White matter lesion extension to automatic brain tissue segmentation on MRI

被引：251

作者：

de Boer, Renske ^{[1
,2
]}

Vrooman, Henri A. ^{[2
]}

van der Lijn, Fedde ^{[2
]}

Vernooij, Meike W. ^{[1
,3
]}

Ikram, M. Arfan ^{[1
]}

van der Lugt, Aad ^{[3
]}

Breteler, Monique M. B. ^{[1
]}

Niessen, Wiro J. ^{[2
,4
]}

机构：

[1] Erasmus MC, Dept Epidemiol, Rotterdam, Netherlands

[2] Erasmus MC, Biomed Imaging Grp Rotterdam, Dept Radiol & Med Informat, Rotterdam, Netherlands

[3] Erasmus MC, Dept Radiol, Rotterdam, Netherlands

[4] Delft Univ Technol, Fac Sci Appl, NL-2600 AA Delft, Netherlands

来源：

NEUROIMAGE | 2009年 / 45卷 / 04期

关键词：

MRI; Brain tissue segmentation; White matter lesions; White matter hyperintensities; ROTTERDAM SCAN; DISCRIMINANT-ANALYSIS; MULTIPLE-SCLEROSIS; MUTUAL-INFORMATION; IMAGES; CLASSIFICATION; VOLUME; POPULATION; MODEL; HYPERINTENSITIES;

D O I：

10.1016/j.neuroimage.2009.01.011

中图分类号：

Q189 [神经科学];

学科分类号：

071006 ;

摘要：

A fully automated brain tissue segmentation method is optimized and extended with white matter lesion segmentation. Cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM) are segmented by an atlas-based k-nearest neighbor classifier on multi-modal magnetic resonance imaging data. This classifier is trained by registering brain atlases to the subject. The resulting GM segmentation is used to automatically find a white matter lesion (WML) threshold in a fluid-attenuated inversion recovery scan. False positive lesions are removed by ensuring that the lesions are within the white matter. The method was visually validated on a set of 209 subjects. No segmentation errors were found in 98% of the brain tissue segmentations and 97% of the WML segmentations. A quantitative evaluation using manual segmentations was performed on a subset of 6 subjects for CSF, GM and WM segmentation and an additional 14 for the WML segmentations. The results indicated that the automatic segmentation accuracy is close to the interobserver variability of manual segmentations. (C) 2009 Elsevier Inc. All rights reserved.

引用

页码：1151 / 1161

页数：11

共 37 条

[31]

Song Z, 2006, LECT NOTES COMPUT SC, V4191, P831

[32] Automated model-based tissue classification of MR images of the brain [J].

Van Leemput, K ;

Maes, F ;

Vandermeulen, D ;

Suetens, P .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 1999, 18 (10) :897-908

[33] Automated segmentation of multiple sclerosis lesions by model outlier detection [J].

Van Leemput, K ;

Maes, F ;

Vandermeulen, D ;

Colchester, A ;

Suetens, P .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (08) :677-688

[34] Silent brain infarcts and white matter lesions increase stroke risk in the general population - The Rotterdam Scan Study [J].

Vermeer, SE ;

Hollander, M ;

van Dijk, EJ ;

Hofman, A ;

Koudstaal, PJ ;

Breteler, MMB .

STROKE, 2003, 34 (05) :1126-1129

[35] Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification [J].

Vrooman, Henri A. ;

Cocosco, Chris A. ;

van der Lijn, Fedde ;

Stokking, Rik ;

Ikram, M. Arfan ;

Vernooij, Meike W. ;

Breteler, Monique M. B. ;

Niessen, Wiro J. .

NEUROIMAGE, 2007, 37 (01) :71-81

[36] Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm [J].

Zhang, YY ;

Brady, M ;

Smith, S .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (01) :45-57

[37]

Zijdenbos A, 1998, LECT NOTES COMPUT SC, V1496, P439, DOI 10.1007/BFb0056229

← 1 2 3 4 →