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

Area of Science:

• Medical Imaging Analysis
• Computational Intelligence
• Bioinformatics

Background:

• Disease detection relies heavily on accurate image segmentation and feature selection.
• Traditional methods may not fully optimize classification performance.
• Metaheuristic optimization offers potential for enhancing diagnostic accuracy.

Purpose of the Study:

• To explore metaheuristic optimization techniques for disease detection.
• To evaluate swarm intelligence methods for image segmentation and feature selection.
• To improve classification performance in medical image analysis.

Main Methods:

• Artificial Bee Colony (ABC) for image segmentation.
• Krill Herd Optimization (KHO) for segmentation and feature selection.
• Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), and Moth-Flame Optimization (MFO) for feature selection.

Main Results:

• Significant accuracy improvements observed across evaluated methods.
• Accuracy increases ranged from 0.9% to 4.2%.
• Optimized exploration/exploitation, diversity, and convergence contributed to performance gains.

Conclusions:

• Metaheuristic techniques effectively enhance disease detection accuracy.
• Swarm intelligence methods show promise in medical image segmentation and feature selection.
• This framework provides a robust approach for improving diagnostic tools.