Presentation 2002/4/11
Improvement of detection performance of tumors on mammogramsby sub-optimal feature set
Mitsutaka NEMOTO, Sachiko FURUYA, Akinobu SHIMIZU, Yoshihiro HAGIHARA, Hidefumi KOBATAKE, Shigeru NAWANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When detecting breast tumors on mammograms, features used for discrimination of the extracted candidates play important roles. We have improved the performance of the previously proposed computer-aided diagnosis (CAD) system for detecting malignant tumors on mammograms by using a sub-optimal feature set derived from 39 features. In this paper, we study three different evaluation methods for selecting a sub-optimal feature set by the comparative method. Then a sub-optimal feature set is selected from 208 features to improve the performance of the CAD system furthermore and the effectiveness is demonstrated on 231 mammograms by comparison with our previous works.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Computer-aided diagnosis / feature selection / mammogram / breast tumor
Paper # MI2002-6
Date of Issue

Conference Information
Committee MI
Conference Date 2002/4/11(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 detection performance of tumors on mammogramsby sub-optimal feature set
Sub Title (in English)
Keyword(1) Computer-aided diagnosis
Keyword(2) feature selection
Keyword(3) mammogram
Keyword(4) breast tumor
1st Author's Name Mitsutaka NEMOTO
1st Author's Affiliation Graduate School of Bio-Applications and Systems Engineering, Tokyo University of Agriculture & Technology()
2nd Author's Name Sachiko FURUYA
2nd Author's Affiliation Graduate School of Bio-Applications and Systems Engineering, Tokyo University of Agriculture & Technology
3rd Author's Name Akinobu SHIMIZU
3rd Author's Affiliation Graduate School of Bio-Applications and Systems Engineering, Tokyo University of Agriculture & Technology
4th Author's Name Yoshihiro HAGIHARA
4th Author's Affiliation Graduate School of Bio-Applications and Systems Engineering, Tokyo University of Agriculture & Technology
5th Author's Name Hidefumi KOBATAKE
5th Author's Affiliation Graduate School of Bio-Applications and Systems Engineering, Tokyo University of Agriculture & Technology
6th Author's Name Shigeru NAWANO
6th Author's Affiliation National Cancer Center Hospital East
Date 2002/4/11
Paper # MI2002-6
Volume (vol) vol.102
Number (no) 17
Page pp.pp.-
#Pages 6
Date of Issue