Glioblastoma is a form of primary brain cancer. Mass effect is a clinical term of art to indicate clearly visible mechanical deformations due to the presence of the tumor. In many cases such effect is absent but when it is present it seems to correlate with the tumor aggressiveness (but not always). In this talk I will present a framework for quantitatively characterizing mass effect and a set of inverse problems and algorithms that can be used to analyze clinical datasets.

This presentation is part of Minisymposium “MS36 - Computational Methods for Large-Scale Machine Learning in Imaging (2 parts)”
organized by: Matthias Chung (Virginia Tech) , Lars Ruthotto (Department of Mathematics and Computer Science, Emory University) .

Authors:

Andreas Mang (Department of Mathematics, University of Houston)

Sameer Tharakan (UT Austin)

Amir Gholami (UC Berkeley)

James Levitt (UT Austin)

Naveen Himthani (UT Austin)

George Biros (Institute for Computational Engineering and Sciences, University of Texas at Austin)

Keywords:

image segmentation, machine learning