Segmenting Brain Tumors using Pseudo-Conditional Random Fields
Full Text:
pcrf_cam1.pdf 
Locating Brain tumor segmentation within MR (magnetic
resonance) images is integral to the treatment of brain cancer. This segmentation task requires classifying each voxel as either tumor or non-tumor, based on a description of that voxel. Unfortunately, standard classifiers, such as Logistic Regression (LR) and Support Vector Machines
(SVM), typically have limited accuracy as they treat voxels as independent and identically distributed (i.i.d.). Approaches based on random fields, which are able to incorporate spatial constraints, have recently
been applied to brain tumor segmentation with notable performance improvement over i.i.d. classifiers. However, previous random field systems involved computationally intractable formulations, which are typically
solved using some approximation. Here, we present pseudo-conditional random fields (PCRFs), which achieve accuracy similar to other random fields variants, but are significantly more efficient. We formulate a PCRF
as a regularized discriminative classifier that achieves the robustness of an i.i.d. learner (such as LR and SVM) while also incorporating spatial
dependencies is as effective as state-of-the-art random fields, but significantly more efficient Our empirical experiments demonstrate PCRF's effectiveness and efficiency in a real-world segmentation task (brain tumors from MR images), which involves non-trivial spatial dependencies.
Citation
C. Lee,
S. Wang,
M. Brown,
A. Murtha,
R. Greiner.
"Segmenting Brain Tumors using Pseudo-Conditional Random Fields".
Medical Image Computing and Computer-Assisted Intervention, pp 359-366, September 2008.
| Keywords: |
brain tumor, BTAP, machine learning, random fields, medical informatics |
| Category: |
In Conference |
| Web Links: |
DOI |
BibTeX
@incollection{Lee+al:MICCAI08,
author = {Chi-Hoon Lee and Shaojun Wang and Matt Brown and Albert Murtha and
Russ Greiner},
title = {Segmenting Brain Tumors using Pseudo-Conditional Random Fields},
Pages = {359-366},
booktitle = {Medical Image Computing and Computer-Assisted Intervention},
year = 2008,
}Last Updated: April 28, 2012
Submitted by Russ Greiner 
