Presentation 2011-01-20
Improvement of CAD Scheme for Lacunar Infarcts in MR Images : Elimination of False Positives using Gombining Pattern Classifier
Kyouhei ITONAGA, Yoshikazu UCHIYAMA, Takeshi HARA, Toru IWAMA, Hiroaki HOSHI, Hiroshi FUJITA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The detection of asymptomatic lacunar infarcts on MR images is important because their presence indicates an increased risk of severe cerebral infarction. Therefore, we developed computerized method for the detection of lacunar infarcts. However, false positives detected by our method are classified into four types which have different distributions in the feature space. Thus, it is difficult to distinguish between these specific types of false positives and lacunar infarcts by using a single classifier. In this study, we eliminated these false positives by use of the combining pattern classifier. The result indicated that the sensitivity for the detection of lacunar infarcts was 96.8% with 0.39 false positives per slice. Our computerized method would be a useful method for eliminating specific types of false positives.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Lacunar infarct / Elimination of false positive / Combining pattern classifier / Computer-aided diagnosis
Paper # MI2010-99
Date of Issue

Conference Information
Committee MI
Conference Date 2011/1/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Medical Imaging (MI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Improvement of CAD Scheme for Lacunar Infarcts in MR Images : Elimination of False Positives using Gombining Pattern Classifier
Sub Title (in English)
Keyword(1) Lacunar infarct
Keyword(2) Elimination of false positive
Keyword(3) Combining pattern classifier
Keyword(4) Computer-aided diagnosis
1st Author's Name Kyouhei ITONAGA
1st Author's Affiliation Dept. of Electrical Electronics Information Engineering Major, Advanced Course, Oita National College of Technology()
2nd Author's Name Yoshikazu UCHIYAMA
2nd Author's Affiliation Dept. of Electrical Electronics Information Engineering Major, Advanced Course, Oita National College of Technology
3rd Author's Name Takeshi HARA
3rd Author's Affiliation Dept. of Intelligent Image Information, Graduate School of Medicine, Gifu University
4th Author's Name Toru IWAMA
4th Author's Affiliation Dept. of Neurosurgery, Graduate School of Medicine, Gifu University
5th Author's Name Hiroaki HOSHI
5th Author's Affiliation Dept. of Radiology, Graduate School of Medicine, Gifu University
6th Author's Name Hiroshi FUJITA
6th Author's Affiliation Dept. of Intelligent Image Information, Graduate School of Medicine, Gifu University
Date 2011-01-20
Paper # MI2010-99
Volume (vol) vol.110
Number (no) 364
Page pp.pp.-
#Pages 4
Date of Issue