Computer-aided evaluation method of white matter hyperintensities related to subcortical vascular dementia based on magnetic resonance imaging

Yasuo Kawata, Hidetaka Arimura, Yasuo Yamashita, Taiki Magome, Masafumi Ohki, Fukai Toyofuku, Yoshiharu Higashida, Kazuhiro Tsuchiya

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

It has been reported that the severity of subcortical vascular dementia (VaD) correlated with an area ratio of white matter hyperintensity (WMH) regions to the brain parenchyma (WMH area ratio). The purpose of this study was to develop a computer-aided evaluation method of WMH regions for diagnosis of subcortical VaD based on magnetic resonance (MR) images. A brain parenchymal region was segmented based on the histogram analysis of a T1-weigthed image. The WMH regions were segmented on the subtraction image between a T1-weighted and fluid-attenuated inversion-recovery (FLAIR) images using two segmentation methods, i.e., a region-growing technique and a level-set method, which were automatically and adaptively selected on each WMH region based on its image features by using a support vector machine. We applied the proposed method to 33 slices of the three types of MR images with 245 lesions, which were acquired from 10 patients (age range: 64-90 years, mean: 78) with a diagnosis of VaD on a 1.5-T MR imaging scanner. The average similarity index between regions determined by a manual method and the proposed method was 93.5 ± 2.0% for brain parenchymal regions and 78.2 ± 11.0% for WMH regions. The WMH area ratio obtained by the proposed method correlated with that determined by two neuroradiologists with a correlation coefficient of 0.992. The results presented in this study suggest that the proposed method could assist neuroradiologists in the evaluation of WMH regions related to the subcortical VaD.

Original languageEnglish
Pages (from-to)370-376
Number of pages7
JournalComputerized Medical Imaging and Graphics
Volume34
Issue number5
DOIs
Publication statusPublished - Jul 1 2010

Fingerprint

Vascular Dementia
Magnetic resonance
Brain
Magnetic Resonance Imaging
Imaging techniques
Support vector machines
Recovery
Magnetic Resonance Spectroscopy
Fluids
White Matter

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Computer-aided evaluation method of white matter hyperintensities related to subcortical vascular dementia based on magnetic resonance imaging. / Kawata, Yasuo; Arimura, Hidetaka; Yamashita, Yasuo; Magome, Taiki; Ohki, Masafumi; Toyofuku, Fukai; Higashida, Yoshiharu; Tsuchiya, Kazuhiro.

In: Computerized Medical Imaging and Graphics, Vol. 34, No. 5, 01.07.2010, p. 370-376.

Research output: Contribution to journalArticle

Kawata, Yasuo ; Arimura, Hidetaka ; Yamashita, Yasuo ; Magome, Taiki ; Ohki, Masafumi ; Toyofuku, Fukai ; Higashida, Yoshiharu ; Tsuchiya, Kazuhiro. / Computer-aided evaluation method of white matter hyperintensities related to subcortical vascular dementia based on magnetic resonance imaging. In: Computerized Medical Imaging and Graphics. 2010 ; Vol. 34, No. 5. pp. 370-376.
@article{f65b6feceed04f86bec25d8d3c7da644,
title = "Computer-aided evaluation method of white matter hyperintensities related to subcortical vascular dementia based on magnetic resonance imaging",
abstract = "It has been reported that the severity of subcortical vascular dementia (VaD) correlated with an area ratio of white matter hyperintensity (WMH) regions to the brain parenchyma (WMH area ratio). The purpose of this study was to develop a computer-aided evaluation method of WMH regions for diagnosis of subcortical VaD based on magnetic resonance (MR) images. A brain parenchymal region was segmented based on the histogram analysis of a T1-weigthed image. The WMH regions were segmented on the subtraction image between a T1-weighted and fluid-attenuated inversion-recovery (FLAIR) images using two segmentation methods, i.e., a region-growing technique and a level-set method, which were automatically and adaptively selected on each WMH region based on its image features by using a support vector machine. We applied the proposed method to 33 slices of the three types of MR images with 245 lesions, which were acquired from 10 patients (age range: 64-90 years, mean: 78) with a diagnosis of VaD on a 1.5-T MR imaging scanner. The average similarity index between regions determined by a manual method and the proposed method was 93.5 ± 2.0{\%} for brain parenchymal regions and 78.2 ± 11.0{\%} for WMH regions. The WMH area ratio obtained by the proposed method correlated with that determined by two neuroradiologists with a correlation coefficient of 0.992. The results presented in this study suggest that the proposed method could assist neuroradiologists in the evaluation of WMH regions related to the subcortical VaD.",
author = "Yasuo Kawata and Hidetaka Arimura and Yasuo Yamashita and Taiki Magome and Masafumi Ohki and Fukai Toyofuku and Yoshiharu Higashida and Kazuhiro Tsuchiya",
year = "2010",
month = "7",
day = "1",
doi = "10.1016/j.compmedimag.2009.12.014",
language = "English",
volume = "34",
pages = "370--376",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Computer-aided evaluation method of white matter hyperintensities related to subcortical vascular dementia based on magnetic resonance imaging

AU - Kawata, Yasuo

AU - Arimura, Hidetaka

AU - Yamashita, Yasuo

AU - Magome, Taiki

AU - Ohki, Masafumi

AU - Toyofuku, Fukai

AU - Higashida, Yoshiharu

AU - Tsuchiya, Kazuhiro

PY - 2010/7/1

Y1 - 2010/7/1

N2 - It has been reported that the severity of subcortical vascular dementia (VaD) correlated with an area ratio of white matter hyperintensity (WMH) regions to the brain parenchyma (WMH area ratio). The purpose of this study was to develop a computer-aided evaluation method of WMH regions for diagnosis of subcortical VaD based on magnetic resonance (MR) images. A brain parenchymal region was segmented based on the histogram analysis of a T1-weigthed image. The WMH regions were segmented on the subtraction image between a T1-weighted and fluid-attenuated inversion-recovery (FLAIR) images using two segmentation methods, i.e., a region-growing technique and a level-set method, which were automatically and adaptively selected on each WMH region based on its image features by using a support vector machine. We applied the proposed method to 33 slices of the three types of MR images with 245 lesions, which were acquired from 10 patients (age range: 64-90 years, mean: 78) with a diagnosis of VaD on a 1.5-T MR imaging scanner. The average similarity index between regions determined by a manual method and the proposed method was 93.5 ± 2.0% for brain parenchymal regions and 78.2 ± 11.0% for WMH regions. The WMH area ratio obtained by the proposed method correlated with that determined by two neuroradiologists with a correlation coefficient of 0.992. The results presented in this study suggest that the proposed method could assist neuroradiologists in the evaluation of WMH regions related to the subcortical VaD.

AB - It has been reported that the severity of subcortical vascular dementia (VaD) correlated with an area ratio of white matter hyperintensity (WMH) regions to the brain parenchyma (WMH area ratio). The purpose of this study was to develop a computer-aided evaluation method of WMH regions for diagnosis of subcortical VaD based on magnetic resonance (MR) images. A brain parenchymal region was segmented based on the histogram analysis of a T1-weigthed image. The WMH regions were segmented on the subtraction image between a T1-weighted and fluid-attenuated inversion-recovery (FLAIR) images using two segmentation methods, i.e., a region-growing technique and a level-set method, which were automatically and adaptively selected on each WMH region based on its image features by using a support vector machine. We applied the proposed method to 33 slices of the three types of MR images with 245 lesions, which were acquired from 10 patients (age range: 64-90 years, mean: 78) with a diagnosis of VaD on a 1.5-T MR imaging scanner. The average similarity index between regions determined by a manual method and the proposed method was 93.5 ± 2.0% for brain parenchymal regions and 78.2 ± 11.0% for WMH regions. The WMH area ratio obtained by the proposed method correlated with that determined by two neuroradiologists with a correlation coefficient of 0.992. The results presented in this study suggest that the proposed method could assist neuroradiologists in the evaluation of WMH regions related to the subcortical VaD.

UR - http://www.scopus.com/inward/record.url?scp=77953021989&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953021989&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2009.12.014

DO - 10.1016/j.compmedimag.2009.12.014

M3 - Article

C2 - 20116974

AN - SCOPUS:77953021989

VL - 34

SP - 370

EP - 376

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

IS - 5

ER -