acm-header
Sign In

Communications of the ACM

ACM TechNews

Using AI to Predict Bone Fractures in Cancer Patients


View as: Print Mobile App Share:

Using non-invasive tools like AI could help researchers better understand and treat bone fractures.

Credit: Getty Images

Ohio State University (OSU) researchers used artificial intelligence to predict how cancer could elevate the probability of spinal fractures by creating digital twins of patients' vertebrae.

The researchers trained the ReconGAN AI-assisted framework on magnetic resonance imagery and micro-computed tomography scans of cadaveric vertebrae to produce realistic virtual reconstructions of the spine.

The team also used the digital twins to virtually enlarge the model, enabling them "to virtually evolve the same bone from one stage to another," said OSU's Soheil Soghrati.

Using scans of a female patient with metastasized lung cancer, the researchers predicted how the tumors would cause the vertebra to weaken, which clinical observations validated.

"By predicting the outcome of these fractures, our research offers medical experts the opportunity to design better treatment strategies, and help patients make better-informed decisions," said Soghrati.

From Ohio State News
View Full Article

 

Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account