This project implements a deep learning Convolutional Neural Network (CNN) to classify medical organ images into four categories: Heart, Brain, Liver, Limbs.

1. 📽️ Video
2. 📂 Project Structure
3. 🛠️ Prerequisites
4. ✨ Key Features
5. 🛠️ Installation
6. 📊 Dataset Preparation
7. 🧠 Model Architecture
8. 🚀 Training
9. 🪄 Usage
   • Training the Model
   • Predicting with the Model
10. 📈 Performance Metrics
11. 💾 Model Saving
12. 🛠️ Customization
13. ⚠️ Limitations
14. 📈 Future Improvements
15. 🤝 Contributions
16. 📜 License
17. 📧 Contact

project_root/
│
├── data_sets/
│   ├── heart/
│   ├── brain/
│   ├── liver/
│   └── limbs/
│
├── test_data/
│   └── NONE/
│
├── save_model/
│   └── organsClssify.h5
│
└── logs/

• Python 3.8+
• TensorFlow
• Numpy
• Matplotlib

• Image classification using CNN
• Data augmentation
• TensorBoard logging
• Model saving and loading functionality
• Visulization of training metrics

1. Clone the repository
2. Install required dependencies:

pip install tensorflow numpy matplotlib

• Organize images in data_sets/ directory
• Each subdirectory represents a different organ class
• Recommended image size: 256x256 pixels

• Convolutional layers for feature extraction
• MaxPooling for dimensionality reduction
• Dropout for preventing overfitting
• Dense layers for classification

• Uses Adam optimizer
• Categorical cross-entropy loss
• 5 training epochs
• Automatic train/validation/test split

# Run the main script to train the model
python organ_classification.py

test_model('path/to/test_image.jpg')

• Training and validation loss tracked
• Training and validation accuracy visualized
• Final test set evaluation provided

• Trained model saved as organsClssify.h5
• Can be loaded for future predictions

• Adjust hyperparameters in the script
• Modify model architecture as needed

• Requires diverse and well-labeled training data
• Performance depends on image quality and dataset composition

• Increase training epochs
• Implement more advanced data augmentation
• Experiment with deeper network architectures

Contributions are welcome! Feel free to fork this repository, create a branch, and submit a pull request with your enhancements.

This project is licensed under the MIT License - see the LICENSE file for details.

If you have any questions or suggestions, feel free to reach out via GitHub or email at [Ibrahim.Ibrahim051@eng-st.cu.edu.eg]