Automated detection of patellofemoral osteoarthritis from knee lateral view radiographs using deep learning: data from the Multicenter Osteoarthritis Study (MOST)

Abstract

To assess the ability of imaging-based deep learning to detect radiographic patellofemoral osteoarthritis (PFOA) from knee lateral view radiographs. Knee lateral view radiographs were extracted from The Multicenter Osteoarthritis Study (MOST) public use datasets (n=18,436 knees). Patellar region-of-interest (ROI) was first automatically detected, and subsequently, end-to-end deep convolutional neural networks (CNNs) were trained and validated to detect the status of patellofemoral OA. Patellar ROI was detected using deep-learning-based object detection method. Atlas-guided visual assessment of PFOA status by expert readers provided in the MOST public use datasets was used as a classification outcome for the models. Performance of classification models was assessed using the area under the receiver operating characteristic curve (ROC AUC) and the average precision (AP) obtained from the Precision-Recall (PR) curve in the stratified 5-fold cross validation setting. Of the 18,436 knees, 3,425 (19%) had PFOA. AUC and AP for the reference model including age, sex, body mass index (BMI), the total Western Ontario and McMaster Universities Arthritis Index (WOMAC) score, and tibiofemoral Kellgren-Lawrence (KL) grade to detect PFOA were 0.806 and 0.478, respectively. The CNN model that used only image data significantly improved the classifier performance (ROC AUC=0.958, AP=0.862). We present the first machine learning based automatic PFOA detection method. Furthermore, our deep learning based model trained on patella region from knee lateral view radiographs performs better at detecting PFOA than models based on patient characteristics and clinical assessments.