Quantitative MRI Interpretable 100D Feature Space of Knee Osteoarthritis

While the Osteoarthritis Initiative data has been explored in independent studies, to our knowledge, never has such a comprehensive analysis been completed, investigating morphology of femur, patella, tibia, menisci, for biomarkers: cartilage thickness, cartilage T2, bone shape, and meniscus shape. With 4,796 subjects from the OAI, this study utilizes an automatic statistical shape modeling technique to create a 100D interpretable space of biomarker-tissue PC modes, which can be disseminated using an innovative opensource app. In combination with Image Twin and Clinical Twin analyses, variations in morphology, as well as clinical metadata, were identified as being significantly associated with osteoarthritis incidence.