Computer-Assisted Segmentation of White Matter Lesions in 3D MR Images Using Support Vector Machine

Zhiqiang Lao; Dinggang Shen; Dengfeng Liu; Abbas F. Jawad; Elias R. Melhem; Lenore J. Launer; R. Nick Bryan; Christos Davatzikos

doi:10.1016/j.acra.2007.10.012

Computer-Assisted Segmentation of White Matter Lesions in 3D MR Images Using Support Vector Machine

Zhiqiang Lao, Dinggang Shen, Dengfeng Liu, Abbas F. Jawad, Elias R. Melhem, Lenore J. Launer, R. Nick Bryan, Christos Davatzikos

Research output: Contribution to journal › Article › peer-review

209 Citations (Scopus)

Abstract

Rationale and Objectives: Brain lesions, especially white matter lesions (WMLs), are associated with cardiac and vascular disease, but also with normal aging. Quantitative analysis of WML in large clinical trials is becoming more and more important. Materials and Methods: In this article, we present a computer-assisted WML segmentation method, based on local features extracted from multiparametric magnetic resonance imaging (MRI) sequences (ie, T1-weighted, T2-weighted, proton density-weighted, and fluid attenuation inversion recovery MRI scans). A support vector machine classifier is first trained on expert-defined WMLs, and is then used to classify new scans. Results: Postprocessing analysis further reduces false positives by using anatomic knowledge and measures of distance from the training set. Conclusions: Cross-validation on a population of 35 patients from three different imaging sites with WMLs of varying sizes, shapes, and locations tests the robustness and accuracy of the proposed segmentation method, compared with the manual segmentation results from two experienced neuroradiologists.

Original language	English
Pages (from-to)	300-313
Number of pages	14
Journal	Academic Radiology
Volume	15
Issue number	3
DOIs	https://doi.org/10.1016/j.acra.2007.10.012
Publication status	Published - 2008 Mar
Externally published	Yes

Bibliographical note

Funding Information:
Supported (in part) by the Intramural Research Program of the NIH, National Institute of Aging contract N01-HC-95178. Image analysis was supported in part by R01-AG-1497.

Funding Information:
We would like to thank the committee of ACCORD-MIND project, which is funded by the NIA through an intra-agency agreement with NIHLBI (Y3-HC-3065), for providing the datasets, valuable comments and giving us permissions to publish this paper. We also like to thank Ms. Lisa Desiderio for assistance in coordinating this study. Finally, we would like to thank patients recruited by ACCORD-MIND project.

Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.

Keywords

White matter lesion segmentation
machine learning
support vector machine

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging

Access to Document

10.1016/j.acra.2007.10.012

Cite this

@article{1258c2cd94794e708c2ee984126d57e4,

title = "Computer-Assisted Segmentation of White Matter Lesions in 3D MR Images Using Support Vector Machine",

abstract = "Rationale and Objectives: Brain lesions, especially white matter lesions (WMLs), are associated with cardiac and vascular disease, but also with normal aging. Quantitative analysis of WML in large clinical trials is becoming more and more important. Materials and Methods: In this article, we present a computer-assisted WML segmentation method, based on local features extracted from multiparametric magnetic resonance imaging (MRI) sequences (ie, T1-weighted, T2-weighted, proton density-weighted, and fluid attenuation inversion recovery MRI scans). A support vector machine classifier is first trained on expert-defined WMLs, and is then used to classify new scans. Results: Postprocessing analysis further reduces false positives by using anatomic knowledge and measures of distance from the training set. Conclusions: Cross-validation on a population of 35 patients from three different imaging sites with WMLs of varying sizes, shapes, and locations tests the robustness and accuracy of the proposed segmentation method, compared with the manual segmentation results from two experienced neuroradiologists.",

keywords = "White matter lesion segmentation, machine learning, support vector machine",

author = "Zhiqiang Lao and Dinggang Shen and Dengfeng Liu and Jawad, {Abbas F.} and Melhem, {Elias R.} and Launer, {Lenore J.} and Bryan, {R. Nick} and Christos Davatzikos",

note = "Funding Information: Supported (in part) by the Intramural Research Program of the NIH, National Institute of Aging contract N01-HC-95178. Image analysis was supported in part by R01-AG-1497. Funding Information: We would like to thank the committee of ACCORD-MIND project, which is funded by the NIA through an intra-agency agreement with NIHLBI (Y3-HC-3065), for providing the datasets, valuable comments and giving us permissions to publish this paper. We also like to thank Ms. Lisa Desiderio for assistance in coordinating this study. Finally, we would like to thank patients recruited by ACCORD-MIND project. Copyright: Copyright 2008 Elsevier B.V., All rights reserved.",

year = "2008",

month = mar,

doi = "10.1016/j.acra.2007.10.012",

language = "English",

volume = "15",

pages = "300--313",

journal = "Academic Radiology",

issn = "1076-6332",

publisher = "Elsevier USA",

number = "3",

}

TY - JOUR

T1 - Computer-Assisted Segmentation of White Matter Lesions in 3D MR Images Using Support Vector Machine

AU - Lao, Zhiqiang

AU - Shen, Dinggang

AU - Liu, Dengfeng

AU - Jawad, Abbas F.

AU - Melhem, Elias R.

AU - Launer, Lenore J.

AU - Bryan, R. Nick

AU - Davatzikos, Christos

N1 - Funding Information: Supported (in part) by the Intramural Research Program of the NIH, National Institute of Aging contract N01-HC-95178. Image analysis was supported in part by R01-AG-1497. Funding Information: We would like to thank the committee of ACCORD-MIND project, which is funded by the NIA through an intra-agency agreement with NIHLBI (Y3-HC-3065), for providing the datasets, valuable comments and giving us permissions to publish this paper. We also like to thank Ms. Lisa Desiderio for assistance in coordinating this study. Finally, we would like to thank patients recruited by ACCORD-MIND project. Copyright: Copyright 2008 Elsevier B.V., All rights reserved.

PY - 2008/3

Y1 - 2008/3

N2 - Rationale and Objectives: Brain lesions, especially white matter lesions (WMLs), are associated with cardiac and vascular disease, but also with normal aging. Quantitative analysis of WML in large clinical trials is becoming more and more important. Materials and Methods: In this article, we present a computer-assisted WML segmentation method, based on local features extracted from multiparametric magnetic resonance imaging (MRI) sequences (ie, T1-weighted, T2-weighted, proton density-weighted, and fluid attenuation inversion recovery MRI scans). A support vector machine classifier is first trained on expert-defined WMLs, and is then used to classify new scans. Results: Postprocessing analysis further reduces false positives by using anatomic knowledge and measures of distance from the training set. Conclusions: Cross-validation on a population of 35 patients from three different imaging sites with WMLs of varying sizes, shapes, and locations tests the robustness and accuracy of the proposed segmentation method, compared with the manual segmentation results from two experienced neuroradiologists.

AB - Rationale and Objectives: Brain lesions, especially white matter lesions (WMLs), are associated with cardiac and vascular disease, but also with normal aging. Quantitative analysis of WML in large clinical trials is becoming more and more important. Materials and Methods: In this article, we present a computer-assisted WML segmentation method, based on local features extracted from multiparametric magnetic resonance imaging (MRI) sequences (ie, T1-weighted, T2-weighted, proton density-weighted, and fluid attenuation inversion recovery MRI scans). A support vector machine classifier is first trained on expert-defined WMLs, and is then used to classify new scans. Results: Postprocessing analysis further reduces false positives by using anatomic knowledge and measures of distance from the training set. Conclusions: Cross-validation on a population of 35 patients from three different imaging sites with WMLs of varying sizes, shapes, and locations tests the robustness and accuracy of the proposed segmentation method, compared with the manual segmentation results from two experienced neuroradiologists.

KW - White matter lesion segmentation

KW - machine learning

KW - support vector machine

UR - http://www.scopus.com/inward/record.url?scp=39049098162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=39049098162&partnerID=8YFLogxK

U2 - 10.1016/j.acra.2007.10.012

DO - 10.1016/j.acra.2007.10.012

M3 - Article

C2 - 18280928

AN - SCOPUS:39049098162

SN - 1076-6332

VL - 15

SP - 300

EP - 313

JO - Academic Radiology

JF - Academic Radiology

IS - 3

ER -

Computer-Assisted Segmentation of White Matter Lesions in 3D MR Images Using Support Vector Machine

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this