Cross-Dataset Generalization of Deep Learning Models for Pneumonia Detection from Chest X-Ray Images
This project focuses on developing and evaluating deep learning models for detecting pneumonia from chest X-ray images. Models such as ResNet50 and DenseNet121 are used to classify X-ray images into Normal and Pneumonia categories. The main objective is to study how well these trained models perform on different datasets, even when tested on images they have not previously seen. Performance is evaluated using accuracy, precision, recall, F1-score and confusion matrices. Grad-CAM is also used to visualize the image regions influencing model predictions. The project aims to understand the generalization ability and limitations of deep learning models in medical image classification.
Authors
- Yash Chaudhari
- Priyanshu Patil
- Jitesh Raskar
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.5281/zenodo.24333414
- Primary Topic
- COVID-19 diagnosis using AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00