Multi-class Chest Radiograph Classification Using Deep Convolutional Generative Adversarial Networks

The urgency for precise diagnostics during the COVID-19 pandemic has driven advancements in imaging and deep learning tools. However, progress is impeded by limited access to medical imaging data. This study employs cutting-edge deep learning techniques to identify chest diseases, including COVID-19 and various lung conditions. State-of-the-art Generative Adversarial Networks (GANs), including CycleGAN, Super-Resolution GAN (SRGAN), and Deep Convolutional GAN (DCGAN), are used to synthesize medical images, augmenting the dataset and enhancing model robustness. VGG-19 achieves a remarkable 91% accuracy and an F1-score of 0.98 across diverse chest-related diseases. Saliency Maps and Grad-CAM graphics improve interpretability, showcasing the model’s healthcare potential. The study encompasses diseases such as Pneumonia and COVID-19, contributing to a comprehensive classification task. These findings underscore the impact of deep learning in medical imaging, promising improved patient care and healthcare accessibility.