CrispenGari/tuberculosis-AI

🧑‍⚕️🤖 AI-powered tuberculosis detection system using chest X-rays - built for low-resource environments with mobile support and radiologist-in-the-loop validation. ### 🫁 TB-AI Diagnostic Assistant (TBAIDA) > 🚀 **AI-powered Tuberculosis Screening for Underserved Communities** TBAIDA is an intelligent, scalable, and cost-effective diagnostic assistant designed to support healthcare professionals in detecting **Tuberculosis (TB)** using chest X-ray images. Built with deep learning and deployed through a mobile-first ecosystem, the system is engineered for **real-world impact in resource-constrained environments**. > This repository contains two main sub directory which are: 1. `mobile` - The mobile app that does predictions by sending requests to the API server using `X-Ray` images of a human chest. 2. `server` - This is an API server that serves different models that does TB predictions on chest-x-ray images of a human. ### Table of Contents - 🫁 TB-AI Diagnostic Assistant (TBAIDA) - Table of Contents - 🌍 Why This Matters - 💡 Our Solution - 🏗️ System Architecture - 📱 Key Features - 🔬 AI-Powered Diagnosis - 📡 Offline-First Capability - ⚖️ Bias-Aware AI - 🔄 Continuous Learning System - 👨‍⚕️ Radiologist-in-the-Loop - 🎯 Target Users - 📱 Application UI - Landing Page - Home Screen - Results - History Page - Settings Page - Home \& Prediction Flow - Diagnosis Results - 🧪 How It Works - 🌟 What Makes TBAIDA Different? - 💰 Business \& Sustainability Model - 🚀 Roadmap - 🤝 Contributors - ⚠️ Disclaimer - 📜 License - ⭐ Support This Project --- ### 🌍 Why This Matters Tuberculosis remains one of the leading causes of death in South Africa and globally. - 🇿🇦 South Africa reports **~280,000 TB cases annually** - ⚠️ ~54,000 deaths each year - 👨‍⚕️ Only **~650 radiologists serving ~63 million people** - ⏱️ Delayed diagnosis = preventable deaths > 💡 **Early detection saves lives — but access to radiologists is limited.** --- ### 💡 Our Solution TBAIDA leverages **Artificial Intelligence + Mobile Technology** to: - 🧠 Analyze chest X-ray images using deep learning models - ⚡ Provide **instant diagnostic insights** - 👩‍⚕️ A …