A multimodal deep learning model for classifying early- versus late-stage osteonecrosis of the femoral head on biparametric MRI.
Authors
Affiliations (8)
Affiliations (8)
- The Third Medical College, Guangzhou University of Chinese Medicine, Guangzhou, 510405, China.
- Department of Orthopedic, The Third Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, 510378, China.
- The National Key Discipline and the Orthopedic Laboratory, Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, 510405, China.
- Department of Radiology, Guangzhou First People's Hospital, No. 1 Panfu Road, Yuexiu District, Guangzhou, Guangdong, 510180, China. [email protected].
- Department of Orthopedic, The Third Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, 510378, China. [email protected].
- The National Key Discipline and the Orthopedic Laboratory, Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, 510405, China. [email protected].
- Department of Joint Orthopedic, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, No. 111Dade Road, Yuexiu District, Guangdong, 510405, Guangzhou, China. [email protected].
- Department of Joint Orthopedic, Guangdong Provincial Hospital of Chinese Medicine, No. 111 Dade Road, Yuexiu District, Guangzhou, Guangdong, 510405, China. [email protected].
Abstract
Precise early- versus late-stage stratification of osteonecrosis of the femoral head (ONFH) is critical for hip-preserving treatment selection, yet conventional MRI interpretation suffers from interobserver variability and limited objectivity. This study aimed to develop a multimodal deep learning model integrating biparametric MRI (STIR and T1-FSE) with clinical parameters (including age, sex, affected side (left, right, or bilateral), and etiology) to differentiate early- from late-stage ONFH and provide objective imaging evidence. This retrospective study included 530 patients with ONFH, yielding imaging data from 851 hips. The collected data comprised STIR sequences, T1-FSE sequences, and clinical information, including age, sex, and etiology. The dataset was randomly divided at the patient level into a training set (424 patients, 675 hips) and a test set (106 patients, 176 hips) at an 8:2 ratio. Seven models were constructed: a clinical model, a STIR model, a T1-FSE model, a bpMRI model, a STIR-clinical model, a T1-FSE-clinical model, and a bpMRI-clinical model. Early- and late-fusion strategies were used for multimodal integration. The diagnostic performance of the seven models for classifying early- versus late-stage ONFH was systematically compared, with particular emphasis on their ability to identify borderline cases at the transition between clinical stages. Model interpretability was assessed using Gradient-weighted Class Activation Mapping (Grad-CAM). The early-fusion bpMRI-clinical model achieved the highest AUC of 0.944 (95% CI 0.905-0.973), accuracy 90.9%, sensitivity 89.0%, and specificity 92.9%, significantly outperforming single-sequence models (all P < 0.05). The confusion matrix showed that the model misclassified 10 late-stage cases as early-stage and 6 early-stage cases as late-stage. Grad-CAM visualizations indicated that the model primarily focused on clinically relevant regions, including the necrotic lesion boundary, areas of bone marrow edema, and subchondral structural abnormalities. These attention patterns were highly consistent with the core imaging features used for early- versus late-stage ONFH stratification. This study presents an interpretable multimodal deep learning framework that integrates dual-sequence MRI with clinical parameters. The framework accurately differentiates early- from late-stage ONFH according to the ARCO classification and provides objective evidence for determining the critical threshold for hip-preservation decision-making. The trial was registered with the Chinese Clinical Trial Registry (Registration No: ChiCTR2300075354. Sep 1, 2023).