Enhancing Pneumonia Disease Classification using Genetic Algorithm-Tuned DCGANs and VGG-16 Integration

Abstract

Diagnostic complications arise from pneumonia, characterized by lung inflammation caused by alveolar fluid accumulation, particularly in regions with limited radiologists. To tackle this issue, a new method utilizes the VGG16 methodology for categorization, bolstered by genetic algorithms. In addition, Deep Convolutional Generative Adversarial Networks (DCGANs) improve the dataset by adding fake X-rays of pneumonia. Genetic algorithms are used to optimize hyperparameters in classification tasks. In contrast, DCGANs are employed to increase data augmentation techniques, boosting models' accuracy in identifying and categorizing pneumonia cases. The study partitioned a dataset into training, testing, and validation sets for pneumonia X-ray pictures. The training of GANs entails utilizing both generators and discriminators to produce increasingly realistic pictures gradually. The genetic algorithm enhances the hyperparameter tuning process, resulting in a substantial increase in accuracy. Initially, VGG16 achieved a success rate of 89.50% and a fitness score of 87.50%. Post-optimization and DCGAN augmentation, accuracy climbed to 95.50%, and F1-Score improved to 94.75%. This study combines genetic algorithms and DCGANs to create a model that can produce genuine pneumonia X-ray pictures and enhance categorization accuracy.