Automatic segmentation and classification of human brain image based on a fuzzy brain atlas

Ou Tan, Chunguang Jia, Huilong Duan, Weixue Lu

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

Abstract

It is difficult to automatically segment and classify tomograph images of actual patient's brain. Therefore, many interactive operations are performed. It is very time consuming and its precision is much depended on the user. In this paper, we combine a brain atlas and 3D fuzzy image segmentation into the image matching. It can not only find out the precise boundary of anatomic structure but also save time of the interactive operation. At first, the anatomic information of atlas is mapped into tomograph images of actual brain with a two step image matching method. Then, based on the mapping result, a 3D fuzzy structure mask is calculated. With the fuzzy information of anatomic structure, a new method of fuzzy clustering based on genetic algorithm is used to segment and classify the real brain image. There is only a minimum requirement of interaction in the whole process, including removing the skull and selecting some intrinsic point pairs.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsJ. Zhou, A.K. Jain, T. Zhang, Y. Zhu, M. Ding, J. Liu
PublisherSPIE
Pages508-511
Number of pages4
Volume3545
StatePublished - 1998
Externally publishedYes
EventProceedings of the 1998 International Symposium on Multispectral Image Processing, ISMIP'98 - Wuhan, China
Duration: Oct 21 1998Oct 23 1998

Other

OtherProceedings of the 1998 International Symposium on Multispectral Image Processing, ISMIP'98
CityWuhan, China
Period10/21/9810/23/98

Fingerprint

brain
Brain
Image matching
Fuzzy clustering
Image segmentation
Masks
skull
Genetic algorithms
genetic algorithms
masks
requirements
interactions

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Tan, O., Jia, C., Duan, H., & Lu, W. (1998). Automatic segmentation and classification of human brain image based on a fuzzy brain atlas. In J. Zhou, A. K. Jain, T. Zhang, Y. Zhu, M. Ding, & J. Liu (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 3545, pp. 508-511). SPIE.

Automatic segmentation and classification of human brain image based on a fuzzy brain atlas. / Tan, Ou; Jia, Chunguang; Duan, Huilong; Lu, Weixue.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / J. Zhou; A.K. Jain; T. Zhang; Y. Zhu; M. Ding; J. Liu. Vol. 3545 SPIE, 1998. p. 508-511.

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

Tan, O, Jia, C, Duan, H & Lu, W 1998, Automatic segmentation and classification of human brain image based on a fuzzy brain atlas. in J Zhou, AK Jain, T Zhang, Y Zhu, M Ding & J Liu (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 3545, SPIE, pp. 508-511, Proceedings of the 1998 International Symposium on Multispectral Image Processing, ISMIP'98, Wuhan, China, 10/21/98.
Tan O, Jia C, Duan H, Lu W. Automatic segmentation and classification of human brain image based on a fuzzy brain atlas. In Zhou J, Jain AK, Zhang T, Zhu Y, Ding M, Liu J, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3545. SPIE. 1998. p. 508-511
Tan, Ou ; Jia, Chunguang ; Duan, Huilong ; Lu, Weixue. / Automatic segmentation and classification of human brain image based on a fuzzy brain atlas. Proceedings of SPIE - The International Society for Optical Engineering. editor / J. Zhou ; A.K. Jain ; T. Zhang ; Y. Zhu ; M. Ding ; J. Liu. Vol. 3545 SPIE, 1998. pp. 508-511
@inproceedings{539786da6b6c4d1db14281b5f33092a8,
title = "Automatic segmentation and classification of human brain image based on a fuzzy brain atlas",
abstract = "It is difficult to automatically segment and classify tomograph images of actual patient's brain. Therefore, many interactive operations are performed. It is very time consuming and its precision is much depended on the user. In this paper, we combine a brain atlas and 3D fuzzy image segmentation into the image matching. It can not only find out the precise boundary of anatomic structure but also save time of the interactive operation. At first, the anatomic information of atlas is mapped into tomograph images of actual brain with a two step image matching method. Then, based on the mapping result, a 3D fuzzy structure mask is calculated. With the fuzzy information of anatomic structure, a new method of fuzzy clustering based on genetic algorithm is used to segment and classify the real brain image. There is only a minimum requirement of interaction in the whole process, including removing the skull and selecting some intrinsic point pairs.",
author = "Ou Tan and Chunguang Jia and Huilong Duan and Weixue Lu",
year = "1998",
language = "English (US)",
volume = "3545",
pages = "508--511",
editor = "J. Zhou and A.K. Jain and T. Zhang and Y. Zhu and M. Ding and J. Liu",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",

}

TY - GEN

T1 - Automatic segmentation and classification of human brain image based on a fuzzy brain atlas

AU - Tan, Ou

AU - Jia, Chunguang

AU - Duan, Huilong

AU - Lu, Weixue

PY - 1998

Y1 - 1998

N2 - It is difficult to automatically segment and classify tomograph images of actual patient's brain. Therefore, many interactive operations are performed. It is very time consuming and its precision is much depended on the user. In this paper, we combine a brain atlas and 3D fuzzy image segmentation into the image matching. It can not only find out the precise boundary of anatomic structure but also save time of the interactive operation. At first, the anatomic information of atlas is mapped into tomograph images of actual brain with a two step image matching method. Then, based on the mapping result, a 3D fuzzy structure mask is calculated. With the fuzzy information of anatomic structure, a new method of fuzzy clustering based on genetic algorithm is used to segment and classify the real brain image. There is only a minimum requirement of interaction in the whole process, including removing the skull and selecting some intrinsic point pairs.

AB - It is difficult to automatically segment and classify tomograph images of actual patient's brain. Therefore, many interactive operations are performed. It is very time consuming and its precision is much depended on the user. In this paper, we combine a brain atlas and 3D fuzzy image segmentation into the image matching. It can not only find out the precise boundary of anatomic structure but also save time of the interactive operation. At first, the anatomic information of atlas is mapped into tomograph images of actual brain with a two step image matching method. Then, based on the mapping result, a 3D fuzzy structure mask is calculated. With the fuzzy information of anatomic structure, a new method of fuzzy clustering based on genetic algorithm is used to segment and classify the real brain image. There is only a minimum requirement of interaction in the whole process, including removing the skull and selecting some intrinsic point pairs.

UR - http://www.scopus.com/inward/record.url?scp=0032302288&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032302288&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3545

SP - 508

EP - 511

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

A2 - Zhou, J.

A2 - Jain, A.K.

A2 - Zhang, T.

A2 - Zhu, Y.

A2 - Ding, M.

A2 - Liu, J.

PB - SPIE

ER -