Researchers at the University of Waterloo and the University of Toronto have developed a new computational model to predict the growth of glioblastoma multiforme (GBM) more accurately.
The proliferation-invasion (PI) model is a mathematical model commonly used to describe the growth of glioblastoma multiforme (GBM). It relies on known values of two key parameters, the rate of cell movement (tumor cell diffusivity) and the rate at which cells divide and form new tumors (proliferation rate). Because it is difficult to estimate the key parameters in a patient-specific manner, it is challenging to make accurate predictions about the progression of a particular patient’s tumor.
The researchers developed a deep learning model that can accurately estimate the key parameters of tumors and predict the progression of the tumors using multi-sequence MRI data. They applied the model to synthetic tumors to test its capabilities and identify situations where prediction errors are likely to occur. They then applied it to a clinical dataset of five patients diagnosed with GBM.
The researchers used a deep learning model to turn the MRI data into patient-specific parameter estimates that inform a predictive model for GBM growth.
Cameron Meaney, Sunit Das, Errol Colak, Mohammad Kohandel,
Deep learning characterization of brain tumours with diffusion weighted imaging, Journal of Theoretical Biology, Volume 557, 2023,111342, ISSN 0022-5193,