorithm.

JF - Proceedings of the Conference on Decision and Control VL - 5 ER - TY - JOUR T1 - Localization of notches with Lamb waves. JF - The Journal of the Acoustical Society of America Y1 - 2003 A1 - Benz, R A1 - Niethammer, M A1 - Hurlebaus, S A1 - Jacobs, LJ AB -A time-frequency representation (TFR) is used to analyze the interaction of a multimode and dispersive Lamb wave with a notch, and then serves as the basis for a correlation technique to locate the notch. The experimental procedure uses a laser source and a dual-probe laser interferometer to generate and detect Lamb waves in a notched plate. The high fidelity, broad-bandwidth, point-like and noncontact nature of laser ultrasonics are critical to the success of this study, making it possible to experimentally measure transient Lamb waves without any frequency biases. A specific TFR, the reassigned spectrogram, is used to resolve the dispersion curves of the individual modes of the plate, and then the slowness-frequency representation (SFR) of the plate is calculated from this reassigned spectrogram. By considering the notch to be an additional (second) source, the reflected and transmitted contributions of each Lamb mode are automatically identified using the SFRs. These results are then used to develop a quantitative understanding of the interaction of an incident Lamb wave with a notch, helping to identify mode conversion. Finally, two complementary, automated localization techniques are developed based on this understanding of scattering of Lamb waves.

VL - 114 UR - http://link.aip.org/link/?jas/114/677&agg=MEDLINE_JAS IS - 2 U1 -http://www.ncbi.nlm.nih.gov/pubmed/12942951?dopt=Abstract

U3 -12942951

U4 -2003-08-01 12:00:00

JO - J Acoust Soc Am ER - TY - CONF T1 - A Stokes flow boundary integral measurement of tubular structure cross sections in two dimensions T2 - Proceedings of the International Conference on Image Processing Y1 - 2003 A1 - Niethammer, M A1 - E. Pichon A1 - Tannenbaum, A A1 - P. J. Mucha AB -In this paper we will develop a method to determine cross sections of arbitrary two-dimensional tubular structures, which are allowed to branch, by means of a Stokes flow based boundary integral formulation. The measure for the cross sections for a point on the boundary of a given structure will be the path obtained by integrating perpendicularly to the flow lines from one side of the boundary to the other. Special emphasis will be put on the behavior at branching points, the behavior at vortices, and the necessary boundary conditions. The method can be extended to three dimensional problems.

JF - Proceedings of the International Conference on Image Processing ER - TY - CONF T1 - Analysis of blood vessel topology by cubical homology T2 - Proceedings of the International Conference on Image Processing Y1 - 2002 A1 - Niethammer, M A1 - A. N. Stein A1 - Kalies, WD A1 - P. Pilarczyk A1 - Mischaikow, K A1 - Tannenbaum, A AB -In this note, we segment and topologically classify brain vessel data obtained from magnetic resonance angiography (MRA). The segmentation is done adaptively and the classification by means of cubical homology, i.e. the computation of homology groups. In this way the number of connected components (measured by H0), the tunnels (given by H1) and the voids (given by 2) are determined, resulting in a topological characterization of the blood vessels.

JF - Proceedings of the International Conference on Image Processing VL - 2 ER - TY - JOUR T1 - Automated methodology to locate notches with Lamb waves JF - Acoustic Research Letters Online Y1 - 2001 A1 - Hurlebaus, S A1 - Niethammer, M A1 - Jacobs, LJ A1 - C. Valle AB -This study develops an automated method capable of detecting notches in isotropic plates. Laser ultrasonic techniques are used to generate and detect Lamb waves in perfect and notched plates. These signals are first transformed into the time-frequency domain using a short time Fourier transform (STFT) and subsequently into the group velocity-frequency domain. Finally, the notch is located with an autocorrelation in the group velocity-frequency domain. A verification of the proposed methodology shows excellent agreement with the actual location of the notch.

VL - 2 ER - TY - JOUR T1 - Crack characterization using guided circumferential waves JF - Journal of the Acoustical Society of America Y1 - 2001 A1 - C. Valle A1 - Niethammer, M A1 - J. Qu A1 - Jacobs, LJ AB -This paper examines the propagation of guided circumferential waves in a hollow isotropic cylinder that contains a crack, with the goal of using these guided waves to both locate and size the crack. The crack is sized using a modified Auldâ€™s formula, which relates the crackâ€™s length to a reflected energy coefficient. The crack is then located by operating on the backscattered signal with a time-frequency digital signal processing (DSP) technique, and then comparing these results to those obtained if the cylinder is perfect. The guided circumferential waves are generated with a commercial finite element method (FEM) code. One objective of this work is to demonstrate the effectiveness of using sophisticated DSP techniques to describe the effect of scattering on dispersive waves, showing it is possible to characterize cracks systematically and accurately by quantifying this scattering effect. The results show that the need for high frequency signals to detect small cracks is significantly decreased by using these techniques.

VL - 110 ER - TY - CONF T1 - Parameter and derivative estimation for nonlinear continuous-time system identification T2 - Proceedings of the 5 th IFAC Symposium on Nonlinear Systems, (NOLCOS 01) Y1 - 2001 A1 - Niethammer, M A1 - P. H. Menold A1 - F. Allgöwer AB -In this note we investigate parameter identification for nonlinear continuous-time SISO systems, based on input/output data, where the output is assumed to be noise corrupted. Continuous-time identification requires (i) the estimation of derivatives of the output (which is nontrivial due to the influence of noise), a suitable measure thereof or a way to avoid them and (ii) methods for parameter estimation based on the measured data. Problem (i) is addressed by reviewing modulating functions and the concept of delayed state variable filters; furthermore a high-gain observer is introduced as an approach to provide the necessary derivative information. Its performance is investigated with respect to the modulating function and the delayed state variable filter approaches. Least-squares methods are assessed for continuous-time nonlinear identification (problem (ii)). It is shown that parameter identification based in modulating functions and a standard least-squares method does not guarantee bias-free estimates for some systems. Whereas ordinary (or weighted) least-squares is sufficient for parameter identification by means of modulating functions it is not for the delayed state variable filter and the high-gain observer approaches (due to dependencies between error terms). Requirements on least-squares methods for nonlinear continuous-time system identification are discusses and a solution for bilinear systems is given. The importance of an appropriate least-squares method is underlined by parameter identification for a simulated bilinear example system.

JF - Proceedings of the 5 th IFAC Symposium on Nonlinear Systems, (NOLCOS 01) ER - TY - JOUR T1 - Time-frequency representations of Lamb waves JF - Journal of the Acoustical Society of America Y1 - 2001 A1 - Niethammer, M A1 - Jacobs, LJ A1 - J. Qu A1 - J. Jarzynski AB -The objective of this study is to establish the effectiveness of four different time-frequency representations (TFRs): the reassigned spectrogram, the reassigned scalogram, the smoothed Wigner-Ville distribution, and the Hilbert spectrum by comparing their ability to resolve the dispersion relationships for Lamb waves generated and detected with optical techniques. This paper illustrates the utility of using TFRs to quantitatively resolve changes in the frequency content of these nonstationary signals, as a function of time. While each technique has certain strengths and weaknesses, the reassigned spectrogram appears to be the best choice to characterize multimode Lamb waves.

VL - 109 ER - TY - JOUR T1 - Time-frequency representation of Lamb waves using the reassigned spectrogram JF - Acoustic Research Letters Online Y1 - 2000 A1 - Niethammer, M A1 - Jacobs, LJ A1 - J. Qu A1 - J. Jarzynski AB -This brief note reports on a study that applies the reassigned spectrogram (the reassigned energy density spectrum of the short-time Fourier transform [STFT]) to develop the dispersion curves for multimode Lamb waves propagating in an aluminum plate. The proposed procedure first uses the spectrogram to operate on a single, laser-generated and detected waveform to develop the dispersion relationship for this plate. Next, a reassignment procedure is used to refine the time-frequency resolution of the calculated dispersion curves. This reassignment operation clarifies the definition of the measured modes. This study demonstrates that the reassigned spectrogram is capable of distinguishing multiple, closely spaced Lamb modes in the ultrasonic frequency range.

VL - 107 ER -