Hippopotamus Optimization for Medical Image Enhancement

Abstract

Medical image enhancement plays a crucial role in improving the accuracy and reliability of diagnostic processes. The quality of medical images often suffers from poor contrast and noise, which can hinder the effective interpretation of critical details. To address these challenges, we propose a novel Hippopotamus Optimization Algorithm-Based Adaptive Histogram Equalization (HOAAHE) technique for medical image enhancement. The HOAAHE technique combines the adaptive histogram equalization (AHE) method with the Hippopotamus Optimization Algorithm (HOA), a nature-inspired metaheuristic optimization technique. AHE is widely recognized for enhancing local contrast and preserving edge details in images, but it can sometimes result in over-enhancement or noise amplification in certain areas. HOA is introduced to optimize the parameters of AHE, aiming for an optimal balance between contrast improvement and noise suppression. The proposed method is evaluated on a range of medical images, including X-ray, MRI, and CT scans, and compared with traditional image enhancement techniques. The results demonstrate that HOAAHE effectively enhances image contrast, preserves fine details, and reduces noise artifacts, leading to better visual quality and improved diagnostic capabilities. The performance metrics, such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Natural Image Quality Evaluator (NIQE) and Absolute Mean Brightness Error (AMBE)confirm the superiority of the HOAAHE technique in medical image enhancement.