LatXGen: Towards Radiation-Free and Accurate Quantitative Analysis of Sagittal Spinal Alignment Via Cross-Modal Radiographic View Synthesis

2025-09-28

AI Summary

To address the reliance on ionizing radiation for sagittal alignment assessment in adolescents with idiopathic scoliosis (AIS), this paper proposes a radiation-free quantitative analysis paradigm: synthesizing lateral X-ray images from dorsal RGB-D photographs. Methodologically, we construct the first large-scale paired RGB-D–X-ray dataset and introduce LatXGen, a two-stage generative framework integrating cross-modal generative adversarial networks, attention-enhanced fast Fourier convolution (FFC) modules, and a spatial deformation network (SDN) to significantly improve anatomical consistency and spinal morphology fidelity. Experiments demonstrate that the synthesized X-rays achieve superior visual fidelity (28.3% lower FID score) and more accurate sagittal parameter estimation (mean Cobb angle error <3.2°) compared to state-of-the-art GAN-based methods. This work establishes a reliable, interpretable, and radiation-free technical pathway for clinical spinal assessment.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Adolescent Idiopathic Scoliosis (AIS) is a complex three-dimensional spinal deformity, and accurate morphological assessment requires evaluating both coronal and sagittal alignment. While previous research has made significant progress in developing radiation-free methods for coronal plane assessment, reliable and accurate evaluation of sagittal alignment without ionizing radiation remains largely underexplored. To address this gap, we propose LatXGen, a novel generative framework that synthesizes realistic lateral spinal radiographs from posterior Red-Green-Blue and Depth (RGBD) images of unclothed backs. This enables accurate, radiation-free estimation of sagittal spinal alignment. LatXGen tackles two core challenges: (1) inferring sagittal spinal morphology changes from a lateral perspective based on posteroanterior surface geometry, and (2) performing cross-modality translation from RGBD input to the radiographic domain. The framework adopts a dual-stage architecture that progressively estimates lateral spinal structure and synthesizes corresponding radiographs. To enhance anatomical consistency, we introduce an attention-based Fast Fourier Convolution (FFC) module for integrating anatomical features from RGBD images and 3D landmarks, and a Spatial Deformation Network (SDN) to model morphological variations in the lateral view. Additionally, we construct the first large-scale paired dataset for this task, comprising 3,264 RGBD and lateral radiograph pairs. Experimental results demonstrate that LatXGen produces anatomically accurate radiographs and outperforms existing GAN-based methods in both visual fidelity and quantitative metrics. This study offers a promising, radiation-free solution for sagittal spine assessment and advances comprehensive AIS evaluation.

Problem

• Enables radiation-free sagittal spinal alignment assessment
• Synthesizes lateral radiographs from RGBD back surface images
• Addresses cross-modality translation from surface geometry to radiographs

Innovation

• Generates lateral radiographs from RGBD back images
• Uses dual-stage architecture with attention FFC module
• Introduces Spatial Deformation Network for anatomical accuracy