Brain MR perfusion image segmentation using independent component analysis and hierarchical clustering

Chia Fung Lu, Yen Chun Chou, Wan Yuo Guo, Yu Te Wu

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

2 Citations (Scopus)

Abstract

Extraction of various perfusion components from dynamic-susceptibility- contrast (DSC) MR brain images is critical for the analysis of brain perfusion. According to the variation of temporal signal on different brain tissues, one can segment whole brain area into distinct blood supply patterns which are vital for the profound analysis of cerebral hemodynamics. In this study, independent component analysis (ICA) is used to project the perfusion image data into independent components from which each elucidated tissue cluster can be automatically segment out by using the hierarchical clustering (HC). Five normal subjects and a case of internal carotid artery stenosis subjects were analyzed. The results demonstrated that ICA-HC is effective in multi-tissue hemodynamic classification which improves differentiation of pathological and physiological hemodynamics.

Original languageEnglish
Title of host publication29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
Pages5547-5550
Number of pages4
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 - Lyon, France
Duration: Aug 23 2007Aug 26 2007

Conference

Conference29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
CountryFrance
CityLyon
Period8/23/078/26/07

Fingerprint

Independent component analysis
Image segmentation
Brain
Hemodynamics
Tissue
Blood

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Lu, C. F., Chou, Y. C., Guo, W. Y., & Wu, Y. T. (2007). Brain MR perfusion image segmentation using independent component analysis and hierarchical clustering. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 (pp. 5547-5550). [4353603] https://doi.org/10.1109/IEMBS.2007.4353603

Brain MR perfusion image segmentation using independent component analysis and hierarchical clustering. / Lu, Chia Fung; Chou, Yen Chun; Guo, Wan Yuo; Wu, Yu Te.

29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. p. 5547-5550 4353603.

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

Lu, CF, Chou, YC, Guo, WY & Wu, YT 2007, Brain MR perfusion image segmentation using independent component analysis and hierarchical clustering. in 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07., 4353603, pp. 5547-5550, 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07, Lyon, France, 8/23/07. https://doi.org/10.1109/IEMBS.2007.4353603
Lu CF, Chou YC, Guo WY, Wu YT. Brain MR perfusion image segmentation using independent component analysis and hierarchical clustering. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. p. 5547-5550. 4353603 https://doi.org/10.1109/IEMBS.2007.4353603
Lu, Chia Fung ; Chou, Yen Chun ; Guo, Wan Yuo ; Wu, Yu Te. / Brain MR perfusion image segmentation using independent component analysis and hierarchical clustering. 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. pp. 5547-5550
@inproceedings{f56112264af14907a79c6f76a35d5821,
title = "Brain MR perfusion image segmentation using independent component analysis and hierarchical clustering",
abstract = "Extraction of various perfusion components from dynamic-susceptibility- contrast (DSC) MR brain images is critical for the analysis of brain perfusion. According to the variation of temporal signal on different brain tissues, one can segment whole brain area into distinct blood supply patterns which are vital for the profound analysis of cerebral hemodynamics. In this study, independent component analysis (ICA) is used to project the perfusion image data into independent components from which each elucidated tissue cluster can be automatically segment out by using the hierarchical clustering (HC). Five normal subjects and a case of internal carotid artery stenosis subjects were analyzed. The results demonstrated that ICA-HC is effective in multi-tissue hemodynamic classification which improves differentiation of pathological and physiological hemodynamics.",
author = "Lu, {Chia Fung} and Chou, {Yen Chun} and Guo, {Wan Yuo} and Wu, {Yu Te}",
year = "2007",
doi = "10.1109/IEMBS.2007.4353603",
language = "English",
isbn = "1424407885",
pages = "5547--5550",
booktitle = "29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07",

}

TY - GEN

T1 - Brain MR perfusion image segmentation using independent component analysis and hierarchical clustering

AU - Lu, Chia Fung

AU - Chou, Yen Chun

AU - Guo, Wan Yuo

AU - Wu, Yu Te

PY - 2007

Y1 - 2007

N2 - Extraction of various perfusion components from dynamic-susceptibility- contrast (DSC) MR brain images is critical for the analysis of brain perfusion. According to the variation of temporal signal on different brain tissues, one can segment whole brain area into distinct blood supply patterns which are vital for the profound analysis of cerebral hemodynamics. In this study, independent component analysis (ICA) is used to project the perfusion image data into independent components from which each elucidated tissue cluster can be automatically segment out by using the hierarchical clustering (HC). Five normal subjects and a case of internal carotid artery stenosis subjects were analyzed. The results demonstrated that ICA-HC is effective in multi-tissue hemodynamic classification which improves differentiation of pathological and physiological hemodynamics.

AB - Extraction of various perfusion components from dynamic-susceptibility- contrast (DSC) MR brain images is critical for the analysis of brain perfusion. According to the variation of temporal signal on different brain tissues, one can segment whole brain area into distinct blood supply patterns which are vital for the profound analysis of cerebral hemodynamics. In this study, independent component analysis (ICA) is used to project the perfusion image data into independent components from which each elucidated tissue cluster can be automatically segment out by using the hierarchical clustering (HC). Five normal subjects and a case of internal carotid artery stenosis subjects were analyzed. The results demonstrated that ICA-HC is effective in multi-tissue hemodynamic classification which improves differentiation of pathological and physiological hemodynamics.

UR - http://www.scopus.com/inward/record.url?scp=57649181769&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57649181769&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2007.4353603

DO - 10.1109/IEMBS.2007.4353603

M3 - Conference contribution

AN - SCOPUS:57649181769

SN - 1424407885

SN - 9781424407880

SP - 5547

EP - 5550

BT - 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07

ER -