Deep learning for radiographic differentiation between lateral malleolar avulsion fractures and subfibular ossicles.
Authors
Affiliations (4)
Affiliations (4)
- Department of Radiology, Air Force Medical Center, Air Force Medical University, 30 Fucheng Road, Haidian District, Beijing 100142, P.R. China.
- Department of Emergency, Air Force Medical Center, Air Force Medical University, 30 Fucheng Road, Haidian District, Beijing 100142, P.R. China.
- Department of Radiology, Sir Run Run Hospital, Nanjing Medical University, 109 Longmian Road, Nanjing, Jiangsu 211002, P.R. China.
- School of Mathematics and Physics, Xi'an Jiaotong-Liverpool University, 111 Renai Road, Suzhou, Jiangsu 215123, P.R. China.
Abstract
Distinguishing lateral malleolar avulsion fractures (LMAFs) from subfibular ossicles (SFOs) on routine ankle radiographs is a clinically consequential challenge, as the two conditions share overlapping radiographic appearances but require distinct management strategies. We developed a two-stage deep learning framework that first localizes perimalleolar bone fragments using RetinaNet and subsequently classifies them as an LMAF or an SFO using a fine-tuned MobileNetV2 classifier. Applied to X-ray images from 2,121 patients across two centers, MobileNetV2 achieved an area under the curve of 0.887 on the external test set, outperforming three comparator architectures and two experienced radiologists. Radiologists provided with AI-generated predictions and saliency maps showed significant improvement in diagnostic accuracy over unaided reading. These findings demonstrate that an integrated detection-classification pipeline can enhance first-visit radiographic triage, offering a practical, lightweight approach to support earlier and more accurate clinical decision-making in acute ankle injuries.