Abstract
Background/Objectives: scoliosis is a three-dimensional structural deformity characterized by lateral and rotational curvature of the spine. The current gold-standard method to assess scoliosis is the measurement of lateral curvature of the spine using the Cobb angle in coronal plane radiographs. The interrater variability for Cobb angle measurements reaches up to 10°. The purpose of this study was to describe and assess the performance of a fully automated method for measuring Cobb angles using a commercially available artificial intelligence (AI) model trained on over 17,000 images, and investigate its interrater/intrarater agreement with a reference standard. Methods: in total, 196 AP/PA full-spine radiographs were included in this study. A reference standard was established by four radiologists, defined as the median of their Cobb angle measurements. Independently, an AI-based software, IB Lab SQUIRREL (version 1.0), also performed Cobb angle measurements on the same radiographs. Results: after comparing the readers' Cobb angle end vertebrae selection to the AI's outputs, 194 curvatures were considered valid for performance assessment, displaying an accuracy of 88.58% in end vertebrae selection. The AI's performance showed very low absolute bias, with a mean difference and standard deviation of differences from the reference standard of 0.16° ± 0.35° in the Cobb angle measurements. The ICC comparing the reference standard and the AI's measurements was 0.97. Conclusions: the AI model demonstrated good results in the determination of end vertebrae and excellent results in automated Cobb angle measurements compared to radiologists and could serve as a reliable tool in clinical practice and research.