Pathologic Image Classification of Flat Urothelial Lesions Using Pathologic Criteria-Based Deep Learning. Issue 6 (5th October 2022)

• Record Type: Journal Article
• Authors: Nishikawa, Toui; Iwamoto, Ryuta; Matsuzaki, Ibu; Musangile, Fidele Yambayamba; Takahashi, Ayata; Mikasa, Yurina; Takahashi, Yuichi; Kojima, Fumiyoshi; Murata, Shin-ichi
• Is Part Of: American journal of clinical pathology. Volume 158:Issue 6(2022)
• Page Start: 759
• Page End: 769
• Publication Date: 2022-10-05
• Subjects: Deep learning -- Genitourinary pathology -- Pathologic criteria -- Flat urothelial lesion -- Reliability; Diagnosis, Laboratory -- Periodicals; Pathology -- Periodicals; 616.07
• DOI: 10.1093/ajcp/aqac117
• Languages: English
• ISSNs: 0002-9173

Abstract

Abstract: Objectives: Pathologic diagnosis of flat urothelial lesions is subject to high interobserver variability. We expected that deep learning could improve the accuracy and consistency of such pathologic diagnosis, although the learning process is a black box. We therefore propose a new approach for pathologic image classification incorporating the diagnostic process of the pathologist into a deep learning method. Methods: A total of 267 H&E-stained slides of normal urothelium and urothelial lesions from 127 cases were examined. Six independent convolutional neural networks were trained to classify pathologic images according to six pathologic criteria. We then used these networks in the main training for the final diagnosis. Results: Compared with conventional manual analysis, our method significantly improved the classification accuracy of images of flat urothelial lesions. The automated classification showed almost perfect agreement (weighted κ = 0.98) with the consensus reading. In addition, our approach provides the advantages of reliable diagnosis corresponding to histologic interpretation. Conclusions: We used deep learning to establish an automated subtype classifier for flat urothelial lesions that successfully combines traditional morphologic approaches and complex deep learning to achieve a learning mechanism that seems plausible to the pathologist.