This project is an AI-based medical image analysis system that detects Pneumonia from Chest X-ray images using Deep Learning.
It provides an end-to-end pipeline including:
- Image preprocessing
- CNN model training
- Prediction system
- Interactive Streamlit web application
Manual diagnosis of diseases from X-ray images can be:
- Time-consuming
- Prone to human error
- Dependent on expert availability
This project demonstrates how AI can assist doctors by providing fast and accurate predictions.
This system simulates real-world applications used in:
- 🏥 Hospitals
- 🧪 Diagnostic Labs
- 🩻 Radiology Centers
- 💻 HealthTech Companies
AI models like this help in:
- Early disease detection
- Faster diagnosis
- Reducing workload of radiologists
- Training Accuracy: ~98%
- Validation Accuracy: ~95%
- Loss: Low and stable
✔ Model generalizes well on unseen data ✔ Suitable for real-world prototype demonstration
- Python
- TensorFlow / Keras
- OpenCV
- NumPy
- Matplotlib
- Streamlit
Dataset used: 👉 Chest X-ray Pneumonia Dataset (Kaggle)
Download link: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia
After downloading, place dataset in:
data/ ├── train/ ├── test/
AI-Medical-Image-Analysis/
│
├── app.py
├── src/
├── models/
├── outputs/
├── images/
├── requirements.txt
├── README.md
git clone https://github.com/varda24/AI-Medical-Image-Analysis.git
cd AI-Medical-Image-Analysis
pip install -r requirements.txt
streamlit run app.py
✔ Upload chest X-ray image ✔ AI-based prediction (Normal / Pneumonia) ✔ Confidence score display ✔ Medical-style interpretation ✔ Clean and interactive UI
-
Input: Chest X-ray image
-
Output:
- 🟥 Pneumonia Detected
- 🟩 Normal
- Deep Learning (CNN) for image classification
- Medical image preprocessing
- Model evaluation techniques
- Streamlit web app development
- Deployment of ML models
This project is for educational purposes only and should not be used for real medical diagnosis.
Varda Kunde