System uses plain lumbar anteroposterior X-ray image
By Lori Solomon HealthDay Reporter
WEDNESDAY, July 16, 2025 (HealthDay News) — An artificial intelligence (AI)-assisted diagnostic system can accurately estimate bone mineral density (BMD) and classify osteoporosis category, according to a study published online July 9 in the Journal of Orthopaedic Research.
Toru Moro, M.D., Ph.D., from the University of Tokyo, and colleagues developed an AI-assisted diagnostic system that estimated lumbar spine and femoral BMD from anteroposterior lumbar X-ray images (1,454 images from 1,454 participants).
The researchers found that for the BMD estimation performance, the mean absolute errors were 0.076 g/cm2 for the lumbar spine and 0.071 g/cm2 for the femur between dual-energy X-ray absorptiometry-derived and AI-estimated BMD values. For the lumbar spine and femur of patients with osteopenia, performance showed a sensitivity of 86.4 and 80.4 percent, respectively, and specificities of 84.1 and 76.3 percent, respectively.
“Bone mineral density measurement is essential for screening and diagnosing osteoporosis, but limited access to diagnostic equipment means that millions of people worldwide may remain undiagnosed,” Moro said in a statement. “This AI system has the potential to transform routine clinical X-rays into a powerful tool for opportunistic screening, enabling earlier, broader, and more efficient detection of osteoporosis.”
Several authors disclosed ties to the KYOCERA Corporation.
Copyright © 2025 HealthDay. All rights reserved.
