This project aims to predict whether a breast tumor is benign or malignant using various machine learning algorithms. The implementation is done in Python with Jupyter Notebook, leveraging powerful libraries like scikit-learn, pandas, and matplotlib.
Breast cancer is one of the most common types of cancer among women worldwide. Early diagnosis can significantly improve recovery chances.
This project leverages machine learning to classify breast tumors into benign or malignant, helping in medical diagnostics research.
The dataset used is the Breast Cancer Wisconsin (Diagnostic) Dataset, which contains features computed from digitized images of a fine needle aspirate (FNA) of breast masses.
🔗 UCI ML Repository – Breast Cancer Wisconsin Dataset
- Python 3.x
- Jupyter Notebook
- Pandas
- NumPy
- Matplotlib & Seaborn
- Scikit-learn (Logistic Regression, SVM, KNN, Random Forest, etc.)
The models were evaluated using:
- Accuracy
- Confusion Matrix
- Precision, Recall, F1 Score
- ROC-AUC Curve
The models achieved high accuracy (97%+ depending on the algorithm).
- Random Forest and SVM performed particularly well, making them strong candidates for assisting medical diagnostics.
-
Clone this repository
git clone https://github.com/yourusername/Breast-Cancer-Detection-System.git cd Breast-Cancer-Detection-System -
Install dependencies
pip install -r requirements.txt
-
Run the notebook
Openbreast_cancer_detection.ipynbin Jupyter and run all cells.
- Add deep learning models (TensorFlow/Keras)
- Deploy as a web app using Streamlit or Flask
- Integrate cross-validation and hyperparameter tuning
- Add support for image-based diagnosis
This project is open source and available under the MIT License.
🔗 Project Link: Breast Cancer Detection System