AbdulManafSahito/Pediatric-Chest-Xray-Pneumonia-Classification-System

🫁 Pediatric Chest Pneumonia Classification System

A Gradio-based web application for detecting pneumonia in pediatric chest X-ray images using deep learning.

🚀 Features

• —AI-Powered Detection: Uses a trained CNN model to classify chest X-rays
• —User-Friendly Interface: Simple drag-and-drop image upload
• —Real-time Predictions: Instant classification results with confidence scores
• —Educational Purpose: Designed for learning and research applications

🏥 How It Works

1. 1.Upload: Upload a chest X-ray image (PNG, JPG, JPEG)
2. 2.Analyze: The AI model processes the image using computer vision
3. 3.Predict: Get classification results (NORMAL or PNEUMONIA) with confidence score

🔬 Model Architecture

• —Input Size: 148x148 grayscale images
• —Architecture: Convolutional Neural Network (CNN)
• —Layers:
• —Conv2D (32 filters) + MaxPooling + BatchNormalization
• —Conv2D (64 filters) + MaxPooling
• —Dense layer with sigmoid activation
• —Output: Binary classification (Normal vs Pneumonia)

🛠️ Technical Details

• —Framework: TensorFlow/Keras
• —Interface: Gradio
• —Image Processing: OpenCV
• —Deployment: Hugging Face Spaces

📋 Usage Instructions

Local Development

1. 1.Install dependencies:

pip install -r requirements.txt

1. 1.Run the application:

python app.py

1. 1.Open the provided URL in your browser

Hugging Face Spaces Deployment

1. 1.Create a new Space on Hugging Face
2. 2.Upload all files from this directory
3. 3.The space will automatically deploy using the requirements.txt

⚠️ Important Disclaimer

This application is for educational and research purposes only.

• —Not intended for actual medical diagnosis
• —Should not replace professional medical consultation
• —Results should be verified by qualified healthcare professionals
• —Always consult with a doctor for medical concerns

📊 Model Performance

The model has been trained on pediatric chest X-ray datasets and provides classification confidence scores. However, medical AI should always be used as a supportive tool alongside professional medical expertise.

🤝 Contributing

Feel free to contribute to improve the model accuracy, user interface, or add new features!

📄 License

This project is for educational purposes. Please ensure compliance with medical data regulations in your jurisdiction.