Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative

Abstract

Knee osteoarthritis is the second most dreadful disease after cardiovascular diseases. Affected patients will not have any effective cure and face the risk of undergoing total knee replacement in chronic stage. Quantitative analysis enhances our understanding of the pathophysiology of osteoarthritis. Nonetheless, manual segmentation is notorious for time- and resource-intensive. Hence, we propose a multilabel, semiautomated segmentation method based on random walks to facilitate the segmentation process. Random walks method is robust to noise, allows multiple objects segmentation and achieves global minimum solution. Our experiment results indicated that random walks achieved greater efficiency than manual segmentation while preserved the quality of knee cartilage segmentation as measured by the Dice's coefficient.