Fuzzy multi-channel clustering with individualized spatial priors for segmenting brain lesions and infarcts

Evangelia I. Zacharaki, Guray Erus, Anastasios Bezerianos, Christos Davatzikos

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

Abstract

Quantitative analysis of brain lesions and ischemic infarcts is becoming very important due to their association with cardiovascular disease and normal aging. In this paper, we present a semi-supervised segmentation methodology that detects and classifies cerebrovascular disease in multi-channel magnetic resonance (MR) images. The method combines intensity based fuzzy c-means (FCM) segmentation with spatial probability maps calculated from a normative set of images from healthy individuals. Unlike common FCM-based methods which segment only healthy tissue, we have extended the fuzzy segmentation to include patient-specific spatial priors for both pathological conditions (lesions and infarcts). These priors are calculated by estimating the statistical voxel-wise variation of the healthy anatomy, and identifying abnormalities as deviations from normality. False detection is reduced by knowledge-based rules. Assessment on a population of 47 patients from different imaging sites illustrates the potential of the proposed method in segmenting both hyperintense lesions and necrotic infarcts.

Original languageEnglish (US)
Title of host publicationIFIP Advances in Information and Communication Technology
Pages76-85
Number of pages10
Volume382 AICT
EditionPART 2
DOIs
StatePublished - 2012
Externally publishedYes
Event8th International Workshop on Artificial Intelligence Applications and Innovations, AIAI 2012: AIAB, AIeIA, CISE, COPA, IIVC, ISQL, MHDW, and WADTMB - Halkidiki, Greece
Duration: Sep 27 2012Sep 30 2012

Publication series

NameIFIP Advances in Information and Communication Technology
NumberPART 2
Volume382 AICT
ISSN (Print)18684238

Other

Other8th International Workshop on Artificial Intelligence Applications and Innovations, AIAI 2012: AIAB, AIeIA, CISE, COPA, IIVC, ISQL, MHDW, and WADTMB
CountryGreece
CityHalkidiki
Period9/27/129/30/12

Fingerprint

Clustering
Segmentation
Normality
Cardiovascular disease
Deviation
Knowledge-based
Quantitative analysis
Methodology
Imaging

Keywords

  • brain tissue segmentation
  • fuzzy clustering
  • infarcts
  • lesions
  • MRI
  • outlier detection

ASJC Scopus subject areas

  • Information Systems and Management

Cite this

Zacharaki, E. I., Erus, G., Bezerianos, A., & Davatzikos, C. (2012). Fuzzy multi-channel clustering with individualized spatial priors for segmenting brain lesions and infarcts. In IFIP Advances in Information and Communication Technology (PART 2 ed., Vol. 382 AICT, pp. 76-85). (IFIP Advances in Information and Communication Technology; Vol. 382 AICT, No. PART 2). https://doi.org/10.1007/978-3-642-33412-2_8

Fuzzy multi-channel clustering with individualized spatial priors for segmenting brain lesions and infarcts. / Zacharaki, Evangelia I.; Erus, Guray; Bezerianos, Anastasios; Davatzikos, Christos.

IFIP Advances in Information and Communication Technology. Vol. 382 AICT PART 2. ed. 2012. p. 76-85 (IFIP Advances in Information and Communication Technology; Vol. 382 AICT, No. PART 2).

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

Zacharaki, EI, Erus, G, Bezerianos, A & Davatzikos, C 2012, Fuzzy multi-channel clustering with individualized spatial priors for segmenting brain lesions and infarcts. in IFIP Advances in Information and Communication Technology. PART 2 edn, vol. 382 AICT, IFIP Advances in Information and Communication Technology, no. PART 2, vol. 382 AICT, pp. 76-85, 8th International Workshop on Artificial Intelligence Applications and Innovations, AIAI 2012: AIAB, AIeIA, CISE, COPA, IIVC, ISQL, MHDW, and WADTMB, Halkidiki, Greece, 9/27/12. https://doi.org/10.1007/978-3-642-33412-2_8
Zacharaki EI, Erus G, Bezerianos A, Davatzikos C. Fuzzy multi-channel clustering with individualized spatial priors for segmenting brain lesions and infarcts. In IFIP Advances in Information and Communication Technology. PART 2 ed. Vol. 382 AICT. 2012. p. 76-85. (IFIP Advances in Information and Communication Technology; PART 2). https://doi.org/10.1007/978-3-642-33412-2_8
Zacharaki, Evangelia I. ; Erus, Guray ; Bezerianos, Anastasios ; Davatzikos, Christos. / Fuzzy multi-channel clustering with individualized spatial priors for segmenting brain lesions and infarcts. IFIP Advances in Information and Communication Technology. Vol. 382 AICT PART 2. ed. 2012. pp. 76-85 (IFIP Advances in Information and Communication Technology; PART 2).
@inproceedings{910b3ddfd1854c9384dd798bc50ba061,
title = "Fuzzy multi-channel clustering with individualized spatial priors for segmenting brain lesions and infarcts",
abstract = "Quantitative analysis of brain lesions and ischemic infarcts is becoming very important due to their association with cardiovascular disease and normal aging. In this paper, we present a semi-supervised segmentation methodology that detects and classifies cerebrovascular disease in multi-channel magnetic resonance (MR) images. The method combines intensity based fuzzy c-means (FCM) segmentation with spatial probability maps calculated from a normative set of images from healthy individuals. Unlike common FCM-based methods which segment only healthy tissue, we have extended the fuzzy segmentation to include patient-specific spatial priors for both pathological conditions (lesions and infarcts). These priors are calculated by estimating the statistical voxel-wise variation of the healthy anatomy, and identifying abnormalities as deviations from normality. False detection is reduced by knowledge-based rules. Assessment on a population of 47 patients from different imaging sites illustrates the potential of the proposed method in segmenting both hyperintense lesions and necrotic infarcts.",
keywords = "brain tissue segmentation, fuzzy clustering, infarcts, lesions, MRI, outlier detection",
author = "Zacharaki, {Evangelia I.} and Guray Erus and Anastasios Bezerianos and Christos Davatzikos",
year = "2012",
doi = "10.1007/978-3-642-33412-2_8",
language = "English (US)",
isbn = "9783642334115",
volume = "382 AICT",
series = "IFIP Advances in Information and Communication Technology",
number = "PART 2",
pages = "76--85",
booktitle = "IFIP Advances in Information and Communication Technology",
edition = "PART 2",

}

TY - GEN

T1 - Fuzzy multi-channel clustering with individualized spatial priors for segmenting brain lesions and infarcts

AU - Zacharaki, Evangelia I.

AU - Erus, Guray

AU - Bezerianos, Anastasios

AU - Davatzikos, Christos

PY - 2012

Y1 - 2012

N2 - Quantitative analysis of brain lesions and ischemic infarcts is becoming very important due to their association with cardiovascular disease and normal aging. In this paper, we present a semi-supervised segmentation methodology that detects and classifies cerebrovascular disease in multi-channel magnetic resonance (MR) images. The method combines intensity based fuzzy c-means (FCM) segmentation with spatial probability maps calculated from a normative set of images from healthy individuals. Unlike common FCM-based methods which segment only healthy tissue, we have extended the fuzzy segmentation to include patient-specific spatial priors for both pathological conditions (lesions and infarcts). These priors are calculated by estimating the statistical voxel-wise variation of the healthy anatomy, and identifying abnormalities as deviations from normality. False detection is reduced by knowledge-based rules. Assessment on a population of 47 patients from different imaging sites illustrates the potential of the proposed method in segmenting both hyperintense lesions and necrotic infarcts.

AB - Quantitative analysis of brain lesions and ischemic infarcts is becoming very important due to their association with cardiovascular disease and normal aging. In this paper, we present a semi-supervised segmentation methodology that detects and classifies cerebrovascular disease in multi-channel magnetic resonance (MR) images. The method combines intensity based fuzzy c-means (FCM) segmentation with spatial probability maps calculated from a normative set of images from healthy individuals. Unlike common FCM-based methods which segment only healthy tissue, we have extended the fuzzy segmentation to include patient-specific spatial priors for both pathological conditions (lesions and infarcts). These priors are calculated by estimating the statistical voxel-wise variation of the healthy anatomy, and identifying abnormalities as deviations from normality. False detection is reduced by knowledge-based rules. Assessment on a population of 47 patients from different imaging sites illustrates the potential of the proposed method in segmenting both hyperintense lesions and necrotic infarcts.

KW - brain tissue segmentation

KW - fuzzy clustering

KW - infarcts

KW - lesions

KW - MRI

KW - outlier detection

UR - http://www.scopus.com/inward/record.url?scp=84870868779&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870868779&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-33412-2_8

DO - 10.1007/978-3-642-33412-2_8

M3 - Conference contribution

SN - 9783642334115

VL - 382 AICT

T3 - IFIP Advances in Information and Communication Technology

SP - 76

EP - 85

BT - IFIP Advances in Information and Communication Technology

ER -