MR image segmentation using a fuzzy-based neural network

Jesse C. Ma, Jeffrey J Rodriguez

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

Abstract

Most techniques for segmentation of magnetic resonance images of the brain are extremely time consuming and/or require extensive user interaction. An automated segmentation procedure is presented, whereby the fuzzy c-means classification results are used to train a feed-forward neural network. The cascade correlation algorithm is used to optimize the network training process. After applying a brain-extraction technique, the segmented images are then used for rendering computer-generated images of the brain's surface. Experimental results using real, 3-D magnetic resonance images are presented, demonstrating the performance of the segmentation as well as the final surface rendering.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages2190-2195
Number of pages6
Volume5
StatePublished - 1995
EventProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
Duration: Nov 27 1995Dec 1 1995

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period11/27/9512/1/95

Fingerprint

Image segmentation
Brain
Magnetic resonance
Neural networks
Feedforward neural networks

ASJC Scopus subject areas

  • Software

Cite this

Ma, J. C., & Rodriguez, J. J. (1995). MR image segmentation using a fuzzy-based neural network. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 5, pp. 2190-2195). IEEE.

MR image segmentation using a fuzzy-based neural network. / Ma, Jesse C.; Rodriguez, Jeffrey J.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 5 IEEE, 1995. p. 2190-2195.

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

Ma, JC & Rodriguez, JJ 1995, MR image segmentation using a fuzzy-based neural network. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 5, IEEE, pp. 2190-2195, Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 11/27/95.
Ma JC, Rodriguez JJ. MR image segmentation using a fuzzy-based neural network. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 5. IEEE. 1995. p. 2190-2195
Ma, Jesse C. ; Rodriguez, Jeffrey J. / MR image segmentation using a fuzzy-based neural network. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 5 IEEE, 1995. pp. 2190-2195
@inproceedings{aaacee7c3af84974be8ce82f9c687f24,
title = "MR image segmentation using a fuzzy-based neural network",
abstract = "Most techniques for segmentation of magnetic resonance images of the brain are extremely time consuming and/or require extensive user interaction. An automated segmentation procedure is presented, whereby the fuzzy c-means classification results are used to train a feed-forward neural network. The cascade correlation algorithm is used to optimize the network training process. After applying a brain-extraction technique, the segmented images are then used for rendering computer-generated images of the brain's surface. Experimental results using real, 3-D magnetic resonance images are presented, demonstrating the performance of the segmentation as well as the final surface rendering.",
author = "Ma, {Jesse C.} and Rodriguez, {Jeffrey J}",
year = "1995",
language = "English (US)",
volume = "5",
pages = "2190--2195",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - MR image segmentation using a fuzzy-based neural network

AU - Ma, Jesse C.

AU - Rodriguez, Jeffrey J

PY - 1995

Y1 - 1995

N2 - Most techniques for segmentation of magnetic resonance images of the brain are extremely time consuming and/or require extensive user interaction. An automated segmentation procedure is presented, whereby the fuzzy c-means classification results are used to train a feed-forward neural network. The cascade correlation algorithm is used to optimize the network training process. After applying a brain-extraction technique, the segmented images are then used for rendering computer-generated images of the brain's surface. Experimental results using real, 3-D magnetic resonance images are presented, demonstrating the performance of the segmentation as well as the final surface rendering.

AB - Most techniques for segmentation of magnetic resonance images of the brain are extremely time consuming and/or require extensive user interaction. An automated segmentation procedure is presented, whereby the fuzzy c-means classification results are used to train a feed-forward neural network. The cascade correlation algorithm is used to optimize the network training process. After applying a brain-extraction technique, the segmented images are then used for rendering computer-generated images of the brain's surface. Experimental results using real, 3-D magnetic resonance images are presented, demonstrating the performance of the segmentation as well as the final surface rendering.

UR - http://www.scopus.com/inward/record.url?scp=0029461018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029461018&partnerID=8YFLogxK

M3 - Conference contribution

VL - 5

SP - 2190

EP - 2195

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -