Improving Robustness of Cartilage segmentation using IDEAL water and fat images

INTRODUCTION: Accurate and reliable quantification of cartilage volume in MRI is required for diagnosis of many degenerative and inflammatory diseases such as osteoarthritis or rheumatoid arthritis. Segmentation techniques are often challenged by the variation in the MRI data and anatomical shape of the cartilage. Many techniques were proposed based on region growing, active contours and model-based guidance to improve the cartilage detection [2-4]. IDEAL[1] water-fat suppression technique enhances the cartilage anatomy with better suppression of fat around it but the robustness challenge remains. In the present work, we propose a novel method using IDEAL water and fat images for robust segmentation of the anatomical features in knee MRI data.