Using Symmetry to Detect Abnormalities in Brain MRI
- Nilanjan Ray, Dept of Computing Science
- Russ Greiner, Dept of Computing Science; PI of AICML
- Albert Murtha, Cross Cancer Institute, Edmonton
Automated tumor segmentation from magnetic resonance imagery (MRI) plays a significant role in cancer research and clinical practice. However, tumor segmentation is an extremely challenging task: clinicians believe that a gamut of prior domain knowledge and clinical data should be used, along with the MR image. As a step toward tumor segmentation, we illustrate here a real-time algorithm to locate the brain abnormality in an MR image by putting a bounding box around it. Our approach is based on left-toright symmetry of the brain. In additional to being real-time, some advantages of the proposed algorithm are: (a) it requires no registration of MR images, (b) it needs no training image and (c) it is independent of intensity variations across MR images. Our detection algorithm can play a useful role in indexing and storage of MRI data and as an initial step toward accurate tumor boundary delineation.
Citation
N. Ray, R. Greiner, A. Murtha. "Using Symmetry to Detect Abnormalities in Brain MRI". Computer Society of India Communications, 31(19), pp 7--10, January 2008.| Keywords: | brain segmentation, brain tumor, magnetic resonance, BTAP |
| Category: | In Journal |
BibTeX
@article{Ray+al:CSIC08,
author = {Nilanjan Ray and Russ Greiner and Albert Murtha},
title = {Using Symmetry to Detect Abnormalities in Brain MRI},
Volume = "31",
Number = "19",
Pages = {7--10},
journal = {Computer Society of India Communications},
year = 2008,
}Last Updated: March 23, 2020Submitted by Sabina P
