Breast Cancer Detection using Deep Learning

Breast cancer is a leading cause of morbidity for women all over the world, BC, or breast cancer, affects many women globally. It ranks fourth in fatality among colon, brain, and cervical malignancies. New BC cases are predicted to rise 70% in the following two decades. Thus, early identification and accurate breast cancer diagnosis improve prognosis and long-term survival. Machine learning methods like "Support Vector Machines" (SVM) and Nearest Neighbor have shown promising but limited efficacy in recognizing BC. This study introduced a "Convolutional Neural Network" (CNN) model of utilizing deep neural networks to diagnose BC using the Wisconsin BC database. The research demonstrates the application of DL technology for diagnosing BC using the Kaggle Dataset. The research method involves data acquisition, data preprocessing and using the dataset to train the CNN model and assess its performance using four key metrics: precision, recall, accuracy, and F-measure. CNN model accuracy is 95.57%, precision is 97.70%, recall is 98.64%, and F-measure is 98.14%. This approach outperforms standard models, proving its effectiveness in detecting BC.