Computer assisted diagnosis for digital mammography

Abstract

This article describes the application of wavelet transform for image enhancement in medical imaging. The initial clinical application is the enhancement of microcalcification clusters (MCCs) in digitized mammograms to improve both their visualization and their detection using computer assisted diagnostic (CAD) methods. The potential universal application for improved visual interpretation of medical images using a computer monitor is also demonstrated. The early detection of MCCs is important in screening programs since their presence is often associated with a high incidence of breast cancer. The enhancement of MCCs is an excellent model for real world evaluation of the wavelet transform. The detection of MCCs presents a significant challenge to the performance characteristics of X-ray imaging sensors and image display monitors since microcalcifications vary in size, shape, signal intensity, and contrast and may be located in areas of very dense parenchymal tissue, making their detection difficult. The classification of MCCs, in turn, as benign or malignant, requires their morphology and detail to be preserved. >