Automatic Atlas-based Three-label Cartilage Segmentation from MR Knee Images

TitleAutomatic Atlas-based Three-label Cartilage Segmentation from MR Knee Images
Publication TypeConference Paper
Year of Publication2011
AuthorsShan L, Charles C, Niethammer M
Conference NameProceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA)
Abstract

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).

Full Text