Credit score: Pixabay/CC0 Public Area
Investigators have developed a man-made intelligence-assisted diagnostic system that may estimate bone mineral density in each the lumbar backbone and the femur of the higher leg, based mostly on X-ray pictures. The advance is described in a research revealed within the Journal of Orthopaedic Analysis.
A complete of 1,454 X-ray pictures have been analyzed utilizing the scientists’ system. Efficiency charges for the lumbar and femur of sufferers with bone density loss, or osteopenia, have been 86.4% and 84.1%, respectively, when it comes to sensitivity.
The respective specificities have been 80.4% and 76.3%. (Sensitivity mirrored the flexibility of the check to accurately determine folks with osteopenia, whereas specificity mirrored its capacity to accurately determine these with out osteopenia). The check additionally had excessive sensitivity and specificity for categorizing sufferers with and with out osteoporosis.
“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,” mentioned corresponding writer Toru Moro, MD, Ph.D., of the College of Tokyo.
“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.”
Extra data:
Improvement of synthetic intelligence-assisted lumbar and femoral BMD estimation system utilizing anteroposterior lumbar X-ray pictures, Journal of Orthopaedic Analysis (2025). DOI: 10.1002/jor.70000
Quotation:
AI–based mostly check detects early indicators of osteoporosis from X-ray pictures (2025, July 9)
retrieved 9 July 2025
from https://medicalxpress.com/information/2025-07-aibased-early-osteoporosis-ray-images.html
This doc is topic to copyright. Aside from any truthful dealing for the aim of personal research or analysis, no
half could also be reproduced with out the written permission. The content material is offered for data functions solely.
