Automated segmentation and quantification of white matter hyperintensities in acute ischemic stroke patients with cerebral infarction

Jang Zern Tsai, Syu Jyun Peng, Yu Wei Chen, Kuo Wei Wang, Chen Hua Li, Jing Yi Wang, Chi Jen Chen, Huey Juan Lin, Eric Edward Smith, Hsiao Kuang Wu, Sheng Feng Sung, Poh Shiow Yeh, Yue Loong Hsin

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

White matter hyperintensities (WMHs) of presumed vascular origin are common in ageing population, especially in patients with acute cerebral infarction and the volume has been reported to be associated with mental impairment and the risk of hemorrhage from antithrombotic agents. WMHs delineation can be computerized to minimize human bias. However, the presence of cerebral infarcts greatly degrades the accuracy of WMHs detection and thus limits the application of computerized delineation to patients with acute cerebral infarction. We propose a computer-assisted segmentation method to depict WMHs in the presence of cerebral infarcts in combined T1-weighted, fluid attenuation inversion recovery, and diffusion-weighted magnetic resonance imaging (MRI). The proposed method detects WMHs by empirical threshold and atlas information, with subtraction of white matter voxels affected by acute infarction. The method was derived using MRI from 25 hemispheres with WMHs only and 13 hemispheres with both WMHs and cerebral infarcts. Similarity index (SI) and correlation were utilized to assess the agreement between the new automated method and a gold standard visually guided semi-automated method done by an expert rater. The proposed WMHs segmentation approach produced average SI, sensitivity and specificity of 83.1426 11.742, 84.154616.086 and 99.98860.029% with WMHs only and of 68.826±14.036, 74.381±18.473 and 99.956±0.054% with both WMHs and cerebral infarcts in the derivation cohort. The performance of the proposed method with an external validation cohort was also highly consistent with that of the experienced rater.

Original languageEnglish
Article numbere104011
JournalPLoS One
Volume9
Issue number8
DOIs
Publication statusPublished - Aug 15 2014

Fingerprint

infarction
Cerebral Infarction
Magnetic resonance
stroke
Stroke
Imaging techniques
Fibrinolytic Agents
Aging of materials
Recovery
Fluids
magnetic resonance imaging
methodology
White Matter
blood vessels
gold
hemorrhage
Diffusion Magnetic Resonance Imaging
Atlases
Infarction
Blood Vessels

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Automated segmentation and quantification of white matter hyperintensities in acute ischemic stroke patients with cerebral infarction. / Tsai, Jang Zern; Peng, Syu Jyun; Chen, Yu Wei; Wang, Kuo Wei; Li, Chen Hua; Wang, Jing Yi; Chen, Chi Jen; Lin, Huey Juan; Smith, Eric Edward; Wu, Hsiao Kuang; Sung, Sheng Feng; Yeh, Poh Shiow; Hsin, Yue Loong.

In: PLoS One, Vol. 9, No. 8, e104011, 15.08.2014.

Research output: Contribution to journalArticle

Tsai, JZ, Peng, SJ, Chen, YW, Wang, KW, Li, CH, Wang, JY, Chen, CJ, Lin, HJ, Smith, EE, Wu, HK, Sung, SF, Yeh, PS & Hsin, YL 2014, 'Automated segmentation and quantification of white matter hyperintensities in acute ischemic stroke patients with cerebral infarction', PLoS One, vol. 9, no. 8, e104011. https://doi.org/10.1371/journal.pone.0104011
Tsai, Jang Zern ; Peng, Syu Jyun ; Chen, Yu Wei ; Wang, Kuo Wei ; Li, Chen Hua ; Wang, Jing Yi ; Chen, Chi Jen ; Lin, Huey Juan ; Smith, Eric Edward ; Wu, Hsiao Kuang ; Sung, Sheng Feng ; Yeh, Poh Shiow ; Hsin, Yue Loong. / Automated segmentation and quantification of white matter hyperintensities in acute ischemic stroke patients with cerebral infarction. In: PLoS One. 2014 ; Vol. 9, No. 8.
@article{fc9c2e538e2f4ff88f294a9f5910c55b,
title = "Automated segmentation and quantification of white matter hyperintensities in acute ischemic stroke patients with cerebral infarction",
abstract = "White matter hyperintensities (WMHs) of presumed vascular origin are common in ageing population, especially in patients with acute cerebral infarction and the volume has been reported to be associated with mental impairment and the risk of hemorrhage from antithrombotic agents. WMHs delineation can be computerized to minimize human bias. However, the presence of cerebral infarcts greatly degrades the accuracy of WMHs detection and thus limits the application of computerized delineation to patients with acute cerebral infarction. We propose a computer-assisted segmentation method to depict WMHs in the presence of cerebral infarcts in combined T1-weighted, fluid attenuation inversion recovery, and diffusion-weighted magnetic resonance imaging (MRI). The proposed method detects WMHs by empirical threshold and atlas information, with subtraction of white matter voxels affected by acute infarction. The method was derived using MRI from 25 hemispheres with WMHs only and 13 hemispheres with both WMHs and cerebral infarcts. Similarity index (SI) and correlation were utilized to assess the agreement between the new automated method and a gold standard visually guided semi-automated method done by an expert rater. The proposed WMHs segmentation approach produced average SI, sensitivity and specificity of 83.1426 11.742, 84.154616.086 and 99.98860.029{\%} with WMHs only and of 68.826±14.036, 74.381±18.473 and 99.956±0.054{\%} with both WMHs and cerebral infarcts in the derivation cohort. The performance of the proposed method with an external validation cohort was also highly consistent with that of the experienced rater.",
author = "Tsai, {Jang Zern} and Peng, {Syu Jyun} and Chen, {Yu Wei} and Wang, {Kuo Wei} and Li, {Chen Hua} and Wang, {Jing Yi} and Chen, {Chi Jen} and Lin, {Huey Juan} and Smith, {Eric Edward} and Wu, {Hsiao Kuang} and Sung, {Sheng Feng} and Yeh, {Poh Shiow} and Hsin, {Yue Loong}",
year = "2014",
month = "8",
day = "15",
doi = "10.1371/journal.pone.0104011",
language = "English",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "8",

}

TY - JOUR

T1 - Automated segmentation and quantification of white matter hyperintensities in acute ischemic stroke patients with cerebral infarction

AU - Tsai, Jang Zern

AU - Peng, Syu Jyun

AU - Chen, Yu Wei

AU - Wang, Kuo Wei

AU - Li, Chen Hua

AU - Wang, Jing Yi

AU - Chen, Chi Jen

AU - Lin, Huey Juan

AU - Smith, Eric Edward

AU - Wu, Hsiao Kuang

AU - Sung, Sheng Feng

AU - Yeh, Poh Shiow

AU - Hsin, Yue Loong

PY - 2014/8/15

Y1 - 2014/8/15

N2 - White matter hyperintensities (WMHs) of presumed vascular origin are common in ageing population, especially in patients with acute cerebral infarction and the volume has been reported to be associated with mental impairment and the risk of hemorrhage from antithrombotic agents. WMHs delineation can be computerized to minimize human bias. However, the presence of cerebral infarcts greatly degrades the accuracy of WMHs detection and thus limits the application of computerized delineation to patients with acute cerebral infarction. We propose a computer-assisted segmentation method to depict WMHs in the presence of cerebral infarcts in combined T1-weighted, fluid attenuation inversion recovery, and diffusion-weighted magnetic resonance imaging (MRI). The proposed method detects WMHs by empirical threshold and atlas information, with subtraction of white matter voxels affected by acute infarction. The method was derived using MRI from 25 hemispheres with WMHs only and 13 hemispheres with both WMHs and cerebral infarcts. Similarity index (SI) and correlation were utilized to assess the agreement between the new automated method and a gold standard visually guided semi-automated method done by an expert rater. The proposed WMHs segmentation approach produced average SI, sensitivity and specificity of 83.1426 11.742, 84.154616.086 and 99.98860.029% with WMHs only and of 68.826±14.036, 74.381±18.473 and 99.956±0.054% with both WMHs and cerebral infarcts in the derivation cohort. The performance of the proposed method with an external validation cohort was also highly consistent with that of the experienced rater.

AB - White matter hyperintensities (WMHs) of presumed vascular origin are common in ageing population, especially in patients with acute cerebral infarction and the volume has been reported to be associated with mental impairment and the risk of hemorrhage from antithrombotic agents. WMHs delineation can be computerized to minimize human bias. However, the presence of cerebral infarcts greatly degrades the accuracy of WMHs detection and thus limits the application of computerized delineation to patients with acute cerebral infarction. We propose a computer-assisted segmentation method to depict WMHs in the presence of cerebral infarcts in combined T1-weighted, fluid attenuation inversion recovery, and diffusion-weighted magnetic resonance imaging (MRI). The proposed method detects WMHs by empirical threshold and atlas information, with subtraction of white matter voxels affected by acute infarction. The method was derived using MRI from 25 hemispheres with WMHs only and 13 hemispheres with both WMHs and cerebral infarcts. Similarity index (SI) and correlation were utilized to assess the agreement between the new automated method and a gold standard visually guided semi-automated method done by an expert rater. The proposed WMHs segmentation approach produced average SI, sensitivity and specificity of 83.1426 11.742, 84.154616.086 and 99.98860.029% with WMHs only and of 68.826±14.036, 74.381±18.473 and 99.956±0.054% with both WMHs and cerebral infarcts in the derivation cohort. The performance of the proposed method with an external validation cohort was also highly consistent with that of the experienced rater.

UR - http://www.scopus.com/inward/record.url?scp=84940282291&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940282291&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0104011

DO - 10.1371/journal.pone.0104011

M3 - Article

C2 - 25127120

AN - SCOPUS:84940282291

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 8

M1 - e104011

ER -