Accurate Cobb Angle Estimation via SVD-Based Curve Detection and Vertebral Wedging Quantification

2025-09-29

AI Summary

To address poor inter-rater reliability in manual Cobb angle measurement for adolescent idiopathic scoliosis (AIS) and limitations of existing automated methods—including reliance on predefined spinal curvature models and insufficient representational capacity—this study proposes an end-to-end deep learning framework. It employs an HRNet-Swin hybrid backbone to jointly predict vertebral endplate angles and midpoints. A novel SVD-driven, prior-free curve detection mechanism is introduced to eliminate assumptions about canonical spinal morphology. Furthermore, we first define the Vertebral Wedge Index (VWI), demonstrating its statistically significant association with curve progression and early predictive value. Evaluated on 630 full-spine radiographs, the model achieves 83.45% diagnostic accuracy and a mean absolute error of 2.55°, exhibits strong out-of-distribution generalizability, and significantly outperforms the conventional Cobb angle in progression prediction.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Intelligent Robots: State Estimation
• Machine Learning: Learning with Manifolds

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Adolescent idiopathic scoliosis (AIS) is a common spinal deformity affecting approximately 2.2% of boys and 4.8% of girls worldwide. The Cobb angle serves as the gold standard for AIS severity assessment, yet traditional manual measurements suffer from significant observer variability, compromising diagnostic accuracy. Despite prior automation attempts, existing methods use simplified spinal models and predetermined curve patterns that fail to address clinical complexity. We present a novel deep learning framework for AIS assessment that simultaneously predicts both superior and inferior endplate angles with corresponding midpoint coordinates for each vertebra, preserving the anatomical reality of vertebral wedging in progressive AIS. Our approach combines an HRNet backbone with Swin-Transformer modules and biomechanically informed constraints for enhanced feature extraction. We employ Singular Value Decomposition (SVD) to analyze angle predictions directly from vertebral morphology, enabling flexible detection of diverse scoliosis patterns without predefined curve assumptions. Using 630 full-spine anteroposterior radiographs from patients aged 10-18 years with rigorous dual-rater annotation, our method achieved 83.45% diagnostic accuracy and 2.55° mean absolute error. The framework demonstrates exceptional generalization capability on out-of-distribution cases. Additionally, we introduce the Vertebral Wedging Index (VWI), a novel metric quantifying vertebral deformation. Longitudinal analysis revealed VWI's significant prognostic correlation with curve progression while traditional Cobb angles showed no correlation, providing robust support for early AIS detection, personalized treatment planning, and progression monitoring.

Problem

• Automating Cobb angle measurement for scoliosis assessment to reduce observer variability
• Detecting diverse spinal curve patterns without predefined curve assumptions
• Quantifying vertebral wedging deformation to predict scoliosis progression risk

Innovation

• SVD-based curve detection from vertebral morphology
• HRNet and Swin-Transformer hybrid backbone architecture
• Vertebral Wedging Index for progression quantification