Statistical asymmetry-based brain tumor segmentation from 3D MR images

Chen Ping Yu, Guilherme C.S. Ruppert, Dan Thach Nguyen, Alexandre X. Falcao, Yanxi Liu

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

9 Citations (Scopus)

Abstract

The precise segmentation of brain tumors from MR images is necessary for surgical planning. However, it is a tedious task for the medical professionals to process manually. The performance of supervised machine learning techniques for automatic tumor segmentation is time consuming and very dependent on the type of the training samples. Brain tumors are statistically asymmetrical blobs with respect to the mid-sagittal plane (MSP) in the brain and we present an asymmetry-based, novel, fast, fully-automatic and unsupervised framework for 3D brain tumor segmentation from MR images. Our approach detects asymmetrical intensity deviation of brain tissues in 4 stages: (1) automatic MSP extraction, (2) asymmetrical slice extraction for an estimated tumor location, (3) region of interest localization, and (4) 3D tumor volume delineation using a watershed method. The method has been validated on 17 clinical MR volumes with a 71.23%±27.68% mean Jaccard Coefficient.

Original languageEnglish (US)
Title of host publicationBIOSIGNALS 2012 - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing
Pages527-533
Number of pages7
StatePublished - Jun 13 2012
EventInternational Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2012 - Vilamoura, Algarve, Portugal
Duration: Feb 1 2012Feb 4 2012

Publication series

NameBIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing

Other

OtherInternational Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2012
CountryPortugal
CityVilamoura, Algarve
Period2/1/122/4/12

Fingerprint

Tumors
Brain
Watersheds
Learning systems
Tissue
Planning

All Science Journal Classification (ASJC) codes

  • Signal Processing

Cite this

Yu, C. P., Ruppert, G. C. S., Nguyen, D. T., Falcao, A. X., & Liu, Y. (2012). Statistical asymmetry-based brain tumor segmentation from 3D MR images. In BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing (pp. 527-533). (BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing).
Yu, Chen Ping ; Ruppert, Guilherme C.S. ; Nguyen, Dan Thach ; Falcao, Alexandre X. ; Liu, Yanxi. / Statistical asymmetry-based brain tumor segmentation from 3D MR images. BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing. 2012. pp. 527-533 (BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing).
@inproceedings{0ddc55060bbb4de69c91eda8d17ad405,
title = "Statistical asymmetry-based brain tumor segmentation from 3D MR images",
abstract = "The precise segmentation of brain tumors from MR images is necessary for surgical planning. However, it is a tedious task for the medical professionals to process manually. The performance of supervised machine learning techniques for automatic tumor segmentation is time consuming and very dependent on the type of the training samples. Brain tumors are statistically asymmetrical blobs with respect to the mid-sagittal plane (MSP) in the brain and we present an asymmetry-based, novel, fast, fully-automatic and unsupervised framework for 3D brain tumor segmentation from MR images. Our approach detects asymmetrical intensity deviation of brain tissues in 4 stages: (1) automatic MSP extraction, (2) asymmetrical slice extraction for an estimated tumor location, (3) region of interest localization, and (4) 3D tumor volume delineation using a watershed method. The method has been validated on 17 clinical MR volumes with a 71.23{\%}±27.68{\%} mean Jaccard Coefficient.",
author = "Yu, {Chen Ping} and Ruppert, {Guilherme C.S.} and Nguyen, {Dan Thach} and Falcao, {Alexandre X.} and Yanxi Liu",
year = "2012",
month = "6",
day = "13",
language = "English (US)",
isbn = "9789898425898",
series = "BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing",
pages = "527--533",
booktitle = "BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing",

}

Yu, CP, Ruppert, GCS, Nguyen, DT, Falcao, AX & Liu, Y 2012, Statistical asymmetry-based brain tumor segmentation from 3D MR images. in BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing. BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing, pp. 527-533, International Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2012, Vilamoura, Algarve, Portugal, 2/1/12.

Statistical asymmetry-based brain tumor segmentation from 3D MR images. / Yu, Chen Ping; Ruppert, Guilherme C.S.; Nguyen, Dan Thach; Falcao, Alexandre X.; Liu, Yanxi.

BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing. 2012. p. 527-533 (BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing).

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

TY - GEN

T1 - Statistical asymmetry-based brain tumor segmentation from 3D MR images

AU - Yu, Chen Ping

AU - Ruppert, Guilherme C.S.

AU - Nguyen, Dan Thach

AU - Falcao, Alexandre X.

AU - Liu, Yanxi

PY - 2012/6/13

Y1 - 2012/6/13

N2 - The precise segmentation of brain tumors from MR images is necessary for surgical planning. However, it is a tedious task for the medical professionals to process manually. The performance of supervised machine learning techniques for automatic tumor segmentation is time consuming and very dependent on the type of the training samples. Brain tumors are statistically asymmetrical blobs with respect to the mid-sagittal plane (MSP) in the brain and we present an asymmetry-based, novel, fast, fully-automatic and unsupervised framework for 3D brain tumor segmentation from MR images. Our approach detects asymmetrical intensity deviation of brain tissues in 4 stages: (1) automatic MSP extraction, (2) asymmetrical slice extraction for an estimated tumor location, (3) region of interest localization, and (4) 3D tumor volume delineation using a watershed method. The method has been validated on 17 clinical MR volumes with a 71.23%±27.68% mean Jaccard Coefficient.

AB - The precise segmentation of brain tumors from MR images is necessary for surgical planning. However, it is a tedious task for the medical professionals to process manually. The performance of supervised machine learning techniques for automatic tumor segmentation is time consuming and very dependent on the type of the training samples. Brain tumors are statistically asymmetrical blobs with respect to the mid-sagittal plane (MSP) in the brain and we present an asymmetry-based, novel, fast, fully-automatic and unsupervised framework for 3D brain tumor segmentation from MR images. Our approach detects asymmetrical intensity deviation of brain tissues in 4 stages: (1) automatic MSP extraction, (2) asymmetrical slice extraction for an estimated tumor location, (3) region of interest localization, and (4) 3D tumor volume delineation using a watershed method. The method has been validated on 17 clinical MR volumes with a 71.23%±27.68% mean Jaccard Coefficient.

UR - http://www.scopus.com/inward/record.url?scp=84861972259&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861972259&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84861972259

SN - 9789898425898

T3 - BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing

SP - 527

EP - 533

BT - BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing

ER -

Yu CP, Ruppert GCS, Nguyen DT, Falcao AX, Liu Y. Statistical asymmetry-based brain tumor segmentation from 3D MR images. In BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing. 2012. p. 527-533. (BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing).