This Flask-React app can be used to diagnose colorectal cancer from histopathology images. It implements the following convolutional neural networks to return a tissue classification that is summarised as cancerous or non-cancerous:

• VGG16 trained from scratch
• VGG16 pre-trained
• ResNet50 trained from scratch
• ResNet50 pre-trained
• InceptionV3 trained from scratch
• InceptionV3 pre-trained

To get started, you will need to have the following tools installed on your machine:

• Node.js
• Python

Once you have those tools installed, you can clone the repository to your local machine using the following command:

git clone https://github.com/your-username/crc-diagnosis-app.git

Next, navigate to the cloned repository directory and install the necessary dependencies by running the following commands:

pip install -r requirements.txt
cd frontend
npm install

To start the app, you can use the following command:

npm run start:server-dev

This will start both the front-end and back-end servers, and you should see the app running at http://localhost:3000 in your browser.

Note that in order for the classifier component to work correctly, you will also need to download the model files from this SharePoint link. Once you have downloaded the models, you should add the paths to the address_lookup dictionary in crc-diagnosis-app/backend/classifier.py.

As this is a medical application that deals with potentially sensitive data, it is important to take appropriate precautions when using it. Here are some general guidelines to follow:

• Do not use the application to diagnose medical conditions without consulting a qualified medical professional.
• Do not upload any images containing personally identifiable information.