Presentation 2001/9/7
Development of classification method of mammographic microcalcifications
Takeshi Hara, Norimitsu Shinohara, Yoshitake Ooe, Hiroshi Fujita, Tokiko Endo, Takuji Iwase,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is very important to classify microcalcification on mammograms whether the lesions are benign or malignant and it will be very tough works for radiologist. We have been developing the automated classification scheme for mammographic microcalcifications.The purpose of this works is to apply new feature values of shape-of-microcalcifications based on BI-RADS. criteria derived from a radiologist, and to confirm the usefulriess of the combined input value for artificial neural networks to classify the lesions. By using ROC analysis to compare our previous methods and new one, the classification performance indicated by Az value was improved from 0.98 to 1.00. This result implies that the shape-of-microcalcifications indicated on BI-RADS are very useful to classification of microealcifications.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) mammograms / microcalcifications / classification / computer-aided diagnosis
Paper # MI2001-35
Date of Issue

Conference Information
Committee MI
Conference Date 2001/9/7(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) Development of classification method of mammographic microcalcifications
Sub Title (in English)
Keyword(1) mammograms
Keyword(2) microcalcifications
Keyword(3) classification
Keyword(4) computer-aided diagnosis
1st Author's Name Takeshi Hara
1st Author's Affiliation Department of information science, Gifu University()
2nd Author's Name Norimitsu Shinohara
2nd Author's Affiliation Department of information science, Gifu University
3rd Author's Name Yoshitake Ooe
3rd Author's Affiliation Department of information science, Gifu University
4th Author's Name Hiroshi Fujita
4th Author's Affiliation Department of information science, Gifu University
5th Author's Name Tokiko Endo
5th Author's Affiliation Department of radiology, National Hospital of Nagoya
6th Author's Name Takuji Iwase
6th Author's Affiliation Department of breast surgery, Aichi Cancer Center Hospital
Date 2001/9/7
Paper # MI2001-35
Volume (vol) vol.101
Number (no) 310
Page pp.pp.-
#Pages 5
Date of Issue