Chest X-ray Image Pneumonia Detection using Transfer Learning and Xception CNN Model

Pneumonia is a major worldwide health problem that requires the use of modern diagnostic tools to diagnose it quickly and accurately. This study presents a new approach to improve the accuracy of pneumonia detection in Chest X-ray (CXR) pictures by employing several transfer learning approaches. Transfer learning is a highly efficient technique in image classification, especially when used to medical imaging tasks such as the identification of pneumonia from chest X-ray pictures. We conducted thorough evaluations over 200 epochs utilizing a dataset of 3450 CXR pictures to assess the effectiveness of our proposed model. To enhance generalization, data augmentation, notably the addition of Colour Jitter, was implemented to provide a more diverse training dataset. The model's efficacy was evaluated using performance indicators such as precision, recall, F1 score, and accuracy. With an impressive 97% overall accuracy, this demonstrates the method's reliability in diagnosing pneumonia. This study provides medical practitioners with a reliable and efficient tool that enhances the current level of pneumonia diagnosis.