Voting-based active contour segmentation of fmri images of the brain

Gowri Srinivasa, Vivek S. Oak, Siddharth Garg, Matthew C. Fickus, Jelena Kovacevic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose an algorithm for automated segmentation of white matter in brain MRI images, which can be used to create connected representations of the gray matter in the cerebral cortex of the brain. These representations then provide meaningful visualizations of brain activity data obtained from fMRI studies. Our algorithm to segment the white matter from the rest of the image is based on an active-contour scheme - STACS, and thus inherits all the advantages active-contour schemes possess. The segmentation, performed in three different planes of image capture, is driven by the statistics of the image. We combine the segmentation results from the three planes by a majority voting procedure to classify each voxel in the image as white matter or not. We improve the runtime of the algorithm by rewriting the force computation as a multiscale transformation. Initial results of labeling the white matter with an accuracy of about 89% show great promise of the proposed algorithm.

Original languageEnglish (US)
Title of host publication2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings
Pages1100-1103
Number of pages4
DOIs
StatePublished - 2008
Event2008 IEEE International Conference on Image Processing, ICIP 2008 - San Diego, CA, United States
Duration: Oct 12 2008Oct 15 2008

Other

Other2008 IEEE International Conference on Image Processing, ICIP 2008
CountryUnited States
CitySan Diego, CA
Period10/12/0810/15/08

Fingerprint

Brain
Magnetic resonance imaging
Labeling
Visualization
Statistics

Keywords

  • Active contour
  • Brain fMRI
  • Segmentation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Srinivasa, G., Oak, V. S., Garg, S., Fickus, M. C., & Kovacevic, J. (2008). Voting-based active contour segmentation of fmri images of the brain. In 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings (pp. 1100-1103). [4711951] https://doi.org/10.1109/ICIP.2008.4711951

Voting-based active contour segmentation of fmri images of the brain. / Srinivasa, Gowri; Oak, Vivek S.; Garg, Siddharth; Fickus, Matthew C.; Kovacevic, Jelena.

2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings. 2008. p. 1100-1103 4711951.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Srinivasa, G, Oak, VS, Garg, S, Fickus, MC & Kovacevic, J 2008, Voting-based active contour segmentation of fmri images of the brain. in 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings., 4711951, pp. 1100-1103, 2008 IEEE International Conference on Image Processing, ICIP 2008, San Diego, CA, United States, 10/12/08. https://doi.org/10.1109/ICIP.2008.4711951
Srinivasa G, Oak VS, Garg S, Fickus MC, Kovacevic J. Voting-based active contour segmentation of fmri images of the brain. In 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings. 2008. p. 1100-1103. 4711951 https://doi.org/10.1109/ICIP.2008.4711951
Srinivasa, Gowri ; Oak, Vivek S. ; Garg, Siddharth ; Fickus, Matthew C. ; Kovacevic, Jelena. / Voting-based active contour segmentation of fmri images of the brain. 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings. 2008. pp. 1100-1103
@inproceedings{bba4c1f0c5284f14a56730504afe4adf,
title = "Voting-based active contour segmentation of fmri images of the brain",
abstract = "We propose an algorithm for automated segmentation of white matter in brain MRI images, which can be used to create connected representations of the gray matter in the cerebral cortex of the brain. These representations then provide meaningful visualizations of brain activity data obtained from fMRI studies. Our algorithm to segment the white matter from the rest of the image is based on an active-contour scheme - STACS, and thus inherits all the advantages active-contour schemes possess. The segmentation, performed in three different planes of image capture, is driven by the statistics of the image. We combine the segmentation results from the three planes by a majority voting procedure to classify each voxel in the image as white matter or not. We improve the runtime of the algorithm by rewriting the force computation as a multiscale transformation. Initial results of labeling the white matter with an accuracy of about 89{\%} show great promise of the proposed algorithm.",
keywords = "Active contour, Brain fMRI, Segmentation",
author = "Gowri Srinivasa and Oak, {Vivek S.} and Siddharth Garg and Fickus, {Matthew C.} and Jelena Kovacevic",
year = "2008",
doi = "10.1109/ICIP.2008.4711951",
language = "English (US)",
isbn = "1424417643",
pages = "1100--1103",
booktitle = "2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings",

}

TY - GEN

T1 - Voting-based active contour segmentation of fmri images of the brain

AU - Srinivasa, Gowri

AU - Oak, Vivek S.

AU - Garg, Siddharth

AU - Fickus, Matthew C.

AU - Kovacevic, Jelena

PY - 2008

Y1 - 2008

N2 - We propose an algorithm for automated segmentation of white matter in brain MRI images, which can be used to create connected representations of the gray matter in the cerebral cortex of the brain. These representations then provide meaningful visualizations of brain activity data obtained from fMRI studies. Our algorithm to segment the white matter from the rest of the image is based on an active-contour scheme - STACS, and thus inherits all the advantages active-contour schemes possess. The segmentation, performed in three different planes of image capture, is driven by the statistics of the image. We combine the segmentation results from the three planes by a majority voting procedure to classify each voxel in the image as white matter or not. We improve the runtime of the algorithm by rewriting the force computation as a multiscale transformation. Initial results of labeling the white matter with an accuracy of about 89% show great promise of the proposed algorithm.

AB - We propose an algorithm for automated segmentation of white matter in brain MRI images, which can be used to create connected representations of the gray matter in the cerebral cortex of the brain. These representations then provide meaningful visualizations of brain activity data obtained from fMRI studies. Our algorithm to segment the white matter from the rest of the image is based on an active-contour scheme - STACS, and thus inherits all the advantages active-contour schemes possess. The segmentation, performed in three different planes of image capture, is driven by the statistics of the image. We combine the segmentation results from the three planes by a majority voting procedure to classify each voxel in the image as white matter or not. We improve the runtime of the algorithm by rewriting the force computation as a multiscale transformation. Initial results of labeling the white matter with an accuracy of about 89% show great promise of the proposed algorithm.

KW - Active contour

KW - Brain fMRI

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=70049088535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70049088535&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2008.4711951

DO - 10.1109/ICIP.2008.4711951

M3 - Conference contribution

AN - SCOPUS:70049088535

SN - 1424417643

SN - 9781424417643

SP - 1100

EP - 1103

BT - 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings

ER -