This project focuses on detecting pneumonia in chest X-ray images using a deep learning model based on ResNet50.
Leveraging TensorFlow and Python, the model was trained to accurately distinguish between pneumonia and healthy cases from X-ray data.
The system achieved high-performance metrics on the test set, with an accuracy of 95.78%, F1-score of 0.9719, recall of 0.9845, precision of 0.9597, and an impressive AUC of 0.9945.
This deep learning model aims to assist healthcare professionals in diagnosing pneumonia more efficiently and accurately, particularly in resource-limited settings.
1. Develop a deep learning-based system using ResNet50 to detect pneumonia in chest X-ray images.
2. Train and optimize the model using TensorFlow and Python for high accuracy and reliable performance.
3. Achieve high classification metrics, including accuracy, F1-score, recall, precision, and AUC.
4. Assist healthcare professionals in diagnosing pneumonia effectively using automated image analysis.
5. Test the model on X-ray datasets to ensure robustness and generalizability in real-world clinical settings.
6. Provide an AI-powered solution to enhance diagnostic capabilities in healthcare, especially in areas with limited medical expertise.
