Artificial Intelligence in Medical Image Contrast Enhancement

Enhancing the contrast of medical images is crucial for accurate diagnosis and analysis, especially in cases where image quality is degraded due to acquisition conditions. This study formulates image contrast enhancement as an optimization problem and proposes the Whale Optimization Algorithm (WOA) to achieve optimal enhancement. The performance of WOA is evaluated and compared with two well-established evolutionary algorithms: Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Four randomly selected dermoscopic images of skin cancer were used as test cases. The evaluation metrics included Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure, and Feature Similarity Index Measure (FSIM), which collectively assess the quality, structural integrity, and feature preservation of the enhanced images. Experimental results demonstrate that WOA outperforms GA and PSO in three out of four cases, yielding higher values in PSNR, SSIM, and FSIM, indicative of superior contrast enhancement and image quality. Only in one instance did PSO slightly surpass WOA. Convergence analysis further confirms the efficiency and stability of WOA in optimizing the contrast enhancement process. The findings suggest that WOA is a robust and reliable approach for medical image enhancement, offering significant improvements over traditional evolutionary methods.

کلیدواژه ها:

Artificial Intelligence ، Whale Optimization Contrast Algorithm ، Enhancement ، Medical Image Processing ، Evolutionary Algorithms