Enhancement of microcalcifications in digitized mammograms: Multifractal and mathematical morphology approach

Abstract

Two methods for enhancing the microcalcifications in digitized mammograms are under consideration. First method is based on multifractal approach, and second on modern mathematical morphology. In multifractal approach, from initial mammogram image, a corresponding multifractal 'images' are created, from which a radiologist has a freedom to change the level of segmentation in an interactive manner. The second method, using an appropriate combination of some morphological operations, enables high local contrast enhancement, followed by significant suppression of background tissue, irrespective of the radiology density of the tissue. By iterative procedure this method highly emphasizes only small bright details, possible microcalcifications. The interactive approach enables the physician to control the level of segmentation. Suggested methods were tested through referent mammograms from MiniMIAS database and from clinical praxis mammograms.

Keywords

• medical image processing microcalcifications
• mathematical morphology
• multifractal analysis