How stepankarapetyan/tuberculosis-x-ray-detection-ai-project works
This is a web application for classifying uploaded chest X-rays as Normal or Tuberculosis and, when available, returning a Grad-CAM visualization. The user workflow runs from browser upload through the Flask prediction endpoint, image preparation, model inference, and display of the result. The README also documents a notebook for model training and analysis. The model artifact is named in documentation and server configuration but is not present in the supplied file tree; frontend markup and notebook internals were not sampled, so their connections are limited to documented relationships.
Main entry points: server.py Flask server · index.html Upload interface · script.js Browser interaction · Tuberculosis.ipynb Training analysis
Components 9
Web interface
- Upload interface
index.html - Browser interaction
script.js
Prediction service
- Flask server
server.py - Image preparation
server.py - TB classifier
server.py - Grad-CAM overlay
server.py - Trained model
Model development
- Training analysis
Tuberculosis.ipynb
Other components
- User
Connections 10
- User → Upload interface: uploads X-ray
README.md - Upload interface → Browser interaction: provides interface
README.md - Browser interaction → Flask server: posts image
script.js - Flask server → Upload interface: serves page
server.py - Flask server → Image preparation: prepares image
server.py - Flask server → TB classifier: runs prediction
server.py - TB classifier → Trained model: predicts with
server.py - Flask server → Grad-CAM overlay: generates overlay
server.py - Flask server → Browser interaction: returns result
script.js - Training analysis → Trained model: trains model
README.md