SGX2CT: Self-part Guided 3D CT and Spine Model Reconstruction from Biplanar Lumbar X-rays

Computed tomography (CT) imaging, characterized by its high contrast sensitivity and spatial resolution, provides detailed insights into a patient’s internal anatomical structures, particularly the intricate details of the spinal vertebrae. Compared to conventional X-ray imaging, CT scans entail higher radiation exposure and increased costs. The reconstruction of three-dimensional CT images and precise spinal models from two-dimensional X-ray images has garnered clinical interest due to lower radiation risks and improved accessibility. Inspired by self-supervised learning principles, this study introduces a novel self-guided cross-domain learning approach, SGX2CT, aimed at simultaneously reconstructing three-dimensional lumbar CT scans and spinal models from two-dimensional X-rays while facilitating mutual reinforcement. Specifically, a multi-domain shared generator is employed to acquire robust global information, coupled with perceptual loss functions for alignment in image space. Domain-specific group normalization is utilized to disentangle distinct features across domains to enhance outcomes in each domain. Experimental findings demonstrate that SGX2CT achieves state-of-the-art performance in both lumbar CT reconstruction and spinal model generation, underscoring its potential utility in orthopedic practice.