Deep Learning Based Pneumonia Detection from Chest X-ray Images Using DenseNet169
Deep Learning Based Pneumonia Detection from Chest X-ray Images Using DenseNet169
Authors:
1Monika R, 2Princy Antonia D, 3Pooja K, 4Mr. S. Kandeeban, 5Dr. T. Kumanan, 6Dr. M. Nisha.
1,2,3 Students, Department of CSE
4,6 Assistant Professor, Department of CSE, 5 Professor, Department of CSE
Dr.M.G.R Educational and Research Institute, Maduravoyal, Chennai 95, Tamilnadu, India.
Abstract— Pneumonia is a serious respiratory infection that requires early and accurate diagnosis to reduce complications and mortality. Chest X-ray imaging is commonly used for pneumonia detection; however, manual interpretation by radiologists can be time-consuming and may lead to variability in diagnosis. To address this challenge, this study proposes a deep learning–based approach for automatic pneumonia detection using the DenseNet169 architecture. The model was trained on the publicly available Chest X-ray Pneumonia dataset containing 5,863 images. Prior to training, image preprocessing and data augmentation techniques were applied to enhance model generalization and reduce the effects of data imbalance. Experimental evaluation shows that the proposed model achieves an accuracy of 81% in classifying chest X-ray images as normal or pneumonia. These results demonstrate that the proposed system can support clinicians by providing a fast and reliable tool for preliminary pneumonia screening.
Keywords: Pneumonia Detection, Deep Learning, Chest X-ray Analysis, Image Preprocessing, DenseNet169, Transfer Learning, Medical Image Classification.