A Django based Web Application to detect the presence of COVID-19 in Chest X-Ray Images. The Deep Learning models are trained on a publicly available dataset of ~2500 Chest X-Ray Images labelled as either COVID-19 or non-COVID. For better comparison purposes, three different architectures were used which includes, Xception, ResNet50 and VGG16. The models were trained separately on the dataset and the weightfiles were later loaded onto the Webapp to detect the presence of COVID-19
- Model Architecture
- Loss Curves
- Confusion Matrix Obtained
- Model Architecture
- Loss Curves
- Confusion Matrix Obtained
- Model Architecture
- Loss Curves
- Confusion Matrix Obtained
- Dataset Link - SARS-COV2-Ct-Scan Dataset
Soares, Eduardo, Angelov, Plamen, Biaso, Sarah, Higa Froes, Michele, and Kanda Abe, Daniel. "SARS-CoV-2 CT-scan dataset: A large dataset of real patients CT scans for SARS- CoV-2 identification." medRxiv (2020). doi: https://doi.org/10.1101/2020.04.24.20078584. Angelov, P., & Soares, E. (2020). Towards explainable deep neural networks (xDNN). Neural Networks, 130, 185-194. - Google Drive Folder : Notebooks/Model Weights/Dataset