Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination

Saejoon Kim, Sejong Yoon, Donghyuk Shin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In the analysis of digital or digitized mammographic images, a requirement is to learn to separate benign calcifications from malignant ones. Such an activity could form part of a computer-aided diagnosis (CAD) tool. We present a CAD study of calcification lesions to demonstrate that CAD of same-institutional mammograms provides significantly higher accuracy compared to that of cross-institutional mammograms. Moreover, using only a subset of the widely used six BI-RADS features together with patient age and subtlety value describing each calcification lesion is shown to increase the accuracy of CAD.

Original languageEnglish (US)
Title of host publicationProceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007
Pages396-400
Number of pages5
DOIs
StatePublished - 2007
EventFrontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007 - Jeju Island, Korea, Republic of
Duration: Oct 11 2007Oct 13 2007

Publication series

NameProceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007

Conference

ConferenceFrontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007
CountryKorea, Republic of
CityJeju Island
Period10/11/0710/13/07

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination'. Together they form a unique fingerprint.

Cite this