Pulmonary Disease Classification from X-Rays

This is an image classification app built using TensorFlow, Django, Django REST Framework and React. The app uses a machine learning model built in TensorFlow and trained on X-Ray images from various sources to classify among Normal, Pneumonia and Tuberculosis class.

People Involved in this project

• Pilot Khadka
• Amit Raj Pant
• Sujan Lamichhane

Table of Contents

• Installation
• Running the application

Installation

1. Create a virtual environment

From the root directory run:

cd backend classifier

python -m venv venv

2. Activate the virtual environment

From the backend directory run:

On macOS:

source venv/bin/activate

On Windows:

venv\scripts\activate

3. Install required backend dependencies

From the backend directory run:

pip install -r requirements.txt

4. Install required frontend dependencies

From the root directory run:

cd frontend

npm install

Run the application

To run the application, you need to have both the backend and the frontend up and running.

1. Run backend

From the backend directory run:

python manage.py runserver

2. Run frontend

From the frontend directory run:

npm start

3. View the application

Go to http://localhost:3000/ to view the application.

Dataset

The dataset contains a total of 17,275 images, consisting of 10,406 normal images, 5,775 pneumonia images, and 1,094 tuberculosis infected images

Dataset: https://www.kaggle.com/datasets/amitpant7/lungvision