AI helps doctors measure scoliosis more consistently
Scoliosis is a condition characterized by an abnormal sideways curvature of the spine and most commonly develops during adolescence. Doctors typically assess its severity by measuring spinal curvature on X-ray images. This measurement plays an important role in diagnosis, follow-up evaluation and treatment planning.
An AI system developed by researchers from National Taiwan University and Taipei Veterans General Hospital aims to make scoliosis measurements more consistent and automatic. The system analyzes spinal X-rays to identify vertebrae and assess their shape and tilt, ultimately measuring spinal curvature. In a study published in IEEE Transactions on Medical Imaging, the researchers found that the AI's measurements agreed strongly with those made by experienced specialists, with average differences ranging from approximately 2.3 to 3.4 degrees across the evaluated spinal curves.
The system also performed well on an external dataset collected under different institutional and imaging conditions, suggesting its potential for broader use across various hospitals and clinical settings. The goal of the AI system is not to replace clinical judgment but to provide doctors with a reliable tool that can make scoliosis measurement more consistent and reduce variability during manual assessment.
Brief written by urgent.news from Medical Xpress's own syndicated text. Machine-written — may contain errors; check the original before relying on it.
