SkinAI-flutter-app

# 🏥 AI Skincare Diagnosis App

<div align="center">

[![Flutter](https://img.shields.io/badge/Flutter-02569B?style=for-the-badge&logo=flutter&logoColor=white)](https://flutter.dev)
[![TensorFlow](https://img.shields.io/badge/TensorFlow-FF6F00?style=for-the-badge&logo=tensorflow&logoColor=white)](https://tensorflow.org)
[![Dart](https://img.shields.io/badge/Dart-0175C2?style=for-the-badge&logo=dart&logoColor=white)](https://dart.dev)

**AI-powered dermatological analysis application with multilingual support**

[📱 Features](#-features) • [🚀 Getting Started](#-getting-started) • [🏗️ Tech Stack](#️-tech-stack) • [📋 Usage](#-usage) • [🤝 Contributing](#-contributing)

</div>

---

## 📖 Overview

An advanced Flutter application that leverages artificial intelligence to analyze skin lesions and provide detailed dermatological information. Built with TensorFlow Lite for on-device inference, ensuring privacy and real-time analysis.

### 🎯 Key Highlights

- **🧠 AI-Powered**: Advanced deep learning model for accurate skin lesion classification
- **🌍 Multilingual**: Full Turkish and English language support
- **📱 Cross-Platform**: Native iOS and Android applications
- **🔒 Privacy-First**: On-device processing ensures user data security
- **📚 Educational**: Comprehensive medical information for each condition
- **🎨 Modern UI**: Glass morphism design with smooth animations

## ✨ Features

### 🔬 Medical Analysis
- **7-Class Disease Detection**: Advanced classification of skin conditions
- **Real-time Inference**: Instant analysis using optimized TensorFlow Lite model
- **Confidence Scoring**: Detailed probability scores for each prediction
- **Medical Disclaimers**: Appropriate safety warnings and recommendations

### 🌐 User Experience
- **Bilingual Interface**: Seamless Turkish ↔ English language switching
- **Intuitive Design**: Modern glass morphism UI with gradient backgrounds
- **Detailed Information**: Comprehensive disease descriptions, symptoms, and treatments
- **Image Management**: Camera capture and gallery selection with sharing capabilities

### 📊 Technical Excellence
- **Optimized Performance**: Efficient model inference with minimal latency
- **Responsive Design**: Adaptive layouts for various screen sizes
- **Error Handling**: Robust error management and user feedback
- **Settings Persistence**: User preferences saved locally

## 🏗️ Tech Stack

### Frontend
- **Flutter 3.x** - Cross-platform mobile framework
- **Dart** - Programming language
- **Material Design 3** - Modern UI components

### AI/ML
- **TensorFlow Lite** - On-device machine learning
- **Custom CNN Model** - 7-class skin lesion classifier
- **Image Preprocessing** - Optimized input pipeline

### Dependencies
```yaml
dependencies:
  flutter: ^3.0.0
  tflite_flutter: ^0.10.4
  image_picker: ^1.0.4
  shared_preferences: ^2.2.2
  share_plus: ^7.2.1
  path_provider: ^2.1.1
```

## 🎯 Supported Conditions

| Condition | Risk Level | Description |
|-----------|------------|-------------|
| 🔶 **Actinic Keratosis** | Moderate | Pre-cancerous lesions from sun damage |
| 🔵 **Basal Cell Carcinoma** | Moderate | Most common type of skin cancer |
| 🟢 **Benign Keratosis** | Low | Non-cancerous skin growths |
| 🟤 **Dermatofibroma** | Low | Benign fibrous skin nodules |
| 🔴 **Melanoma** | High | Serious form of skin cancer |
| 🟡 **Melanocytic Nevus** | Low | Common moles and nevi |
| 🟣 **Vascular Lesions** | Low | Blood vessel related skin marks |

## 🚀 Getting Started

### Prerequisites

- **Flutter SDK** (>= 3.0.0)
- **Dart SDK** (>= 3.0.0)
- **iOS 11.0+** or **Android API 21+**
- **Xcode 14+** (for iOS development)
- **Android Studio** (for Android development)

### Installation

1. **Clone the repository**
   ```bash
   git clone https://github.com/yourusername/ai-skincare-app.git
   cd ai-skincare-app
   ```

2. **Install dependencies**
   ```bash
   flutter pub get
   ```

3. **Run the application**
   ```bash
   # For development
   flutter run
   
   # For release build
   flutter build apk --release  # Android
   flutter build ios --release  # iOS
   ```

### 📁 Project Structure

```
lib/
├── main.dart                           # App entry point & main UI
├── skincare_prediction_service.dart    # AI model inference service
├── disease_information_service.dart    # Medical information database
├── ml_inference_interface.dart         # ML interface definitions
└── assets/
    └── models/
        └── improved_balanced_7class_model.tflite
```

## 📋 Usage

### 📸 Basic Workflow

1. **Launch Application**: Open the app and select your preferred language
2. **Capture/Select Image**: Use camera or choose from gallery
3. **AI Analysis**: Wait for real-time processing (< 2 seconds)
4. **View Results**: Examine predictions with confidence scores
5. **Detailed Information**: Tap results for comprehensive medical information
6. **Share Results**: Export analysis results for consultation

### 🛠️ Advanced Features

- **Language Switching**: Toggle between Turkish and English in real-time
- **Settings Persistence**: Your preferences are automatically saved
- **Detailed Medical Info**: Access symptoms, causes, treatments, and prevention
- **Risk Assessment**: Color-coded risk levels for each condition

## 🔒 Privacy & Security

- **On-Device Processing**: All AI inference happens locally
- **No Data Upload**: Images and results never leave your device
- **Medical Disclaimer**: Clear warnings about professional medical consultation
- **HIPAA Considerations**: Designed with healthcare privacy in mind

## ⚠️ Medical Disclaimer

**IMPORTANT**: This application is for educational and informational purposes only. It is not intended to replace professional medical advice, diagnosis, or treatment. Always consult with qualified healthcare professionals for any skin concerns.

## 🤝 Contributing

We welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details.

### Development Setup

1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request

## 📄 License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

## 🙏 Acknowledgments

- TensorFlow team for the excellent mobile ML framework
- Flutter team for the amazing cross-platform toolkit
- Medical professionals who provided domain expertise
- Open source community for invaluable tools and libraries

---

<div align="center">

**⭐ Star this repository if you found it helpful!**

Made with ❤️ using Flutter & TensorFlow

</div>