An AI-assisted digital twin of human vertebrae may foresee how cancer affects spinal column ruptures

A study from Ohio State University has discovered how an AI-assisted digital twin of human vertebrae may foresee how cancer affects the likelihood of spinal column ruptures.

Over one-point-six million cases in the US are diagnosed yearly, and roughly ten per cent of those patients undergo spinal metastasis.

Published in the International Journal for Numerical Methods in Biomedical Engineering, their study describes how the researchers created a digital twin of a patient’s vertebra by training an AI-assisted framework, ReconGAN, which can be utilized to indicate the quantity of stress the vertebra can handle before breaking under pressure.

By training ReconGAN on MRI and micro-CT images formed by getting slice-by-slice pictures of vertebrae taken from a cadaver, researchers could develop accurate micro-structural models of the spine. The team was also capable of extending the model utilizing their simulation, which the paper claims are essential for understanding and comprising modifications to a vertebra’s complete geometric design.

The researchers employed CT/MRI scans from a female, aged 51, lung cancer patient with metastasized cancer to mimic what would happen if cancer weakened some of the vertebrae and how that would affect how much stress the bones could withstand before shattering.

The model estimated how much strength sections of the vertebra would lose as a result of the tumours, as well as other alterations that could occur as cancer advanced, according to the researchers. Clinical observations of cancer patients confirmed some of their expectations.

Associate professor of mechanical and aerospace engineering at The Ohio State University and co-author of the study, Soheil Soghrati, stated: “Spinal fracture increases the risk of patient death by about fifteen per cent. 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. The ultimate goal is to develop a digital twin of everything a surgeon may operate on. Right now, they’re only used for very, very challenging surgeries, but we want to help run those simulations and tune those parameters even more. What really makes the work in a distinct way is how detailed we were able to model the geometry of the vertebra. We can virtually evolve the same bone from one stage to another.”