The most common symptoms of COVID-19 are fever, dry cough, and tiredness. Other symptoms that people may experience include aches, pains, or difficulty in breathing. Most of these symptoms show signs of respiratory infections and lung abnormalities which can be detected by radiologists. Thus, it is possible to use Machine Learning algorithms to detect the disease from images of Chest X-rays and CT scans. Automated applications can be created to help support radiologists.
In our project we have used four Deep Learning algorithms, namely: VGG16, ResNet50, InceptionV3 and Xception.
The project aims to classify the X-ray and CT scan images uploaded by the user as covid affected or non-covid affected with percentage.
- Clone the repository locally.
- Install the dependencies from "requirements.txt".
- Run the app.py file
- Navigate to the web adress where the flask app is hosted.
- Click on the "Detect covid" button and upload the X-ray or CT scan image at the mentioned place. The results would be displayed as percentage of covid or non-covid through the four CNN models that we have trained.
https://docs.google.com/presentation/d/1p1S7nYDqQXqew9sZmWZzTE9hzMEKeEImf8soNXw9mgI/edit?usp=sharing