Glioma Diusion Model using MRI Data

Gliomas are diuse, invasive brain tumors. We propose a 3D classication-bas ed diusion model, cdm, that predicts how a glioma will grow at a voxel-level, on the basis of features specic to the patient, properties of the tumor, and attributes of that voxel. We use Supervised Learning algorithms to learn this general model, by observing the growth patterns of gliomas from other patients. Our empirical results on clinical data demonstrate that our learned cdm model can, in most cases, predict glioma growth more eectiv ely than two standard models: uniform radial growth across all tissue types, and another that assumes faster diusion in white matter.