Medical image enhancement using war strategy optimization algorithm

In medical images, especially Magnetic Resonance Images (MRI), the quality of the image may be poor due to low sharpness value. This makes diagnosing the disease difficult and can even lead to misdiagnosis. In this study, the sharpness values ​​of the images were increased by using the real-coded Genetic Algorithm (GA) and the War Strategy Optimization (WSO) algorithm in the adaptive histogram equalization method. Multiple fitness functions were used in the study. Image entropy, energy, sharpness, peak signal-to-noise ratio, gray level co-occurrence matrix, and Sobel edge feature extraction methods were used in the fitness function. In this study, a without elitism WSO algorithm was developed. The developed method was compared with the real coded GA with elitism, the GA without elitism, and the WSO with elitism. The proposed without elitism WSO method increased the contrast value by 15 % and the entropy level by 10 % in MRI images, thus making image details more distinct. While homogeneity was achieved with a 12 % increase in energy metric, the PSNR value increased from 25 dB to 30 dB because of noise reduction. Improved image sharpness and contrast enhancement will significantly increase doctors’ diagnostic accuracy on disease. It has been determined that the proposed without elitism WSO algorithm gives better results and works faster than other compared methods in some images. Elitism has generally shortened the speed of convergence but has not improved the outcome.