Automated Pneumonia Detection Using ResNet50 Deep Learning Model

Department of Computer Science & Engineering, D.Y.Patil Technical Campus, Shivaji University, Kolhapur

Pneumonia poses a significant health challenge worldwide, causing millions of deaths annually. Accurate and timely diagnosis is essential for effective treatment, but reliance on manual interpretation of chest X-rays by radiologists can lead to delays and errors. This study presents an automated solution leveraging the ResNet50 deep learning architecture for binary classification of pneumonia from chest radiographs. Our approach incorporates data augmentation, transfer learning, and fine-tuning to enhance model robustness. We evaluate performance using metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. The system integrates a Streamlit-based interface to facilitate seamless image uploads and instant diagnostic feedback. Results demonstrate a high classification accuracy of 96.8%, precision of 97.2%, and recall of 96.5%, indicating the model’s potential to assist clinicians in resource-constrained environments.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.