Dermai: Skin Cancer Detection Tool

Dermai Example
🏆 1st Place - Databricks Challenge at KnightHacks 2024

Dermai is a mobile app for skin cancer detection using a 91.2% accurate custom CNN with on-device inference on 10,000+ images. Built for KnightHacks 2024 with 300+ participants, this project addresses the critical need for accessible early-detection tools to combat rising skin cancer cases.

What It Does

Dermai allows users to capture or upload images of skin lesions, which an AI model analyzes to detect potential skin cancer, providing immediate feedback. The app serves as a potentially life-saving tool by making early detection accessible to everyone.

Technical Stack

  • Frontend: React Native & TypeScript
  • AI/ML: TensorFlow, Keras, Custom CNN
  • Database: MongoDB
  • Platform: Mobile (iOS/Android)

Key Features

  • Real-time skin lesion analysis
  • 91.2% accuracy on 10,000+ training images
  • On-device inference for privacy
  • Camera capture and image upload
  • Immediate AI-powered feedback
  • Cross-platform mobile compatibility