Histopathological breast cancer image classification with feature prioritization using a heuristic algorithm

Breast cancer (BC) is one of the most common and most dangerous cancers found in women. A few methods are used for its diagnosis; among them, the biopsy is a very effective method for investigating cancer. In a biopsy, tissue is taken from the breast and observed under a microscope by an experienced histologist. This manual detection is time-consuming and may lead to human error. Hence, computer-aided diagnosis is used to investigate histopathological images. A few computer-aided diagnosis (CAD) methods are available for the investigation of histopathological images. In this work, we describe the extraction of global and local features from images using convolutional neural networks (CNNs) and the use of histograms to classify breast cancer images. In addition, a heuristic algorithm is used to extract a smaller number of effective features with which to classify breast cancer images using an ensemble of random forest (RF) classifiers. Using the ensemble classifier, we obtained an accuracy of 91.92% and a precision of 96.90% by processing the BreakHis dataset.