This project leverages machine learning, specifically Support Vector Machines (SVM), to predict breast cancer outcomes using clinical data. By analyzing a dataset of breast cancer features, the model distinguishes between malignant and benign cases with high accuracy. This tool aims to enhance early detection, contributing to better diagnostic processes and patient outcomes.
- 🎯 Predicts breast cancer as malignant or benign using clinical features.
- 🧠 Utilizes a Support Vector Machine (SVM) with an RBF kernel for classification.
- 📊 High accuracy achieved through robust preprocessing and feature selection.
- 💻 Interactive web-based interface for user-friendly predictions.
🌐 Access the live application: brstcncrpred.pythonanywhere.com
| Category | Technologies |
|---|---|
| Frontend | HTML, Tailwind CSS, JavaScript |
| Backend | Flask |
| Languages | Python |
| Libraries | NumPy, Pandas, Scikit-learn, Matplotlib, Seaborn |
| Model Packaging | Joblib (version 1.4.2) |
| Dataset | Breast Cancer Wisconsin dataset (UCI Machine Learning Repository) |
main
├── app
│ ├── static
│ │ ├── css
│ │ ├── js
│ ├── templates
│ ├── main.py
│ ├── svm_model.joblib
├── model
│ ├── cancer_prediction.ipynb
├── LICENSE
├── README.md
- Clone the repository:
git clone https://github.com/SuddhashilSarkar/Breast-Cancer-Prediction-using-ML.git
- Navigate to the project directory:
cd Breast-Cancer-Prediction-using-ML - Install the required dependencies:
pip install -r requirements.txt
- Run the application:
python app/main.py
- Open the hosted app or run it locally.
- Input clinical data features, such as mean radius and mean texture.
- Click "Predict" to get the classification result (malignant or benign).
The Breast Cancer Wisconsin dataset provides clinical features, including:
- Mean radius
- Mean texture
- Mean perimeter
- Mean area
- Mean smoothness
The dataset is sourced from the UCI Machine Learning Repository.
- Suddhashil Sarkar
- Sulagna Mandal
- Ishita Mondal
- Partha Koley
We are deeply grateful to our project guide, Partha Koley, for his invaluable guidance, and to our families, teachers, and friends for their support. Special thanks to the creators of the Breast Cancer Wisconsin dataset and the developers of the libraries used in this project.
This project is licensed under the MIT License.
For queries or contributions, contact: