Indexed in SCIE, Scopus, PubMed & PMC
pISSN 1226-4512 eISSN 2093-3827


home Article View

Original Article

Korean J Physiol Pharmacol 2020; 24(1): 89-99

Published online January 1, 2020

Copyright © Korean J Physiol Pharmacol.

Feasibility of fully automated classification of whole slide images based on deep learning

Kyung-Ok Cho1,2,3, Sung Hak Lee4,*, and Hyun-Jong Jang2,3,5,*

1Department of Pharmacology, 2Department of Biomedicine & Health Sciences, 3Catholic Neuroscience Institute, 4Department of Hospital Pathology, Seoul St. Mary's Hospital, 5Department of Physiology, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea

Correspondence to:*Sung Hak Lee
*Hyun-Jong Jang

Received: September 23, 2019; Revised: November 25, 2019; Accepted: November 27, 2019

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Although microscopic analysis of tissue slides has been the basis for disease diagnosis for decades, intra- and inter-observer variabilities remain issues to be resolved. The recent introduction of digital scanners has allowed for using deep learning in the analysis of tissue images because many whole slide images (WSIs) are accessible to researchers. In the present study, we investigated the possibility of a deep learning-based, fully automated, computer-aided diagnosis system with WSIs from a stomach adenocarcinoma dataset. Three different convolutional neural network architectures were tested to determine the better architecture for tissue classifier. Each network was trained to classify small tissue patches into normal or tumor. Based on the patch-level classification, tumor probability heatmaps can be overlaid on tissue images. We observed three different tissue patterns, including clear normal, clear tumor and ambiguous cases. We suggest that longer inspection time can be assigned to ambiguous cases compared to clear normal cases, increasing the accuracy and efficiency of histopathologic diagnosis by pre-evaluating the status of the WSIs. When the classifier was tested with completely different WSI dataset, the performance was not optimal because of the different tissue preparation quality. By including a small amount of data from the new dataset for training, the performance for the new dataset was much enhanced. These results indicated that WSI dataset should include tissues prepared from many different preparation conditions to construct a generalized tissue classifier. Thus, multi-national/multi-center dataset should be built for the application of deep learning in the real world medical practice.

Keywords: Computational pathology, Computer-aided diagnosis, Convolutional neural network, Digital pathology