Deteksi Otomatis Citra Histopathologi Kanker Payudara Menggunakan Convolutional Neural Network

Breast cancer is the most common cancer in women, the main cause of death throughout the world and inflict 685,000 deaths in 2020. With advances in deep learning methods, it can improve the accuracy of diagnosing cancer in medical image with computer vision science. This research aims methods to classify breast cancer histopathology images to detecting or diagnosing breast tumors with applying Convolutional Neural Network (CNN). This model undergoes data balancing and augmentation techniques applied to undersampling techniques. The dataset used for this research was "The BreaKHis Database of microscopic biopsy images of breast tumors (benign and malignant)". Data will be divided into two categories: Malignant and Benign with total of 1693 data. The results of this study are 93% recall, 93% precision, and 94% accuracy. To conclude, Convolutional Neural Network method is recommended to diagnose and detecting breast cancer.