Enhancement and diagnosis of breast cancer in mammography images using histogram equalization and genetic algorithm

In breast cancer imaging, a poor quality nature image, especially one with low contrast, may provide insufficient data for visual interpretation of cancerous regions. Breast cancer survival rates are increasing as detection and analytical methods improve. On the other hand, breast cancer remains the most invasive disease that affects women. To improve the visual aspect of medical images, a combination methodology termed Genetic algorithm based histogram equalization is suggested. Histogram equalization is a quick and easy approach to boost visual contrast. The Genetic algorithm is best suited for multiple constraint optimization problems with an objective function that is subject to a variety of tough and easy restrictions. In this work, a Genetic algorithm with histogram equalization based image enrichment technique is suggested as the data mining method for separating information guidelines of breast cancer analysis forecast. Experiments were carried out on an extensive range of medical images for assessing the suggested method's performance both qualitatively and numerically. When related to leading edge enhancement processes, the projected method achieves improved performance in terms of entropy, structural similarity index, contrast improvement index, peak signal to noise ratio, mean square error and computational difficulty. The recommended procedure progresses contrast while conserving brightness and visual excellence. The suggested technique affords better quality for disease inspection and analysis.