Fourier irregularity index: A new approach to measure tumor mass irregularity in breast mammogram images

Gensheng Zhang, Wei Wang, Sung Shin, Carrie B. Hruska, Seong Ho Son

Research output: Contribution to journalArticle

7 Scopus citations

Abstract

Shape descriptors have been identified as important features in distinguishing malignant masses from benign masses. Thus, an effective morphological irregularity measure could provide a helpful reference to indicate the likelihood of malignancy of breast masses. In this paper, a new Fourier-Transform-based measure of irregularity—Fourier Irregularity Index (F2), is proposed to provide reliable malignant/benign tumor/mass classification. The proposed measure has been evaluated on 418 breast masses, including 190 malignant masses and 218 benign lesions identified by radiologists on film mammograms. The results show the proposed measure has better performance than other approaches, such as Compactness Index (CI), Fractal Dimension (FD) and the Fourier-descriptor-based shape Factor (FF). Furthermore, these mentioned measures are paired to investigate the possibility of performance improvement. The results showed the combination of F2 and CI further enhances the performance in indicating the likelihood of malignancy of breast masses.

Original languageEnglish (US)
Pages (from-to)3783-3798
Number of pages16
JournalMultimedia Tools and Applications
Volume74
Issue number11
DOIs
StatePublished - Jun 26 2015

Keywords

  • Breast masses classification
  • Contour analysis
  • Fourier Transform
  • Irregularity index

ASJC Scopus subject areas

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Fourier irregularity index: A new approach to measure tumor mass irregularity in breast mammogram images'. Together they form a unique fingerprint.

  • Cite this