Watershed segmentation of high resolution magnetic resonance images of articular cartilage of the knee
Soumya Ghosh, Olivier Beuf, Michael D. Ries, N.E. Lane, Lynne S. Steinbach, Thomas Marc Link, Sharmila Majumdar · 2002
High-resolution in-vivo Magnetic Resonance Imaging (MRI) can be used effectively to determine variation in cartilage morphometry - a crucial parameter for assessment of osteoarthritis. Segmentation of cartilage from surrounding tissues is a necessary preliminary step to the quantitation process. In this in-vivo study we implement the immersion based watershed algorithm to develop a novel and reliable cartilage segmentation technique. The protocol has been successfully applied to determine morphometric differences among normal, mild and severe osteoarthritic patient populations.