waterloo [Canada]: University of Waterloo researchers have created a computational model that can better predict lethal formation brain tumors.
glioblastoma multiforme (GBM) is a type of brain cancer with a one-year survival rate. Due to its extraordinarily dense core, rapid growth, and location in the brain, it is difficult to cure. Estimating the diffusivity and proliferation rate of these tumors is useful to clinicians, but this information is difficult to estimate for an individual patient quickly and accurately.
Researchers from the University of Waterloo and the University of Toronto have partnered with St. Michael’s Hospital in Toronto to analyze MRI data from multiple GBM patients. They are using machine learning to fully analyze a patient’s tumor, to better predict cancer progression.
The researchers analyzed two sets of MRIs from each of five anonymous GBM patients. The patients underwent extensive MRIs, waited several months, and then received a second set of MRIs. Because these patients, for undisclosed reasons, chose not to receive any treatment or intervention during this time, their MRIs provided scientists with a unique opportunity to understand how GBM grows when left unchecked.
The researchers used a deep learning model to convert MRI data into patient-specific parameter estimates that inform a predictive model for GBM growth. This technique was applied to patient and synthetic tumors, of which the real characteristics were known, which allowed them to validate the model.
“We would have loved to do this analysis on a large data set,” said Cameron Meaney, PhD candidate in Applied Mathematics and the study’s principal investigator, adding: “However, based on the nature of the disease, that’s very challenging because There’s not a long life expectancy, and people tend to start treatment. That’s why the opportunity to compare five untreated tumors was so rare and valuable.”
Now that the scientists have a good model of how GBM grows without treatment, their next step is to expand the model to include the effect of treatment on tumors. Then the data set would grow from a handful of MRIs to thousands.
Meaney emphasizes that access to MRI data, and the partnership between mathematicians and physicians, can have a big impact on patients in the future. “The integration of quantitative analysis into health care is the future,” Meaney said.
