An AI and Deep Learning based solution to help diagnose the presence of Covid-19 infection by analyzing the chest X-Ray images.
The dataset used for this study is a combination of the below mentioned datasets from which the NORMAL
and the COVID-19 INFECTED
chest x-ray images have been extracted.
The dataset contains the images collected from the following 3 datasets.
- https://www.kaggle.com/praveengovi/coronahack-chest-xraydataset
- https://github.com/ieee8023/covid-chestxray-dataset
- https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
Two models were created -
- Custom CNN Model.
- Transfer Learning Model using EfficientNet-B0 pre-trained model.
The training phase metrics for the transfer learning model can be seen in the following image -
The following chart shows a consolidated report of the model testing -
The application is deployed using Heroku Platform as a Service (PaaS) @ https://diagnose-covid19.herokuapp.com/
The images located in the Deployment Testing Directory can be used for testing out the Web application.