Journal of Imaging
Deep Learning Analysis of Routine Preoperative Knee Radiographs for Five-Year Prediction of Contralateral Arthroplasty
By Samer G. Salman, Rohan A. Phadke, Zane G. Salman and 7 others.
Abstract
Background
Before unilateral total knee arthroplasty (TKA), the contralateral radiograph is reduced to a Kellgren–Lawrence grade. We asked what the image adds, what the model reads, and how many views are needed.
Methods
A multi-view DenseNet121 survival network predicted 5-year contralateral arthroplasty from routine radiographs, against Cox models over 11 clinical variables with and without the dataset-inferred grade, on a once-read test split.
