Digital pathology analysis using deep learning has been the subject of several studies. As with other medical data, pathological data are not easily obtained. Because deep learning-based image analysis requires large amounts of data, augmentation techniques are used to increase the size of pathological datasets. This study proposes a novel method for synthesizing brain tumor pathology data using a generative model. For image synthesis, we used embedding features extracted from a segmentation module in a general generative model. We also introduce a simple solution for training a segmentation model in an environment in which the masked label of the training dataset is not supplied. As a result of this experiment, the proposed method did not make great progress in quantitative metrics but showed improved results in the confusion rate of more than 70 subjects and the quality of the visual output.
In digital pathology, pathological tissue images that are obtained using scanners are analyzed and diseases are diagnosed. One crucial aspect of this process is the staining of the tissue slides. However, differences appear in the staining color even when using the same staining protocol owing to various factors such as different facilities, hospitals, and scanning equipment. Many stain style normalization studies have been conducted to solve this problem. In this study, we propose a model named multi-domain single image reconstruction-based stain-style transfer. The proposed model is trained using a reconstruction-based learning framework, which can efficiently reduce the complexity and training time compared with that associated with the GAN objective. We randomly extracted stained tissue image patches from the CAME-LYON17 and Mitos-Atypia-14 datasets and demonstrated an effective stain-style translation. Our study reveals that it is possible to perform translation among multiple domains using a single training image per domain. Furthermore, we experimentally demonstrated that translation among color temperature domains was possible in the natural image domain. Our code is publicly available at: https://github.com/jwkweon/ MS-SST.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.