Augmented Image Dataset Using Image-to-Image Translation to Enhance the Non-Hodgkin Lymphoma Diagnosis

Digital pathology involves the conversion of histology slides into digital format to generate high-resolution images.Tissue classification, particularly for identifying common types of non-Hodgkin lymphomas like mantle cell lymphoma, follicular lymphoma, and chronic lymphocytic leukemia, is a crucial application of this technology.Due to the complexity of these lymphomas, pathologists often encounter challenges in their diagnosis.However, the limited availability of image data in the dataset poses a significant challenge.To solve this issue, we present a new technique for augmenting the dataset and enabling more efficient model training.In this article, we propose a technique capable of approaching lymphoma images.Our idea is to generate lymphoma images by adding a segmented image.The reference images are taken from the available dataset.We use two re neural networks.The first neural network is image-to-image translation, a technique used to transform the appearance or style of images, particularly adversarial neural networks, facilitates this process by using inputs from the source domain to produce images that closely match the target domain.The second neural network, we use an improved convolutional neural network (CNN) algorithm for classifying non-Hodgkin lymphomas.Trained on this augmented dataset, the proposed model achieves a classification accuracy of 99.91%.This precision is higher than that reported by Khelil et al. in their study.Moreover, we acknowledge the ethical implications of generating synthetic medical images and propose guidelines for ensuring the ethical conduct of our proposed technique.