Skip to content
Back to all projects
  • Deep Learning

Tuberculosis Detection from Chest X-Rays

A deep learning system that detects tuberculosis from chest X-ray images via a web interface.

Overview

ResNet50 and EfficientNet architectures predict tuberculosis from chest X-rays with a reliable training and model-persistence workflow. Grad-CAM highlights the infected regions on the image, and a Flask interface returns an instant prediction on upload.

Problem Statement

Tuberculosis screening depends on radiologists who are scarce in exactly the regions where TB burden is highest, and a prediction without visual evidence gives a clinician nothing to check.

Proposed Solution

Deploy a high-accuracy classifier behind a simple upload interface and attach Grad-CAM overlays, so a health worker sees both the call and the region that produced it.

Key Features

  • ResNet50/EfficientNet Classification

    High-accuracy TB prediction from X-ray images.

  • Trained Pipeline & Model Persistence

    Reliable training and model-saving workflow for deployment.

  • Grad-CAM Visualization

    Highlights infected regions on the X-ray.

  • Flask Web Prediction

    Upload an X-ray and receive an instant prediction.

Technologies Used

Deep Learning

  • ResNet50
  • EfficientNet
  • TensorFlow / Keras
  • Transfer learning

Explainability

  • Grad-CAM
  • Matplotlib

Application

  • Flask
  • OpenCV
  • Bootstrap

Project Workflow

  1. 1

    X-ray upload

    A chest X-ray is submitted through the web interface.

  2. 2

    Preprocessing

    The image is resized and normalised for the model.

  3. 3

    Classification

    The CNN predicts TB presence with a confidence score.

  4. 4

    Visualisation

    Grad-CAM overlays the regions driving the prediction.

What You'll Receive

  • Complete, runnable source code with folder structure
  • Project report and technical documentation
  • Ready-to-present PPT content
  • Setup and installation walkthrough
  • Line-by-line project explanation session
  • Viva question bank with answers
  • Bug fixing and troubleshooting help
  • Post-delivery support after submission

Frequently Asked Questions

How much does this project cost?

Every project is quoted individually, because the price depends on the modules you need, your technology stack, your college's format and your deadline. Send us the project name on WhatsApp and we'll share a quote the same day.

Can the project be customised to my college requirements?

Yes. Share your guide's requirements, preferred technology stack and abstract format, and we adapt the modules, dataset or UI accordingly.

Will I be able to explain this project during my viva?

That is the point of the explanation session. We walk you through the architecture, every module, the flow of data and the results, and hand over a viva question bank with answers.

What if the project does not run on my laptop?

We help you with setup end to end — dependencies, environment, database and configuration — over chat or a call until it runs on your machine.

Do I get support after submission?

Yes. Post-delivery support is included, so you can come back for fixes, doubts or demo help even after the project is delivered.

Want This Project?

Get complete source code, documentation, PPT, explanation, and support.

Similar projects

  • Deep Learning
  • NLP

Alzheimer's Disease Prediction

A diagnostic support system for early Alzheimer's disease detection using imaging and behavioral data.

  • Deep Learning-Based Detection
  • Behavioral Pattern Analysis
  • Chatbot Query Resolution

Custom quote

Priced to your scope

View Project
  • Deep Learning
  • Gen-AI

Brain Tumour Detection

A deep learning-based diagnostic tool for detecting brain tumours from MRI scans with explainable predictions.

  • Deep Learning-Based Detection
  • SHAP & LIME Explainability
  • Gen-AI Insights

Custom quote

Priced to your scope

View Project