Enhanced COVID-19 Diagnosis from Chest X-Rays Using Transfer Learning with VGG16

This study explores the application of a deep learning model based on VGG16 for classifying medical images into three categories: normal, COVID-19, and pneumonia. Leveraging the power of transfer learning, the pre-trained VGG16 model was fine-tuned on a custom dataset to achieve high accuracy in image classification. The model achieved a training accuracy of 98% and a validation accuracy of 96%, with a corresponding training loss of 0.03 and a validation loss of 0.12. These results indicate the model's strong ability to learn from the training data and generalize to unseen validation data. Key techniques such as ReduceLROnPlateau and Early Stopping were employed to optimize the training process by automatically adjusting the learning rate and preventing overfitting. Despite the promising results, limitations such as the size of the dataset and the computational resources required for training were identified. Future work may focus on data augmentation and experimenting with more advanced neural network architectures to further enhance model performance