VerteNet -- A Multi-Context Hybrid CNN Transformer for Accurate Vertebral Landmark Localization in Lateral Spine DXA Images

Vertebral Landmarks Localization in Dual-Energy X-ray Absorptiometry based Lateral Spine Imaging plays a critical role in evaluating spinal alignment, Vertebral Fracture Assessment, and facilitating intervertebral guide placement for Abdominal Aortic Calcification quantification. While lateral spine DXA scans offer advantages such as reduced cost and lower radiation exposure, its analysis remains challenging due to a low signal-to-noise ratio and imaging artifacts. Artificial Intelligence presents a promising approach for improving the precision and accuracy of VLL. In this study, we introduce a novel architecture that employs dual-resolution attention mechanisms to capture both fine-grained local details and broader contextual information. Our approach enhances feature integration by leveraging skip connections and decoder layers through dual-resolution self-attention and cross-attention mechanisms. This design improves the ability of the model to learn complex patterns, enabling precise vertebral corner localization while maintaining both local and global contextual awareness. We evaluated the proposed framework on DXA LSI images acquired from multiple machines and found that it outperforms recent state-of-the-art architectures for VLL, achieving a normalized mean error of 4.92 and a normalized median error of 2.35. The proposed framework, VerteNet, enables highly accurate VLL in DXA LSI images from diverse acquisition systems and demonstrates strong robustness to low signal-to-noise ratios, owing to its enhanced ability to capture both fine-grained local details and broader contextual information.