Segmentation of multidimensional magnetic resonance (MR) images using a fuzzy neural network

Jesse C. Ma, Jeffrey J Rodriguez

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Methods of 3-D visualization of the brain based on fuzzy c-means (FCM) classified magnetic resonance (MR) images and a neural network trained on the FCM data are presented. A 3-D MR scan of a volunteer serves as the basis for the unsupervised classification techniques. The images were first classified into different tissue types by using FCM. The classified images were then reconstructed for 3-D display. Results show that individual tissue types can be discriminated during the 3-D rendering process. A neural network trained on the fuzzy classification data was also implemented. By using the cascade correlation algorithm during the network training, much of the tedious training work was avoided. The preliminary results from the neural network approach are quite encouraging.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsAndrew G. Tescher
PublisherSociety of Photo-Optical Instrumentation Engineers
Pages636-643
Number of pages8
Volume2298
ISBN (Print)0819416223
StatePublished - 1994
EventApplications of Digital Image Processing XVII - San Diego, CA, USA
Duration: Jul 26 1994Jul 29 1994

Other

OtherApplications of Digital Image Processing XVII
CitySan Diego, CA, USA
Period7/26/947/29/94

Fingerprint

Fuzzy neural networks
Magnetic resonance
magnetic resonance
Neural networks
Tissue
education
Brain
Visualization
Display devices
brain
cascades

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Ma, J. C., & Rodriguez, J. J. (1994). Segmentation of multidimensional magnetic resonance (MR) images using a fuzzy neural network. In A. G. Tescher (Ed.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 2298, pp. 636-643). Society of Photo-Optical Instrumentation Engineers.

Segmentation of multidimensional magnetic resonance (MR) images using a fuzzy neural network. / Ma, Jesse C.; Rodriguez, Jeffrey J.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / Andrew G. Tescher. Vol. 2298 Society of Photo-Optical Instrumentation Engineers, 1994. p. 636-643.

Research output: Chapter in Book/Report/Conference proceedingChapter

Ma, JC & Rodriguez, JJ 1994, Segmentation of multidimensional magnetic resonance (MR) images using a fuzzy neural network. in AG Tescher (ed.), Proceedings of SPIE - The International Society for Optical Engineering. vol. 2298, Society of Photo-Optical Instrumentation Engineers, pp. 636-643, Applications of Digital Image Processing XVII, San Diego, CA, USA, 7/26/94.
Ma JC, Rodriguez JJ. Segmentation of multidimensional magnetic resonance (MR) images using a fuzzy neural network. In Tescher AG, editor, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2298. Society of Photo-Optical Instrumentation Engineers. 1994. p. 636-643
Ma, Jesse C. ; Rodriguez, Jeffrey J. / Segmentation of multidimensional magnetic resonance (MR) images using a fuzzy neural network. Proceedings of SPIE - The International Society for Optical Engineering. editor / Andrew G. Tescher. Vol. 2298 Society of Photo-Optical Instrumentation Engineers, 1994. pp. 636-643
@inbook{285652552f2b4e0d87a8a7d189de2881,
title = "Segmentation of multidimensional magnetic resonance (MR) images using a fuzzy neural network",
abstract = "Methods of 3-D visualization of the brain based on fuzzy c-means (FCM) classified magnetic resonance (MR) images and a neural network trained on the FCM data are presented. A 3-D MR scan of a volunteer serves as the basis for the unsupervised classification techniques. The images were first classified into different tissue types by using FCM. The classified images were then reconstructed for 3-D display. Results show that individual tissue types can be discriminated during the 3-D rendering process. A neural network trained on the fuzzy classification data was also implemented. By using the cascade correlation algorithm during the network training, much of the tedious training work was avoided. The preliminary results from the neural network approach are quite encouraging.",
author = "Ma, {Jesse C.} and Rodriguez, {Jeffrey J}",
year = "1994",
language = "English (US)",
isbn = "0819416223",
volume = "2298",
pages = "636--643",
editor = "Tescher, {Andrew G.}",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Society of Photo-Optical Instrumentation Engineers",

}

TY - CHAP

T1 - Segmentation of multidimensional magnetic resonance (MR) images using a fuzzy neural network

AU - Ma, Jesse C.

AU - Rodriguez, Jeffrey J

PY - 1994

Y1 - 1994

N2 - Methods of 3-D visualization of the brain based on fuzzy c-means (FCM) classified magnetic resonance (MR) images and a neural network trained on the FCM data are presented. A 3-D MR scan of a volunteer serves as the basis for the unsupervised classification techniques. The images were first classified into different tissue types by using FCM. The classified images were then reconstructed for 3-D display. Results show that individual tissue types can be discriminated during the 3-D rendering process. A neural network trained on the fuzzy classification data was also implemented. By using the cascade correlation algorithm during the network training, much of the tedious training work was avoided. The preliminary results from the neural network approach are quite encouraging.

AB - Methods of 3-D visualization of the brain based on fuzzy c-means (FCM) classified magnetic resonance (MR) images and a neural network trained on the FCM data are presented. A 3-D MR scan of a volunteer serves as the basis for the unsupervised classification techniques. The images were first classified into different tissue types by using FCM. The classified images were then reconstructed for 3-D display. Results show that individual tissue types can be discriminated during the 3-D rendering process. A neural network trained on the fuzzy classification data was also implemented. By using the cascade correlation algorithm during the network training, much of the tedious training work was avoided. The preliminary results from the neural network approach are quite encouraging.

UR - http://www.scopus.com/inward/record.url?scp=0028732890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028732890&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0028732890

SN - 0819416223

VL - 2298

SP - 636

EP - 643

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Tescher, Andrew G.

PB - Society of Photo-Optical Instrumentation Engineers

ER -