DEEP TRANSFER LEARNING FOR AUTOMATED PNEUMONIA DETECTION IN CHEST X-RAY IMAGES USING MOBILENETV2

Abstract

Pneumonia is a serious respiratory disease that affects the lungs and can become lifethreatening if not detected at an early stage. Chest X-ray imaging is one of the most commonly used diagnostic tools for identifying pneumonia; however, manual analysis of these images is time-consuming and requires expert radiologists. With the rapid advancement of Artificial Intelligence (AI) and Deep Learning, automated systems have emerged as effective solutions for medical image analysis. This project proposes a deep transfer learning-based approach for automated pneumonia detection using chest X-ray images. The system utilizes a Convolutional Neural Network (CNN) combined with the pre-trained MobileNetV2 model to classify images into two categories: normal and pneumonia. Transfer learning enables the model to leverage knowledge from previously trained large-scale datasets, thereby improving accuracy and reducing training time. To enhance model performance, image preprocessing techniques such as resizing, normalization, and data augmentation are applied to improve dataset quality and handle variations in medical images. The trained model is evaluated using performance metrics such as accuracy and loss, demonstrating its effectiveness in detecting pneumonia. The experimental results indicate that the proposed deep learning framework can accurately classify chest X-ray images and assist in early diagnosis. This system can support healthcare professionals by providing faster and more reliable decisionmaking, ultimately improving patient outcomes and reducing the burden on medical experts.