Deep Probabilistic Modeling of Glioma Growth

Existing approaches to modeling the dynamics of brain tumor growth, specifically glioma, employ biologically inspired models of cell diffusion, using image data to estimate the associated parameters. In this work, we propose an alternative approach based on recent advances in probabilistic segmentat...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Petersen, Jens, Jäger, Paul F, Isensee, Fabian, Kohl, Simon A A, Neuberger, Ulf, Wick, Wolfgang, Debus, Jürgen, Heiland, Sabine, Bendszus, Martin, Kickingereder, Philipp, Maier-Hein, Klaus H
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 09.07.2019
Subjects
Brain
Brain cancer
Conditioning
Image segmentation
Modelling
Parameter estimation
Tumors
Online AccessGet full text

Cover

More Information
Summary:Existing approaches to modeling the dynamics of brain tumor growth, specifically glioma, employ biologically inspired models of cell diffusion, using image data to estimate the associated parameters. In this work, we propose an alternative approach based on recent advances in probabilistic segmentation and representation learning that implicitly learns growth dynamics directly from data without an underlying explicit model. We present evidence that our approach is able to learn a distribution of plausible future tumor appearances conditioned on past observations of the same tumor.
ISSN:2331-8422