Accurate JIC (Japanese Investigation Committee) classification of osteonecrosis of the femoral head (ONFH) is critical for collapse risk prediction and hip-preserving treatment. However, clinical classification faces challenges: indistinct lesion boundaries, limited annotated medical data, and the black-box inference issue of purely data-driven deep learning models. To address these, a Prior Knowledge-Guided CNN-Swin Transformer Hybrid Network (PGCT-Net) is proposed for high-accuracy classification with interpretable decision support. A cascaded dual-branch structure is adopted: the CNN branch extracts fine-grained local features from MRI images, while the Swin Transformer branch captures multi-scale global semantics and long-range dependencies between necrotic lesions and the acetabular weight-bearing region. A lesion mask-guided learning module injects expert-annotated clinical prior knowledge to focus the model on pathological regions and suppress background interference. Grad-CAM is used to visualize attention distribution for better interpretability. The network is trained end-to-end with a composite loss function combining cross-entropy loss and L1 sparse regularization. On the JLU-ONFH dataset, PGCT-Net achieves 94.38% accuracy, 94.15% F1-score and 93.97% AUC, significantly outperforming mainstream models. Cross-task validation on the BT dataset verifies the architecture’s generalizability. This work provides an effective, interpretable scheme for ONFH JIC classification, with promising clinical auxiliary diagnosis potential.
Yang et al. (Sat,) studied this question.