Medical imaging, including X-ray imaging, involves capturing and interpreting visual representations of the body’s internal structures, aiding in disease diagnosis and treatment planning. In this context, Artificial intelligence (AI) and image processing represent a potential tool for clinical practice and disease detection due to its ability to analyze vast amounts of medical data rapidly, aiding healthcare professionals in making accurate diagnoses and improving patient outcomes. This study explores metaheuristic optimization in neuroevolution techniques to enhance image processing tasks, focusing on X-ray image classification for pneumonia detection. The proposed framework utilizes a pre-trained Convolutional Neural Network (CNN) and different metaheuristic algorithms for hyperparameters optimization for comparison purposes. The test is conducted by using a publicly available dataset, with normal and pneumonia classes. Experimental results demonstrate improved accuracy in distinguishing pneumonia-positive and normal X-ray scans, reaching. The study showcases the potential of neuroevolution combined with metaheuristic optimization for addressing complex image processing challenges in medical diagnostics, hence advancing AI-assisted disease detection systems.