High diagnostic accuracy of a resnet50-based deep learning model for osteochondral lesions of the talus on magnetic resonance imaging

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: T1-weighted: 94.1% accuracy, AUC 0.93; T2-weighted: 87.2% accuracy, AUC 0.91

• Primary Outcome: Diagnostic accuracy for detecting osteochondral lesions of the talus

• Nnt Or Sensitivity: T1 sequence: 82% recall (sensitivity equivalent), 92% precision for OLT cases

• Confidence Interval: T1 accuracy: 95% CI 88.3-97.1%; T2 accuracy: 95% CI 80.5-91.9%

Clinical Application

Requires significant computational infrastructure and integration with existing PACS systems; validation needed in diverse clinical settings Could potentially support radiologist workflow in Australian public hospitals facing imaging backlogs; would require TGA approval as medical device software; cost-effectiveness analysis needed for PBS consideration Patients undergoing ankle MRI for suspected osteochondral lesions, particularly when T1-weighted sequences are available

Abstract

OBJECTIVES: This study aims to evaluate the diagnostic performance of a ResNet50-based convolutional neural network (CNN) in detecting osteochondral lesions of the talus (OLTs) on magnetic resonance imaging (MRI) and to compare its efficacy between T1- and T2- weighted sequences. MATERIALS AND METHODS: A total of 219 ankle MRI scans were reviewed retrospectively, including 60 with confirmed OLTs and 159 without lesions. From each study, coronal and sagittal T1- and T2-weighted images were extracted and standardized to 224 × 224 pixels. Augmentation techniques were applied to strengthen model training. Data were divided into training, validation, and test sets in a 60:20:20 split. A ResNet50 model initialized with ImageNet weights was fine-tuned using crossentropy loss with class weighting. Diagnostic performance was summarized with accuracy, precision, recall, and F1-scores. RESULTS: The model performed better on T1 sequences, achieving an accuracy of 94.1% (95% confidence interval [CI] 88.3-97.1%) and an area under the curve [AUC] of 0.93 (95% CI 0.87-0.97), with patient cases classified at 0.92 precision and 0.82 recall. Healthy controls in the T1 group were recognized with 0.95 precision and 0.98 recall. In contrast, T2 sequences were less reliable, showing an accuracy of 87.2% (95% CI 80.5-91.9%) and an AUC of 0.91 (95% CI 0.85-0.95). Precision for patient cases in the T2 group was notably lower (0.65) despite a recall of 0.81. Misclassifications were more frequent in the T2 dataset, as evidenced by the confusion matrices. CONCLUSION: Even with a relatively modest dataset, the ResNet50 model delivered strong results for T1-weighted MRI. While T2 images proved more challenging, suggesting that deep learning can add value to routine assessment of OLTs.

References

1. 1.Dabiry, S. M., Demirtaş, Y., Türk, F., Yıldırım, T., Ayık, G., & Çakmak, G. (2026). High diagnostic accuracy of a resnet50-based deep learning model for osteochondral lesions of the talus on magnetic resonance imaging. Joint Diseases and Related Surgery. https://doi.org/10.52312/jdrs.2026.2719