ADAPTIVE MEDICAL IMAGE ENHANCEMENT USING WAR STRATEGY OPTIMIZATION: A MULTI-MODAL STUDY ON X-RAY, MRI, AND CT IMAGING

Abstract

Image enhancement is a fundamental requirement in medical diagnostics to improve visual quality and accentuate anatomical features necessary for accurate disease identification. This paper presents an Adaptive Medical Image Enhancement framework leveraging War Strategy Optimization (WSO), a metaheuristic inspired by the strategic "attack and defence" tactics of warfare, to intelligently automate the selection of enhancement parameters. Unlike traditional fixed-parameter methods that often lead to over-enhancement or artifact amplification, the proposed WSO-based approach dynamically tunes variables for Contrast-Limited Adaptive Histogram Equalization (CLAHE), gamma correction, and unsharp masking. The system was implemented in Python and rigorously validated across a multi-modal dataset comprising Chest X-rays, Brain MRIs, and Low-Dose CT (LDCT) scans. The performance was quantified using a multi-dimensional fitness function incorporating Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Entropy, and Edge Preservation Index (EPI). Experimental results demonstrate superior visual clarity and structural integrity, with PSNR values ranging from 29.63 dB to 31.42 dB and SSIM values between 0.904 and 0.923. Furthermore, convergence analysis confirms that War Strategy Optimization (WSO) Algorithm achieves global optima within 40 iterations, showcasing its computational efficiency and stability. Comparative analysis with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) shows that the WSO method achieves superior image quality, higher structural similarity, and improved detection accuracy. The findings suggest that this robust optimization framework is highly suitable for integration into Computer-Aided Diagnosis (CAD) and real-time clinical imaging systems where diagnostic precision is paramount.