Improvement of microcalcification cluster detection in mammography utilizing image enhancement techniques

  • Authors:
  • A. Papadopoulos;D. I. Fotiadis;L. Costaridou

  • Affiliations:
  • Department of Medical Physics, Medical School, University of Ioannina, GR 45110 Ioannina, Greece and Department of Computer Science, University of Ioannina, Unit of Medical Technology and Intellig ...;Department of Computer Science, University of Ioannina, Unit of Medical Technology and Intelligent Information Systems, and Biomedical Research Institute-FORTH, GR 45110 Ioannina, Greece;Department of Medical Physics, Medical School, University of Patras, GR 26500 Patras, Greece

  • Venue:
  • Computers in Biology and Medicine
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this work, the effect of an image enhancement processing stage and the parameter tuning of a computer-aided detection (CAD) system for the detection of microcalcifications in mammograms is assessed. Five (5) image enhancement algorithms were tested introducing the contrast-limited adaptive histogram equalization (CLAHE), the local range modification (LRM) and the redundant discrete wavelet (RDW) linear stretching and shrinkage algorithms. CAD tuning optimization was targeted to the percentage of the most contrasted pixels and the size of the minimum detectable object which could satisfactorily represent a microcalcification. The highest performance in two mammographic datasets, were achieved for LRM (A"Z=0.932) and the wavelet-based linear stretching (A"Z=0.926) methodology.