Klasifikasi Kanker Payudara menggunakan Metode Residual Network (Resnet) pada Citra Histopatologi

Breast cancer is the most common type of cancer suffered by women worldwide and is the leading cause of death. In 2020, there were approximately 2.3 million cases of breast cancer causing 685,000 deaths. In Indonesia, the World Health Organization's (WHO) Global Burden of Cancer Study (Globocan) report estimated a total of 396,914 cancer cases in the same year, with breast cancer accounting for 16.6% of all cancer cases. Various methods are used to identify cancer in medical imaging. For example, in the case of breast cancer, mammography, Ultrasound (US), Computed Tomography (CT), and Magnetic Resonance Imaging (MRI) are often used. Although these diagnostic approaches are frequently used, there is always room for improvement in terms of accuracy. To overcome this limitation, computer vision science has been used to detect diseases in medical images. Computer vision can help pathologists and histopathologists produce more accurate prognosis and faster identification by using advanced machine learning algorithms and techniques. This research aims to detect and classify histopathology images implementing deep learning using the ResNet50 method to diagnose breast cancer. The model used applies data augmentation and data balancing techniques using undersampling techniques. The dataset used in this research is the "Breast Cancer Histopathology Image Classification (BreakHis) dataset" with a total of 1,094 data divided into two classes, namely Benign and Malignant. Each model built will produce accuracy, precision, recall, and confusion matrix values. The results of this study are 69% accuracy, 79% precision, and 74% recall.