Multicenter Study of YOLOv9 for Automated Detection and Classification of Supraspinatus Tendon Tears on MRI.
Authors
Affiliations (7)
Affiliations (7)
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao 266000, Shandong, China (X.Y., C.W., X.L., D.H., J.C.).
- School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, Shandong, China (Z.L., S.M.).
- Department of Sports Medicine, Affiliated Hospital of Qingdao University, Qingdao 266000, Shandong, China (H.J.).
- Department of Radiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Qingdao 266011, Shandong, China (X.X.).
- Department of Radiology, Dongying Hospital of Traditional Chinese Medicine, Dongying 257100, Shandong, China (T.H.).
- Department of Radiology, Zichuan District Hospital, Zibo 255100, Shandong, China (R.Z.).
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao 266000, Shandong, China (X.Y., C.W., X.L., D.H., J.C.). Electronic address: [email protected].
Abstract
This study develops a deep learning model using the You Only Look Once (YOLO) framework for the automated diagnosis of supraspinatus tendon tears (ST) based on multicenter MRI data. In this retrospective study, 1698 patients from five hospitals were included and allocated to training (n=1047), validation (n=299), test (n=154), and external test (n=198) sets. A YOLOv9-based automated model was developed using coronal fat-suppressed T2-weighted images for lesion detection, localization, and classification. Model performance was assessed using Intersection over Union and confusion matrices. Comparisons between model outputs and radiologist interpretations were performed with McNemar's test, and interobserver agreement among radiologists was evaluated using Cohen's kappa. The YOLOv9 model successfully identified the supraspinatus tendon layer in all images across the validation, test, and external test sets, achieving 100% accuracy. For ST tear detection, the model achieved accuracies of 69.0% (755/1094) in the validation set, 73.9% (414/560) in the test set, and 75.64% (559/739) in the external test set. For classification of partial- and full-thickness tears on the test set, the model demonstrated a macro F1 score of 77.7% (95% CI: 67.4-90.5), outperforming all radiologists (all P<0.05). The MRI-based YOLOv9 model excelled in diagnosing supraspinatus tendon tears, surpassing radiologists with varying levels of experience.