ENHANCED PNEUMONIA DETECTION IN CHEST X-RAYS USING ATTENTION AND FNMS

Abstract—Pneumonia is a life-threatening respiratory infection that requires rapid and accurate diagnosis for effective treatment. In this study, we develop a deep learning-based pneumonia detection and classification model using chest X-ray images, distinguishing between normal, bacterial pneumonia, and viral pneumonia cases. The dataset, sourced from publicly available medical image repositories, is preprocessed and augmented to improve generalization. A Convolutional Neural Network (CNN) model is trained using optimized hyperparameters, with tech- niques such as batch normalization, dropout regularization, and early stopping to enhance accuracy and prevent overfitting. The model is evaluated on a separate test set, achieving a promising accuracy in detecting pneumonia subtypes. Further, performance metrics such as precision, recall, F1-score, and confusion matrices are analyzed. This research demonstrates the potential of deep learning in medical image analysis, offering a scalable and automated approach to assist radiologists in early pneumonia diagnosis. Future work includes leveraging transfer learning with ResNet50 and ensemble models for further accuracy improvements. Keywords: Pneumonia Detection, Deep Learning, Chest X-ray, CNN, Medical Image Classification, Machine Learning