1. Clone Repository

git clone https://github.com/yourusername/breastguard-ai.git
cd "breastguard-ai/Breast Ultrasound Images"

2. Create Virtual Environment

python -m venv venv

• Windows: venv\Scripts\activate
• Linux/Mac: source venv/bin/activate

3. Install Dependencies

pip install flask opencv-python scikit-learn numpy matplotlib seaborn pillow werkzeug

4. Download Dataset

Download breast ultrasound dataset:

Extract to Dataset/ folder with structure:

Dataset/
├── benign/
├── malignant/
└── normal/

5. Train ML Model

jupyter notebook Breast_Cancer_Classification.ipynb

Run all cells. This generates:

• breast_cancer_svm_model.pkl
• scaler.pkl
• model_info.pkl
• Visualization charts (*.png)

6. Run Flask Application

python app.py

Open browser: http://127.0.0.1:5000

Project Structure

Breast Ultrasound Images/
├── app.py                    # Flask app
├── Breast_Cancer_Classification.ipynb  # Training notebook
├── breast_cancer_svm_model.pkl       # Trained model
├── Dataset/                  # Ultrasound images
├── static/                   # CSS, JS, uploads
└── templates/                # HTML pages

Troubleshooting

• Model files missing? Re-run Jupyter notebook
• Port 5000 busy? Change to python app.py --port 5001
• Dataset issues? Verify folder structure matches exactly
• Memory errors? Use smaller image batch sizes in notebook