We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us

Download Mobile App




AI Analyzes Spinal X-Rays to Standardize Scoliosis Assessment

By HospiMedica International staff writers
Posted on 23 Aug 2026

Scoliosis, an abnormal sideways curvature of the spine that often arises in adolescence, is gauged on radiographs using angular measurements. More...

These measurements guide diagnosis, follow-up, and treatment planning, yet they are still performed largely by hand. Manual workflows are time-consuming and prone to variation between and within clinicians. To help address this challenge, researchers have developed an artificial intelligence system that aims to make scoliosis measurements more consistent on X-ray images.

Developed by researchers at National Taiwan University and Taipei Veterans General Hospital, the artificial intelligence (AI) system analyzes spinal X-rays to deliver standardized curvature measurements. It automatically identifies each vertebra, delineates its shape, and evaluates tilt before calculating overall spinal curvature. By automating vertebra selection, it targets a major source of variability in manual assessment.

The team evaluated the system using spinal radiographs from Taipei Veterans General Hospital. Against measurements by experienced specialists, the AI showed strong agreement. When two human observers differed by no more than 5 degrees, average differences between the AI and specialists ranged from approximately 2.3 to 3.4 degrees across the assessed curves. Overall, agreement between the AI and clinicians was comparable to agreement between two human observers.

An external validation examined whether the approach would generalize across institutions and imaging conditions. Without retraining, the system continued to perform well on a dataset collected under different acquisition settings. The study, published in IEEE Transactions on Medical Imaging in August, 2026, indicates the tool could support more reproducible scoliosis measurement while reducing time and variability inherent to manual methods.

“Our goal is not to replace clinical judgment, but to provide doctors with a reliable tool that can make scoliosis measurement more consistent and reduce the variability that can occur during manual assessment,” said I-Yun Lisa Hsieh, associate professor of civil engineering at National Taiwan University.

Related Links
National Taiwan University


New
Gold Member
Breast Imaging Monitor
Barco Coronis Onelook MDMC-32133 32MP
Radiology Monitor
MDNC-6121 Barco Nio Color 5.8MP
Fetal Monitor
BT-380
Monitor/Defibrillator
Zenix
Read the full article by registering today, it's FREE! It's Free!
Register now for FREE to HospiMedica.com and get access to news and events that shape the world of Hospital Medicine.
  • Free digital version edition of HospiMedica International sent by email on regular basis
  • Free print version of HospiMedica International magazine (available only outside USA and Canada).
  • Free and unlimited access to back issues of HospiMedica International in digital format
  • Free HospiMedica International Newsletter sent every week containing the latest news
  • Free breaking news sent via email
  • Free access to Events Calendar
  • Free access to LinkXpress new product services
  • REGISTRATION IS FREE AND EASY!
Click here to Register








Channels

Copyright © 2000-2026 Globetech Media. All rights reserved.