Self-similarity guided regression with contrast enhancement for spine segmentation

Accurate spine segmentation is critical for scoliosis diagnosis and treatment. For instance, automatic Cobb angle measurement for scoliosis relies on precisely localized vertebral masks. However, it remains a challenging task due to low tissue contrast, blurred vertebral edges, and overlapping anatomical structures. In this paper, we propose SRNet, a pure segmentation network that produces binary masks of each vertebra. SRNet integrates two novel components, a Self-similarity Guided Dynamic Convolution (SGDC) module and a Contrast-Enhanced Boundary Decoder (CEBD). SGDC exploits the repetitive structure of vertebrae by leveraging non-local attention to compute self-similarity across feature maps and dynamic convolution to combine multiple convolution kernels adaptively. CEBD sharpens segmentation boundaries via a reverse-attention mechanism that erases the coarse prediction and focuses on missing edge details, combined with a spectral-residual filter that amplifies high-frequency edge information. Extensive experiments on the AASCE spine X-ray dataset show that our SRNet achieves a high Dice score of 92.37%, outperforming state-of-the-art approaches. While our primary focus here is mask segmentation, the accurate vertebral masks produced by SRNet could readily support future tasks such as scoliosis Cobb angle estimation.