Automated segmentation method of white matter and gray matter regions with multiple sclerosis lesions in MR images

Taiki Magome, Hidetaka Arimura, Shingo Kakeda, Daisuke Yamamoto, Yasuo Kawata, Yasuo Yamashita, Yoshiharu Higashida, Fukai Toyofuku, Masafumi Ohki, Yukunori Korogi

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Our purpose in this study was to develop an automated method for segmentation of white matter (WM) and gray matter (GM) regions with multiple sclerosis (MS) lesions in magnetic resonance (MR) images. The brain parenchymal (BP) region was derived from a histogram analysis for a T1-weighted image. The WM regions were segmented by addition of MS candidate regions, which were detected by our computer-aided detection system for the MS lesions, and subtraction of a basal ganglia and thalamus template from "tentative" WM regions. The GM regions were obtained by subtraction of the WM regions from the BP region. We applied our proposed method to T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery images acquired from 7 MS patients and 7 control subjects on a 3.0 T MRI system. The average similarity indices between the specific regions obtained by our method and by neuroradiologists for the BP and WM regions were 95.5 ± 1.2 and 85.2 ± 4.3%, respectively, for MS patients. Moreover, they were 95.0 ± 2.0 and 85.9 ± 3.4%, respectively, for the control subjects. The proposed method might be feasible for segmentation of WM and GM regions in MS patients.

Original languageEnglish
Pages (from-to)61-72
Number of pages12
JournalRadiological physics and technology
Volume4
Issue number1
DOIs
Publication statusPublished - Jan 1 2011

Fingerprint

lesions
Multiple Sclerosis
magnetic resonance
Magnetic Resonance Spectroscopy
brain
Brain
subtraction
Basal Ganglia
thalamus
Thalamus
White Matter
Gray Matter
histograms
templates
recovery
inversions
fluids

All Science Journal Classification (ASJC) codes

  • Radiation
  • Physical Therapy, Sports Therapy and Rehabilitation
  • Radiology Nuclear Medicine and imaging

Cite this

Automated segmentation method of white matter and gray matter regions with multiple sclerosis lesions in MR images. / Magome, Taiki; Arimura, Hidetaka; Kakeda, Shingo; Yamamoto, Daisuke; Kawata, Yasuo; Yamashita, Yasuo; Higashida, Yoshiharu; Toyofuku, Fukai; Ohki, Masafumi; Korogi, Yukunori.

In: Radiological physics and technology, Vol. 4, No. 1, 01.01.2011, p. 61-72.

Research output: Contribution to journalArticle

Magome, T, Arimura, H, Kakeda, S, Yamamoto, D, Kawata, Y, Yamashita, Y, Higashida, Y, Toyofuku, F, Ohki, M & Korogi, Y 2011, 'Automated segmentation method of white matter and gray matter regions with multiple sclerosis lesions in MR images', Radiological physics and technology, vol. 4, no. 1, pp. 61-72. https://doi.org/10.1007/s12194-010-0106-x
Magome, Taiki ; Arimura, Hidetaka ; Kakeda, Shingo ; Yamamoto, Daisuke ; Kawata, Yasuo ; Yamashita, Yasuo ; Higashida, Yoshiharu ; Toyofuku, Fukai ; Ohki, Masafumi ; Korogi, Yukunori. / Automated segmentation method of white matter and gray matter regions with multiple sclerosis lesions in MR images. In: Radiological physics and technology. 2011 ; Vol. 4, No. 1. pp. 61-72.
@article{8ea33d293b844d9a9f8d4dc228ec09b3,
title = "Automated segmentation method of white matter and gray matter regions with multiple sclerosis lesions in MR images",
abstract = "Our purpose in this study was to develop an automated method for segmentation of white matter (WM) and gray matter (GM) regions with multiple sclerosis (MS) lesions in magnetic resonance (MR) images. The brain parenchymal (BP) region was derived from a histogram analysis for a T1-weighted image. The WM regions were segmented by addition of MS candidate regions, which were detected by our computer-aided detection system for the MS lesions, and subtraction of a basal ganglia and thalamus template from {"}tentative{"} WM regions. The GM regions were obtained by subtraction of the WM regions from the BP region. We applied our proposed method to T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery images acquired from 7 MS patients and 7 control subjects on a 3.0 T MRI system. The average similarity indices between the specific regions obtained by our method and by neuroradiologists for the BP and WM regions were 95.5 ± 1.2 and 85.2 ± 4.3{\%}, respectively, for MS patients. Moreover, they were 95.0 ± 2.0 and 85.9 ± 3.4{\%}, respectively, for the control subjects. The proposed method might be feasible for segmentation of WM and GM regions in MS patients.",
author = "Taiki Magome and Hidetaka Arimura and Shingo Kakeda and Daisuke Yamamoto and Yasuo Kawata and Yasuo Yamashita and Yoshiharu Higashida and Fukai Toyofuku and Masafumi Ohki and Yukunori Korogi",
year = "2011",
month = "1",
day = "1",
doi = "10.1007/s12194-010-0106-x",
language = "English",
volume = "4",
pages = "61--72",
journal = "Radiological Physics and Technology",
issn = "1865-0333",
publisher = "Springer Japan",
number = "1",

}

TY - JOUR

T1 - Automated segmentation method of white matter and gray matter regions with multiple sclerosis lesions in MR images

AU - Magome, Taiki

AU - Arimura, Hidetaka

AU - Kakeda, Shingo

AU - Yamamoto, Daisuke

AU - Kawata, Yasuo

AU - Yamashita, Yasuo

AU - Higashida, Yoshiharu

AU - Toyofuku, Fukai

AU - Ohki, Masafumi

AU - Korogi, Yukunori

PY - 2011/1/1

Y1 - 2011/1/1

N2 - Our purpose in this study was to develop an automated method for segmentation of white matter (WM) and gray matter (GM) regions with multiple sclerosis (MS) lesions in magnetic resonance (MR) images. The brain parenchymal (BP) region was derived from a histogram analysis for a T1-weighted image. The WM regions were segmented by addition of MS candidate regions, which were detected by our computer-aided detection system for the MS lesions, and subtraction of a basal ganglia and thalamus template from "tentative" WM regions. The GM regions were obtained by subtraction of the WM regions from the BP region. We applied our proposed method to T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery images acquired from 7 MS patients and 7 control subjects on a 3.0 T MRI system. The average similarity indices between the specific regions obtained by our method and by neuroradiologists for the BP and WM regions were 95.5 ± 1.2 and 85.2 ± 4.3%, respectively, for MS patients. Moreover, they were 95.0 ± 2.0 and 85.9 ± 3.4%, respectively, for the control subjects. The proposed method might be feasible for segmentation of WM and GM regions in MS patients.

AB - Our purpose in this study was to develop an automated method for segmentation of white matter (WM) and gray matter (GM) regions with multiple sclerosis (MS) lesions in magnetic resonance (MR) images. The brain parenchymal (BP) region was derived from a histogram analysis for a T1-weighted image. The WM regions were segmented by addition of MS candidate regions, which were detected by our computer-aided detection system for the MS lesions, and subtraction of a basal ganglia and thalamus template from "tentative" WM regions. The GM regions were obtained by subtraction of the WM regions from the BP region. We applied our proposed method to T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery images acquired from 7 MS patients and 7 control subjects on a 3.0 T MRI system. The average similarity indices between the specific regions obtained by our method and by neuroradiologists for the BP and WM regions were 95.5 ± 1.2 and 85.2 ± 4.3%, respectively, for MS patients. Moreover, they were 95.0 ± 2.0 and 85.9 ± 3.4%, respectively, for the control subjects. The proposed method might be feasible for segmentation of WM and GM regions in MS patients.

UR - http://www.scopus.com/inward/record.url?scp=79251603118&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79251603118&partnerID=8YFLogxK

U2 - 10.1007/s12194-010-0106-x

DO - 10.1007/s12194-010-0106-x

M3 - Article

C2 - 20882375

AN - SCOPUS:79251603118

VL - 4

SP - 61

EP - 72

JO - Radiological Physics and Technology

JF - Radiological Physics and Technology

SN - 1865-0333

IS - 1

ER -