AdaBoost-Based Multiple SVM-RFE for Classification of Mammograms in DDSM

被引:12
|
作者
Yoon, Sejong [1 ]
Kim, Saejoon [1 ]
机构
[1] Sogang Univ, Dept Comp Sci & Engn, Seoul, South Korea
关键词
D O I
10.1109/BIBMW.2008.4686212
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Digital mammography is one of the most promising options to diagnose breast cancer which is the most common cancer in women. However, it has weaknesses in excessive unnecessary biopsy referrals that enfeeble its effectiveness due to difficulty in distinguishing actual cancer lesions from benign abnormalities. To overcome this issue, computer aided diagnosis (CADx) using machine learning techniques have been studied worldwide. Since this is a classification problem and the number of features obtainable from a mammogram image is theoretically infinite, CADx can be improved by introducing feature selection techniques that is suitable for mammograms. In this paper, we propose a new ensemble feature selection method based on a recently developed multiple support vector machine recursive feature elimination (MSVM-RFE). We also conduct experiments on actual digital mammograms publicly available and find that our proposed method performs competitively with other leading feature selection schemes.
引用
收藏
页码:75 / 82
页数:8
相关论文
共 50 条
  • [1] AdaBoost-based multiple SVM-RFE for classification of mammograms in DDSM
    Sejong Yoon
    Saejoon Kim
    [J]. BMC Medical Informatics and Decision Making, 9
  • [2] AdaBoost-based multiple SVM-RFE for classification of mammograms in DDSM
    Yoon, Sejong
    Kim, Saejoon
    [J]. BMC MEDICAL INFORMATICS AND DECISION MAKING, 2009, 9
  • [3] Classification of lip color based on multiple SVM-RFE
    Wang, Jingjing
    Li, Xiaoqiang
    Fan, Huafu
    Li, Fufeng
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE WORKSHOPS, 2011, : 769 - 772
  • [4] Mutual information-based SVM-RFE for diagnostic classification of digitized mammograms
    Yoon, Sejong
    Kim, Saejoon
    [J]. PATTERN RECOGNITION LETTERS, 2009, 30 (16) : 1489 - 1495
  • [5] Multiple SVM-RFE using Boosting for Mammogram Classification
    Yoon, Sejong
    Kim, Saejoon
    [J]. INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL SCIENCES AND OPTIMIZATION, VOL 1, PROCEEDINGS, 2009, : 740 - 742
  • [6] Margin-Maximized Redundancy-Minimized SVM-RFE for Diagnostic Classification of Mammograms
    Kim, Saejoon
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE WORKSHOPS, 2011, : 562 - 569
  • [7] Margin-maximised redundancy-minimised SVM-RFE for diagnostic classification of mammograms
    Kim, Saejoon
    [J]. INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS, 2014, 10 (04) : 374 - 390
  • [8] Multiple SVM-RFE for gene selection in cancer classification with expression data
    Duan, KB
    Rajapakse, JC
    Wang, HY
    Azuaje, F
    [J]. IEEE TRANSACTIONS ON NANOBIOSCIENCE, 2005, 4 (03) : 228 - 234
  • [9] Feature selection for tumor classification based on improved SVM-RFE
    Li, Hangeng
    Duan, Yanhua
    Li, Qingshou
    Ruan, Xiaogang
    [J]. PROGRESS IN INTELLIGENCE COMPUTATION AND APPLICATIONS, PROCEEDINGS, 2007, : 422 - 424
  • [10] ECoG classification based on band power normalization and SVM-RFE
    Liu, Chong
    Zhao, Haibin
    Li, Chunsheng
    Wang, Hong
    [J]. Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 2011, 32 (03): : 534 - 539