Machine learning method for personalized prediction of brain tumor progression
2023
University of Waterloo, Waterloo, Canada
Glioblastoma multiforme (GBM) is one of the most deadly forms of cancer. Methods of characterizing these tumours are valuable for improving predictions of their progression and response to treatment. A mathematical model called the proliferation-invasion (PI) model has been used extensively in the literature to model the growth of these tumours, though it relies on two key parameters that are difficult to estimate in a patient-specific manner. In this paper, the researchers develop and apply a deep learning model capable of making accurate estimates of these key GBM-characterizing parameters while simultaneously producing a full prediction of the tumour progression curve. The method uses MRI data. The model was applied to a clinical dataset consisting of five patients diagnosed with GBM. For all patients, the researchers derive evidence-based estimates for each of the PI model parameters and predictions for the future progression of the tumour, along with estimates of the parameter uncertainties. This work provides a new, easily generalizable method for the estimation of patient-specific tumour parameters, which can be built upon to aid physicians in designing personalized treatments.
Deep learning characterization of brain tumours with diffusion weighted imaging
Cameron Meaney
Added on: 01-19-2023
[1] https://www.sciencedirect.com/science/article/abs/pii/S0022519322003332?via%3Dihub[2] https://neurosciencenews.com/brain-cancer-machine-learning-22266/
