Large-scale analysis of the relationship between learned qMRI biomarkers and chronic knee pain. 7,437 patient timepoints reporting chronic pain were used to train three different deep learning models for bone shape, cartilage thickness, and cartilage T2 biomarkers for the femur, tibia, and patella. The true chronic knee pain predictions for each trained model were further investigated with Grad-CAM and the max activation values for each model were sorted into clinically relevant anatomical compartments for each bone. Bone shape and cartilage T2 seemed to be spatially correlated based on the results of the analysis.
This abstract and the presentation materials are available to members only; a login is required.