Computer-aided detection (CAD) of breast masses in mammography: combined detection and ensemble classification

Cited 14 time in webofscience Cited 15 time in scopus
  • Hit : 346
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorChoi, Jae Youngko
dc.contributor.authorKim, Dae Hoeko
dc.contributor.authorPlataniotis, Konstantinos N.ko
dc.contributor.authorRo, YongManko
dc.date.accessioned2014-09-02T02:33:56Z-
dc.date.available2014-09-02T02:33:56Z-
dc.date.created2014-08-12-
dc.date.created2014-08-12-
dc.date.created2014-08-12-
dc.date.issued2014-07-
dc.identifier.citationPHYSICS IN MEDICINE AND BIOLOGY, v.59, no.14, pp.3697 - 3719-
dc.identifier.issn0031-9155-
dc.identifier.urihttp://hdl.handle.net/10203/189853-
dc.description.abstractWe propose a novel computer-aided detection (CAD) framework of breast masses in mammography. To increase detection sensitivity for various types of mammographic masses, we propose the combined use of different detection algorithms. In particular, we develop a region-of-interest combination mechanism that integrates detection information gained from unsupervised and supervised detection algorithms. Also, to significantly reduce the number of false-positive (FP) detections, the new ensemble classification algorithm is developed. Extensive experiments have been conducted on a benchmark mammogram database. Results show that our combined detection approach can considerably improve the detection sensitivity with a small loss of FP rate, compared to representative detection algorithms previously developed for mammographic CAD systems. The proposed ensemble classification solution also has a dramatic impact on the reduction of FP detections; as much as 70% (from 15 to 4.5 per image) at only cost of 4.6% sensitivity loss (from 90.0% to 85.4%). Moreover, our proposed CAD method performs as well or better (70.7% and 80.0% per 1.5 and 3.5 FPs per image respectively) than the results of mammography CAD algorithms previously reported in the literature.-
dc.languageEnglish-
dc.publisherIOP PUBLISHING LTD-
dc.titleComputer-aided detection (CAD) of breast masses in mammography: combined detection and ensemble classification-
dc.typeArticle-
dc.identifier.wosid000338771300004-
dc.identifier.scopusid2-s2.0-84903647885-
dc.type.rimsART-
dc.citation.volume59-
dc.citation.issue14-
dc.citation.beginningpage3697-
dc.citation.endingpage3719-
dc.citation.publicationnamePHYSICS IN MEDICINE AND BIOLOGY-
dc.identifier.doi10.1088/0031-9155/59/14/3697-
dc.contributor.localauthorRo, YongMan-
dc.contributor.nonIdAuthorChoi, Jae Young-
dc.contributor.nonIdAuthorPlataniotis, Konstantinos N.-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorcomputer-aided detection-
dc.subject.keywordAuthorcombined detection-
dc.subject.keywordAuthorensemble classification-
dc.subject.keywordAuthormammography-
dc.subject.keywordPlusFALSE-POSITIVE REDUCTION-
dc.subject.keywordPlusMULTIRESOLUTION TEXTURE ANALYSIS-
dc.subject.keywordPlusSUPPORT VECTOR MACHINES-
dc.subject.keywordPlusDIGITAL MAMMOGRAMS-
dc.subject.keywordPlusSCREENING MAMMOGRAPHY-
dc.subject.keywordPlusCIRCUMSCRIBED MASSES-
dc.subject.keywordPlusCANCER DIAGNOSIS-
dc.subject.keywordPlusSAMPLE-SIZE-
dc.subject.keywordPlusSEGMENTATION-
dc.subject.keywordPlusSELECTION-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 14 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0