A review of case study on different metaheuristic optimization techniques for disease detection and classification.

Abstract

This framework explores the use of metaheuristic optimization techniques for disease detection, specifically in image segmentation and feature selection to enhance classification performance. The study evaluates five swarm intelligence methods: Artificial Bee Colony (ABC) for image segmentation, Krill Herd Optimization (KHO) for both segmentation and feature selection, Particle Swarm Optimization (PSO) for feature selection, Grey Wolf Optimization (GWO) for feature selection, and Moth-Flame Optimization (MFO) for feature selection. Results demonstrate significant performance improvements, with accuracy increases of 0.9%, 2%, 2.3%, 2.1%, and 4.2%. These gains are attributed to optimized exploration/exploitation, enhanced diversity, and convergence, showing the effectiveness of metaheuristic techniques in disease detection.