Optimization of Convolutional Neural Network Architecture by PSO Algorithm for MRI Brain Tumor Image Classification

In recent years, the application of convolutional neural networks (CNN) has significantly advanced image clas-sification tasks, particularly in the medical field. In the present study, we applied CNN to magnetic resonance imaging (MRI) to classify brain tumors. Building a CNN requires adjustment of configuration architecture. For such adjustment, we used Particle Swarm Optimization (PSO) algorithm for optimal configuration that allow us high accuracy. Experimental results showed that PSO applied to CNN performed with a classification accuracy of 98%.