A Classification-based Glioma Diffusion Model Using MRI Data
- Marianne Morris, University of Alberta
- Russ Greiner, Dept of Computing Science; PI of AICML
- Joerg Sander, Dept of Computing Science
- Albert Murtha, Cross Cancer Institute, Edmonton
- Mark Schmidt, Dept of Computing Science, University of Alberta
Gliomas are diffuse, invasive brain tumors. We propose a 3D classification-based diffusion model, CDM, that predicts how a glioma will grow at a voxel-level, on the basis of features specific 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 effectively than two standard models: uniform radial growth across all tissue types, and another that assumes faster diffusion in white matter.
Citation
M. Morris, R. Greiner, J. Sander, A. Murtha, M. Schmidt. "A Classification-based Glioma Diffusion Model Using MRI Data". Canadian Conference on Artificial Intelligence (CAI), Quebec City, May 2006.Keywords: | machine learning, brain tumors, glioma, diffusion models, prediction, medical informatics |
Category: | In Conference |
Web Links: | Webpage |
BibTeX
@incollection{Morris+al:CAI06, author = {Marianne Morris and Russ Greiner and Joerg Sander and Albert Murtha and Mark Schmidt}, title = {A Classification-based Glioma Diffusion Model Using MRI Data}, booktitle = {Canadian Conference on Artificial Intelligence (CAI)}, year = 2006, }Last Updated: April 28, 2012
Submitted by Russ Greiner