An image enhancement technique in the DCT domain for cancer detection

In this paper, we develop an image enhancement technology in the DCT domain for radiologists to screen mammograms. The proposed algorithm is an improved version of the algorithm developed. The improved algorithm overcomes the shortcomings of the old algorithm which requires manual adjustment of multiple parameters to realize non-uniform enhancement in different frequency bands. The proposed image enhancement algorithm is expressed as an optimization problem. In the optimization problem, the optimal local enhancement factors are found so that the target global contrast value is achieved which is specified by a user. Because it's a multi-variable optimization problem, genetic algorithm is used to search the optimal parameters. The experimental results show that the algorithm is progressive.

I. Introduction

Breast cancer is one of the most frequent causes of the cancer death for women in the United States. In the U. S., in 2007, there were an estimated 178,480 new cases of breast cancer diagnosed and 40,460 deaths from this disease among women [2]. Currently, there are no effective ways to prevent breast cancer, because its cause remains unknown. However, efficient diagnosis of breast cancer in its early stages can give a woman a better chance of full recovery. Therefore, early detection of breast cancer can play an important role in reducing the associated morbidity and mortality rates.