In this exploratory study, radiomic measures were computed across radiologist-segmented image patches within 3D-MSI STIR images collected on symptomatic total hip replacements (THR). Utilizing radiologist classifications of normal, infection, polymeric wear, or metallosis debris for each image patch, principle-component based cluster analysis was deployed to visualize and estimate radiomic distinctions between different soft-tissue pathology classifications. The study results offer insights to future studies seeking to utilize quantitative MR to characterize and classify soft-tissue complications near THR.
This abstract and the presentation materials are available to members only; a login is required.