Classification of Malignant Lymphoma Types Using Convolutional Neural Network

Abstract

In this study, it is intended to increase the classification accuracy results of malignant lymphoma images by evaluating spatial relations. As a first step, convolutional neural network (CNN) based features are extracted in the original RGB color space of digital histopathalogical images. Classification models of each feature vectors are obtained by employing CNN, support vector machines (SVM) and random forest (RF) methods. For comparison purposes, the classification accuracy results obtained from supervised learning methods are presented in the experimental results section.