A New Computational Model For Lethal Brain Tumor Prediction

By Radhika K.

A new computational model can now predict lethal brain tumour growth with accuracy, a research from Canada.
Researchers at the University of Waterloo, Canada, have created a model that will measure the growth of deadly brain tumours and predict its accuracy.
The research was published in the Journal of Theoretical Biology under the title "Deep learning characterization of brain tumours with diffusion-weighted imaging."

The research will help in estimating the tumour diffusivity and proliferation rate for neurosurgeons in the case of glioblastoma multiforme (GBM).
GBM is difficult to treat due to its extremely dense core, rapid growth, and location in the brain, like other lethal brain cancer tumours.
St. Michael's Hospital in Toronto collaborated with researchers from the Universities of Waterloo and Toronto to analyse MRI data from GBM patients, whose average survival time is just one year.
During the research, GBM patients underwent two sets of extensive MRIs where they chose not to undergo GBM treatment or any kind of intervention.
Here, scientists used machine learning to fully analyse a patient’s tumour to better predict cancer progression.
These MRIs provided the scientists with a unique opportunity to understand how GBM grows when left untreated.
A deep learning model was used to turn the MRI data into patient-specific parameters for GBM growth prediction.
Cameron Meaney, the study’s lead researcher, says it was challenging to study growth prediction for GBM tumours as there isn't a long life expectancy.
The next step in this study will be to expand the model to include the effect of treatment on the tumours.
"The integration of quantitative analysis into healthcare is the future," says Cameron Meaney.

Source- News Medical

Written by

Radhika K.

Vaidam Health · Updated 25 Sept 2026