Stacked Convolutional Autoencoder (SCAE) for Breast Cancer Classification
Haryoko, Erni Seniwati, Theopilus Bayu Sasongko, Achmad Lukman, Faris Abid Gunawan · 2023
Breast cancer is still one of the deadliest diseases in the world, according to a WHO report. Early detection of tissue of breast cancer is needed in order to we can do early treatment so that the patient can recover. Other researchers have conducted research on Breast cancer by generating datasets for others who can implement some research by developing methods or techniques that are efficiently based on artificial intelligence to address the problem of breast cancer. We propose an approach method that implements a stacked convolutional autoencoder to classify these images with small architecture so that our proposed method can run faster during the training and testing process. We also compare our method with state-of-the-art methods based on convolutional neural networks (CNN) with complex architecture and vary. Dataset breast cancer available at https://web.inf.ufpr.br/vri/databases/breastcancer-histopathological-database-breakhis/. This dataset consists of microscope magnification images of breast tissue of several kinds, 40x, 100x, 200x, and 400x, and is divided into two classes: benign and malignant.