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 artificial intelligence system has been developed to automatically measure scoliosis curvature in spinal X-ray images. Scoliosis is a condition marked by an abnormal sideways curvature of the spine, commonly appearing during adolescence. Doctors typically assess its severity by evaluating spinal curvature on X-ray images, a process that is often time-consuming and prone to variability due to manual analysis.
The researchers from National Taiwan University and Taipei Veterans General Hospital designed the AI system to streamline this process. The system works by first identifying each vertebra in the X-ray and then examining its shape and tilt to automatically measure spinal curvature. The study published in IEEE Transactions on Medical Imaging compared the AI's measurements with those made by experienced specialists.
The AI showed strong agreement, with differences ranging from approximately 2.3 to 3.4 degrees, which is comparable to the agreement between two human observers when differences were 5 degrees or less. Importantly, the AI maintained its accuracy when tested on X-rays from a different source with varying imaging conditions, indicating its potential for broad clinical application.
Co-corresponding author I-Yun Lisa Hsieh emphasized that the goal is not to replace clinical judgment but to provide a reliable tool for more consistent scoliosis measurement, thereby reducing variability associated with manual assessment.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
