Objective Bi-Modal Assessment of Knee Osteoarthritis Severity Grades: Model and Mechanism

Knee osteoarthritis (KOA), a common musculoskeletal disorder, is typically diagnosed by assessing patients' X-rays. This method may have potential implications for health, especially with long-term and repeated examinations. In this study, we propose a KOA severity prediction (SP) model that utilizes bi-modal data, thermal image combined with personal health data, to objectively classify KOA severity into three categories, following the Kellgren-Lawrence (KL) grading criterion. We establish, for the first time, the KOA dataset and evaluate it with the KOA SP model, achieving the classification accuracy of 89.29%. The generalization of the KOA SP model is validated using data from the other centers, attaining the accuracy of 70.83%. The mechanism of KOA SP model is verified by utilizing the theory of thermal resistance in heat conduction and the anatomy of knee joint. The KOA SP model is developed by modeling handcrafted bi-modal features using gradient boosting tree, and we explain the reasons for not using deep neural networks, based on Vapnik-Chervonenkis dimension (VC dimension), from the perspective of the initial and appropriate feature representation of the task. The KOA SP model is anticipated to significantly alleviate the burden on physicians in assessing the severity of the disease, offering crucial supplementary data for knee disease diagnosis, thereby enhancing both efficiency and diagnostic precision in the KOA field. The KOA dataset and the corresponding code can be accessed publicly at https://github.com/chenjjsx/KOA.git.