A novel feature reduction framework for digital mammogram image classification

Hajar Alharbi, Gregory Falzon, Paul Kwan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

The visual similarity between normal breast tissues and abnormal lesions in digital mammogram images makes computer-aided diagnosis of breast cancer using automatically detected features a highly error-prone task. Our contribution in this paper is a novel feature reduction framework for selecting the most discriminative features that achieves both efficiency and classification accuracy. Our approach applies five individual feature-ranking methods including Fisher score, minimum redundancy-maximum relevance, relief-f, sequential forward feature selection, and genetic algorithm for sorting the extracted features and selecting the features with highest ranking to setup a classifier. Our method achieves an accuracy of 94.27% and a sensitivity of 98.36% with a specificity of 99.27% on a set of 1,100 mammogram patches taken from image retrieval in medical applications database using a neural network classifier, which competes with state-of-the-art classification accuracy 93.11%. Furthermore, we demonstrate that only 49 out of the 119 extracted features are sufficient to achieve the reported accuracy of normal vs. abnormal classification.

Original languageEnglish
Title of host publicationProceedings - 3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages221-225
Number of pages5
ISBN (Electronic)9781479961009
DOIs
Publication statusPublished - 9 Jun 2016
Externally publishedYes
Event3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015 - Kuala Lumpur, Malaysia
Duration: 3 Nov 20156 Nov 2015

Publication series

NameProceedings - 3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015

Conference

Conference3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015
CountryMalaysia
CityKuala Lumpur
Period3/11/156/11/15

Keywords

  • Digital mammography
  • Computer-aided detection/diagnosis (CAD)
  • breast cancer
  • Error rates

Fingerprint Dive into the research topics of 'A novel feature reduction framework for digital mammogram image classification'. Together they form a unique fingerprint.

Cite this