Flexible non cartilage seeds for osteoarthritic magnetic resoance image of knee: Data from the osteoarthritis initiative

Difficulties in analyzing diseased knee cartilage is attributed to large anatomical variation caused by osteoarthritic features. Using expert initialization as crucial source of information, interactive method is very useful in osteoarthritic cartilage segmentation. However, high level of expert intervention remains an issue for existing interactive segmentation model. Therefore, a flexible seeds labelling method has been proposed to automatically cover non-cartilage tissue. Compared to manual segmentation, the proposed method lowers the processing time by 48% in observer 1 and 30% in observer 2. Besides, the proposed method has demonstrated high Dice's reproducibility of 0.80 for observer 1 and 0.82 for observer 2. In future, inter-observer reproducibility should be performed to analyze the progression of knee osteoarthritis.