Skeleton-Guided Diffusion Model for Accurate Foot X-ray Synthesis in Hallux Valgus Diagnosis

2025-05-13

AI Summary

Clinical diagnosis of hallux valgus relies on weight-bearing X-rays, which impose substantial operational burden; existing diffusion models struggle to simultaneously ensure image fidelity, anatomical consistency of skeletal structures, and biomechanical plausibility. Method: We propose a bone-guided conditional diffusion model. To jointly model anatomical and biomechanical constraints, we introduce— for the first time—a skeletal keypoint constraint mechanism integrated with multi-scale attention-based feature fusion. Additionally, we design the Keypoint-based Clinical Consistency (KCC) metric for quantitative, clinically interpretable foot assessment. Results: Our method achieves significant improvements over baselines in SSIM (+5.72%, 0.794) and PSNR (+18.34 dB, 21.40 dB); the average KCC score reaches 0.85. The implementation is publicly available.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Medical image synthesis plays a crucial role in providing anatomically accurate images for diagnosis and treatment. Hallux valgus, which affects approximately 19% of the global population, requires frequent weight-bearing X-rays for assessment, placing additional strain on both patients and healthcare providers. Existing X-ray models often struggle to balance image fidelity, skeletal consistency, and physical constraints, particularly in diffusion-based methods that lack skeletal guidance. We propose the Skeletal-Constrained Conditional Diffusion Model (SCCDM) and introduce KCC, a foot evaluation method utilizing skeletal landmarks. SCCDM incorporates multi-scale feature extraction and attention mechanisms, improving the Structural Similarity Index (SSIM) by 5.72% (0.794) and Peak Signal-to-Noise Ratio (PSNR) by 18.34% (21.40 dB). When combined with KCC, the model achieves an average score of 0.85, demonstrating strong clinical applicability. The code is available at https://github.com/midisec/SCCDM.

Problem

• Improving foot X-ray synthesis for Hallux Valgus diagnosis
• Enhancing skeletal consistency in diffusion-based X-ray models
• Balancing image fidelity with physical constraints in medical imaging

Innovation

• Skeletal-Constrained Conditional Diffusion Model (SCCDM)
• Multi-scale feature extraction and attention mechanisms
• Foot evaluation method utilizing skeletal landmarks (KCC)