X2BR: High-Fidelity 3D Bone Reconstruction from a Planar X-Ray Image with Hybrid Neural Implicit Methods
This work addresses a challenge in medical imaging for clinicians, providing a method that balances accuracy and anatomical consistency for 3D bone reconstruction from limited X-ray data, though it builds incrementally on existing neural implicit and template-based approaches.
The paper tackles the problem of accurate 3D bone reconstruction from a single planar X-ray image by proposing X2BR, a hybrid neural implicit framework that combines volumetric reconstruction with template-guided registration, achieving high numerical accuracy with an IoU of 0.952 and Chamfer-L1 distance of 0.005, and offering improved anatomical realism with an IoU of 0.875.
Accurate 3D bone reconstruction from a single planar X-ray remains a challenge due to anatomical complexity and limited input data. We propose X2BR, a hybrid neural implicit framework that combines continuous volumetric reconstruction with template-guided non-rigid registration. The core network, X2B, employs a ConvNeXt-based encoder to extract spatial features from X-rays and predict high-fidelity 3D bone occupancy fields without relying on statistical shape models. To further refine anatomical accuracy, X2BR integrates a patient-specific template mesh, constructed using YOLOv9-based detection and the SKEL biomechanical skeleton model. The coarse reconstruction is aligned to the template using geodesic-based coherent point drift, enabling anatomically consistent 3D bone volumes. Experimental results on a clinical dataset show that X2B achieves the highest numerical accuracy, with an IoU of 0.952 and Chamfer-L1 distance of 0.005, outperforming recent baselines including X2V and D2IM-Net. Building on this, X2BR incorporates anatomical priors via YOLOv9-based bone detection and biomechanical template alignment, leading to reconstructions that, while slightly lower in IoU (0.875), offer superior anatomical realism, especially in rib curvature and vertebral alignment. This numerical accuracy vs. visual consistency trade-off between X2B and X2BR highlights the value of hybrid frameworks for clinically relevant 3D reconstructions.