Machine Learning

Breast Cancer Diagnosis Using Machine Learning

The Breast Cancer Diagnosis Using Machine Learning system is a comprehensive machine learning solution that classifies breast tumors as Benign or Malignant using the Wisconsin Breast Cancer Dataset. This project is ideal for B.Tech, MCA, CSE, and engineering students as their final year project. It implements Decision Tree and Random Forest algorithms with GridSearchCV hyperparameter tuning, achieving 96.5% accuracy and 0.977 ROC-AUC.

The system utilizes the Wisconsin Breast Cancer Dataset comprising 569 samples with 30 numerical features derived from digitized FNA images of breast masses. Features include radius, texture, perimeter, area, smoothness, compactness, concavity, concave points, symmetry, and fractal dimension, with mean, standard error, and worst-case measurements for each characteristic. The system provides real-time diagnosis capabilities with confidence scores and feature importance analysis, supporting clinical decision-making in healthcare settings.

• Multi-Model Cancer Diagnosis
• Random Forest (96.5% Accuracy)
• Decision Tree (94.2% Accuracy)
• GridSearchCV Hyperparameter Tuning
• Feature Engineering & EDA
• Interactive Visualizations
• Real-time Cancer Predictions
• Model Performance Comparison
• Feature Importance Analysis
• Flask Web Application