Genetic Algorithm Based Feature Selection and Optimized Edge Detection for Brain Tumor Detection

This paper presents a novel approach for brain tumor detection using Steady-State Genetic Algorithms for filter optimization and feature selection. The proposed method utilizes two genetic algorithms to select relevant features and optimize filter coefficients. A genetic algorithm is employed to select a subset of features using random forest as the fitness evaluator. Experimental results demonstrate the effectiveness of the method in accurately detecting brain tumors with reduced computational complexity. Subsequently, another genetic algorithm is employed in which the initial population of fractional order filters is evaluated using ideal edge images, and the top-performing filters undergo crossover and mutation operations. After several generations, the filters with the highest fitness values are selected as optimized filter coefficients. The integration of genetic algorithms with brain tumor detection shows promise for optimizing filters and selecting informative features, improving clinical decision-making.