Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine

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

doi:10.1016/j.compmedimag.2010.02.001

Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine

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

Division of medical Quantum Science

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

47 Citations (Scopus)

Abstract

The purpose of this study was to develop a computerized method for detection of multiple sclerosis (MS) lesions in brain magnetic resonance (MR) images. We have proposed a new false positive reduction scheme, which consisted of a rule-based method, a level set method, and a support vector machine. We applied the proposed method to 49 slices selected from 6 studies of three MS cases including 168 MS lesions. As a result, the sensitivity for detection of MS lesions was 81.5% with 2.9 false positives per slice based on a leave-one-candidate-out test, and the similarity index between MS regions determined by the proposed method and neuroradiologists was 0.768 on average. These results indicate the proposed method would be useful for assisting neuroradiologists in assessing the MS in clinical practice.

Original language	English
Pages (from-to)	404-413
Number of pages	10
Journal	Computerized Medical Imaging and Graphics
Volume	34
Issue number	5
DOIs	https://doi.org/10.1016/j.compmedimag.2010.02.001
Publication status	Published - Jul 2010

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

Access to Document

10.1016/j.compmedimag.2010.02.001

Cite this

Yamamoto, D., Arimura, H., Kakeda, S., Magome, T., Yamashita, Y., Toyofuku, F., Ohki, M., Higashida, Y., & Korogi, Y. (2010). Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine. Computerized Medical Imaging and Graphics, 34(5), 404-413. https://doi.org/10.1016/j.compmedimag.2010.02.001

Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine. / Yamamoto, Daisuke; Arimura, Hidetaka; Kakeda, Shingo et al.
In: Computerized Medical Imaging and Graphics, Vol. 34, No. 5, 07.2010, p. 404-413.

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

Yamamoto, D, Arimura, H, Kakeda, S, Magome, T, Yamashita, Y, Toyofuku, F, Ohki, M, Higashida, Y & Korogi, Y 2010, 'Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine', Computerized Medical Imaging and Graphics, vol. 34, no. 5, pp. 404-413. https://doi.org/10.1016/j.compmedimag.2010.02.001

Yamamoto D, Arimura H, Kakeda S, Magome T, Yamashita Y, Toyofuku F et al. Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine. Computerized Medical Imaging and Graphics. 2010 Jul;34(5):404-413. doi: 10.1016/j.compmedimag.2010.02.001

@article{a36902facf3d4b78bcf5befb619440b3,

title = "Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine",

abstract = "The purpose of this study was to develop a computerized method for detection of multiple sclerosis (MS) lesions in brain magnetic resonance (MR) images. We have proposed a new false positive reduction scheme, which consisted of a rule-based method, a level set method, and a support vector machine. We applied the proposed method to 49 slices selected from 6 studies of three MS cases including 168 MS lesions. As a result, the sensitivity for detection of MS lesions was 81.5% with 2.9 false positives per slice based on a leave-one-candidate-out test, and the similarity index between MS regions determined by the proposed method and neuroradiologists was 0.768 on average. These results indicate the proposed method would be useful for assisting neuroradiologists in assessing the MS in clinical practice.",

author = "Daisuke Yamamoto and Hidetaka Arimura and Shingo Kakeda and Taiki Magome and Yasuo Yamashita and Fukai Toyofuku and Masafumi Ohki and Yoshiharu Higashida and Yukunori Korogi",

year = "2010",

month = jul,

doi = "10.1016/j.compmedimag.2010.02.001",

language = "English",

volume = "34",

pages = "404--413",

journal = "Computerized Medical Imaging and Graphics",

issn = "0895-6111",

publisher = "Elsevier Limited",

number = "5",

}

TY - JOUR

T1 - Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images

T2 - False positive reduction scheme consisted of rule-based, level set method, and support vector machine

AU - Yamamoto, Daisuke

AU - Arimura, Hidetaka

AU - Kakeda, Shingo

AU - Magome, Taiki

AU - Yamashita, Yasuo

AU - Toyofuku, Fukai

AU - Ohki, Masafumi

AU - Higashida, Yoshiharu

AU - Korogi, Yukunori

PY - 2010/7

Y1 - 2010/7

N2 - The purpose of this study was to develop a computerized method for detection of multiple sclerosis (MS) lesions in brain magnetic resonance (MR) images. We have proposed a new false positive reduction scheme, which consisted of a rule-based method, a level set method, and a support vector machine. We applied the proposed method to 49 slices selected from 6 studies of three MS cases including 168 MS lesions. As a result, the sensitivity for detection of MS lesions was 81.5% with 2.9 false positives per slice based on a leave-one-candidate-out test, and the similarity index between MS regions determined by the proposed method and neuroradiologists was 0.768 on average. These results indicate the proposed method would be useful for assisting neuroradiologists in assessing the MS in clinical practice.

AB - The purpose of this study was to develop a computerized method for detection of multiple sclerosis (MS) lesions in brain magnetic resonance (MR) images. We have proposed a new false positive reduction scheme, which consisted of a rule-based method, a level set method, and a support vector machine. We applied the proposed method to 49 slices selected from 6 studies of three MS cases including 168 MS lesions. As a result, the sensitivity for detection of MS lesions was 81.5% with 2.9 false positives per slice based on a leave-one-candidate-out test, and the similarity index between MS regions determined by the proposed method and neuroradiologists was 0.768 on average. These results indicate the proposed method would be useful for assisting neuroradiologists in assessing the MS in clinical practice.

UR - http://www.scopus.com/inward/record.url?scp=77953023533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953023533&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2010.02.001

DO - 10.1016/j.compmedimag.2010.02.001

M3 - Article

C2 - 20189353

AN - SCOPUS:77953023533

SN - 0895-6111

VL - 34

SP - 404

EP - 413

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

IS - 5

ER -

Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this