Presentation 2001/1/19
Detection of Clustered Microcalcifications in Masses on Mammograms by Artificial Neural Networks
Xuejun Zhang, Takeshi Hara, Hiroshi Fujita, Takuji Iwase, Tokiko Endo,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A method using neural networks for the detection of clustered microcalcifications in masses on digitized mammograms is presented. A shift-invariant artificial neural network(SIANN) and a triple-ring filter(TRF) method were applied to detect microcalcification candidates within a mass area, and then the false-positive(FP) detections were removed by a variable-ring filter. After these procedures, microcalcifications were classified into cluster or not. We were able to improve the sensitivity of detecting clusters from 90% by our previous method to 95% by using both the SIANN and the TRF with the same number of FPs.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) microcalcification / cluster / shift-invariant neural network / triple-ring filter
Paper # MI2000-81
Date of Issue

Conference Information
Committee MI
Conference Date 2001/1/19(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) Detection of Clustered Microcalcifications in Masses on Mammograms by Artificial Neural Networks
Sub Title (in English)
Keyword(1) microcalcification
Keyword(2) cluster
Keyword(3) shift-invariant neural network
Keyword(4) triple-ring filter
1st Author's Name Xuejun Zhang
1st Author's Affiliation Department of Information Science, Faculty of Engineering, Gifu University()
2nd Author's Name Takeshi Hara
2nd Author's Affiliation Department of Information Science, Faculty of Engineering, Gifu University
3rd Author's Name Hiroshi Fujita
3rd Author's Affiliation Department of Information Science, Faculty of Engineering, Gifu University
4th Author's Name Takuji Iwase
4th Author's Affiliation Department of Breast Surgery, Aichi Cancer Center Hospital
5th Author's Name Tokiko Endo
5th Author's Affiliation Department of Radiology, National Hospital of Nagoya
Date 2001/1/19
Paper # MI2000-81
Volume (vol) vol.100
Number (no) 597
Page pp.pp.-
#Pages 6
Date of Issue