Presentation 2001/5/11
Automated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images
Masahito Aoyama, Qiang Li, Shigehiko Katsuragawa, Heber MacMahon, Naoki Asada, Kunio Doi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A novel automated computerized scheme has been developed to assist radiologists for their distinction between benign and malignant solitary pulmonary nodules on chest images. Our database consisted of fifty-five chest radiographs (33 primary lung cancers and 22 benign nodules). The nodule was segmented automatically by analysis of contour lines of the gray-level distribution based on the polar-coordinate representation. Two clinical parameters (age and sex) and seventy-nine image features were determined from the outline or texture analysis for inside and outside regions of the segmented nodule. The performance of artificial neural network (ANN) and linear discriminant analysis (LDA) showed Az=0.872 and Az=0.886, respectively.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) automated computerized scheme / difference image / polar-coordinate representation / image features / linear discriminant analysis / artificial neural network
Paper # PRMU2001-11,MI2001-23
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/5/11(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images
Sub Title (in English)
Keyword(1) automated computerized scheme
Keyword(2) difference image
Keyword(3) polar-coordinate representation
Keyword(4) image features
Keyword(5) linear discriminant analysis
Keyword(6) artificial neural network
1st Author's Name Masahito Aoyama
1st Author's Affiliation Department of Radiology, The University of Chicago:Department of Intelligent Systems, Hiroshima City University()
2nd Author's Name Qiang Li
2nd Author's Affiliation Department of Radiology, The University of Chicago
3rd Author's Name Shigehiko Katsuragawa
3rd Author's Affiliation Department of Radiology, The University of Chicago
4th Author's Name Heber MacMahon
4th Author's Affiliation Department of Radiology, The University of Chicago
5th Author's Name Naoki Asada
5th Author's Affiliation Department of Intelligent Systems, Hiroshima City University
6th Author's Name Kunio Doi
6th Author's Affiliation Department of Radiology, The University of Chicago
Date 2001/5/11
Paper # PRMU2001-11,MI2001-23
Volume (vol) vol.101
Number (no) 58
Page pp.pp.-
#Pages 8
Date of Issue