Automatic generation of membership functions for brain MR images

C. W. Chang, G. R. Hillman, H. Ying, T. A. Kent, J. Yen

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

1 Citation (Scopus)

Abstract

In this paper, we present a rule-based fuzzy segmentation system that is capable of segmenting magnetic resonance (MR) images of diseased human brains into physiologically and pathologically meaningful regions for measurement. We have developed a novel technique to automatically generate the membership functions for the fuzzy sets in the antecedent of the IF-THEN fuzzy rules in our system. Using this fuzzy system, we have performed the segmentation of brain images with periventricular lesions into four classes (grey matter, white matter, cerebrospinal fluid and periventricular lesions). The brain images were processed by our rule-based system as well as by the standard fuzzy c-means (FCM) algorithm used for performance comparison. The results, confirmed by the medical experts, showed that the rule-based fuzzy system significantly outperformed the standard FCM in the segmentation of the abnormal brain images.

Original languageEnglish (US)
Title of host publicationSoft Computing in Intelligent Systems and Information Processing
EditorsY.Y. Chen, K. Hirota, J.Y. Yen
PublisherIEEE
Pages182-187
Number of pages6
StatePublished - 1996
EventProceedings of the 1996 Asian Fuzzy Systems Symposium - Kenting, Taiwan
Duration: Dec 11 1996Dec 14 1996

Other

OtherProceedings of the 1996 Asian Fuzzy Systems Symposium
CityKenting, Taiwan
Period12/11/9612/14/96

Fingerprint

Magnetic resonance
Membership functions
Brain
Fuzzy systems
Cerebrospinal fluid
Knowledge based systems
Fuzzy rules
Fuzzy sets

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Chang, C. W., Hillman, G. R., Ying, H., Kent, T. A., & Yen, J. (1996). Automatic generation of membership functions for brain MR images. In Y. Y. Chen, K. Hirota, & J. Y. Yen (Eds.), Soft Computing in Intelligent Systems and Information Processing (pp. 182-187). IEEE.
Chang, C. W. ; Hillman, G. R. ; Ying, H. ; Kent, T. A. ; Yen, J. / Automatic generation of membership functions for brain MR images. Soft Computing in Intelligent Systems and Information Processing. editor / Y.Y. Chen ; K. Hirota ; J.Y. Yen. IEEE, 1996. pp. 182-187
@inproceedings{cfe0c771947d4afb94153fff5b0b2ec2,
title = "Automatic generation of membership functions for brain MR images",
abstract = "In this paper, we present a rule-based fuzzy segmentation system that is capable of segmenting magnetic resonance (MR) images of diseased human brains into physiologically and pathologically meaningful regions for measurement. We have developed a novel technique to automatically generate the membership functions for the fuzzy sets in the antecedent of the IF-THEN fuzzy rules in our system. Using this fuzzy system, we have performed the segmentation of brain images with periventricular lesions into four classes (grey matter, white matter, cerebrospinal fluid and periventricular lesions). The brain images were processed by our rule-based system as well as by the standard fuzzy c-means (FCM) algorithm used for performance comparison. The results, confirmed by the medical experts, showed that the rule-based fuzzy system significantly outperformed the standard FCM in the segmentation of the abnormal brain images.",
author = "Chang, {C. W.} and Hillman, {G. R.} and H. Ying and Kent, {T. A.} and J. Yen",
year = "1996",
language = "English (US)",
pages = "182--187",
editor = "Y.Y. Chen and K. Hirota and J.Y. Yen",
booktitle = "Soft Computing in Intelligent Systems and Information Processing",
publisher = "IEEE",

}

Chang, CW, Hillman, GR, Ying, H, Kent, TA & Yen, J 1996, Automatic generation of membership functions for brain MR images. in YY Chen, K Hirota & JY Yen (eds), Soft Computing in Intelligent Systems and Information Processing. IEEE, pp. 182-187, Proceedings of the 1996 Asian Fuzzy Systems Symposium, Kenting, Taiwan, 12/11/96.

Automatic generation of membership functions for brain MR images. / Chang, C. W.; Hillman, G. R.; Ying, H.; Kent, T. A.; Yen, J.

Soft Computing in Intelligent Systems and Information Processing. ed. / Y.Y. Chen; K. Hirota; J.Y. Yen. IEEE, 1996. p. 182-187.

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

TY - GEN

T1 - Automatic generation of membership functions for brain MR images

AU - Chang, C. W.

AU - Hillman, G. R.

AU - Ying, H.

AU - Kent, T. A.

AU - Yen, J.

PY - 1996

Y1 - 1996

N2 - In this paper, we present a rule-based fuzzy segmentation system that is capable of segmenting magnetic resonance (MR) images of diseased human brains into physiologically and pathologically meaningful regions for measurement. We have developed a novel technique to automatically generate the membership functions for the fuzzy sets in the antecedent of the IF-THEN fuzzy rules in our system. Using this fuzzy system, we have performed the segmentation of brain images with periventricular lesions into four classes (grey matter, white matter, cerebrospinal fluid and periventricular lesions). The brain images were processed by our rule-based system as well as by the standard fuzzy c-means (FCM) algorithm used for performance comparison. The results, confirmed by the medical experts, showed that the rule-based fuzzy system significantly outperformed the standard FCM in the segmentation of the abnormal brain images.

AB - In this paper, we present a rule-based fuzzy segmentation system that is capable of segmenting magnetic resonance (MR) images of diseased human brains into physiologically and pathologically meaningful regions for measurement. We have developed a novel technique to automatically generate the membership functions for the fuzzy sets in the antecedent of the IF-THEN fuzzy rules in our system. Using this fuzzy system, we have performed the segmentation of brain images with periventricular lesions into four classes (grey matter, white matter, cerebrospinal fluid and periventricular lesions). The brain images were processed by our rule-based system as well as by the standard fuzzy c-means (FCM) algorithm used for performance comparison. The results, confirmed by the medical experts, showed that the rule-based fuzzy system significantly outperformed the standard FCM in the segmentation of the abnormal brain images.

UR - http://www.scopus.com/inward/record.url?scp=0030365118&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030365118&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030365118

SP - 182

EP - 187

BT - Soft Computing in Intelligent Systems and Information Processing

A2 - Chen, Y.Y.

A2 - Hirota, K.

A2 - Yen, J.Y.

PB - IEEE

ER -

Chang CW, Hillman GR, Ying H, Kent TA, Yen J. Automatic generation of membership functions for brain MR images. In Chen YY, Hirota K, Yen JY, editors, Soft Computing in Intelligent Systems and Information Processing. IEEE. 1996. p. 182-187