A Prospective Validation and Observer Performance Study of a Deep Learning Algorithm for Pathologic Diagnosis of Gastric Tumors in Endoscopic Biopsies.

Abstract

PURPOSE:

Gastric cancer remains the leading cause of cancer-related deaths in Northeast Asia. Population-based endoscopic screenings in the region have yielded successful results in early detection of gastric tumors. Endoscopic screening rates are continuously increasing, and there is a need for an automatic computerized diagnostic system to reduce the diagnostic burden. In this study, we developed an algorithm to classify gastric epithelial tumors automatically and assessed its performance in a large series of gastric biopsies and its benefits as an assistance tool.

EXPERIMENTAL DESIGN:

Using 2,434 whole-slide images, we developed an algorithm based on convolutional neural networks to classify a gastric biopsy image into one of three categories: negative for dysplasia (NFD), tubular adenoma, or carcinoma. The performance of the algorithm was evaluated by using 7,440 biopsy specimens collected prospectively. The impact of algorithm-assisted diagnosis was assessed by six pathologists using 150 gastric biopsy cases.

RESULTS:

Diagnostic performance evaluated by the AUROC curve in the prospective study was 0.9790 for two-tier classification: negative (NFD) versus positive (all cases except NFD). When limited to epithelial tumors, the sensitivity and specificity were 1.000 and 0.9749. Algorithm-assisted digital image viewer (DV) resulted in 47% reduction in review time per image compared with DV only and 58% decrease to microscopy.

CONCLUSIONS:

Our algorithm has demonstrated high accuracy in classifying epithelial tumors and its benefits as an assistance tool, which can serve as a potential screening aid system in diagnosing gastric biopsy specimens.

• Authors: Jeonghyuk Park, Bo Gun Jang, Yeong Won Kim, Hyunho Park, Baek-Hui Kim, Myeung Ju Kim, Hyungsuk Ko, Jae Moon Gwak, Eun Ji Lee, Yul Ri Chung, Kyungdoc Kim, Jae Kyung Myung, Jeong Hwan Park, Dong Youl Choi, Chang Won Jung, Bong-Hee Park, Kyu-Hwan Jung, Dong-Il Kim
• Journal: Clinical cancer research : an official journal of the American Association for Cancer Research (Clin Cancer Res) Vol. 27 Issue 3 Pg. 719-728 (02 01 2021) ISSN: 1557-3265 [Electronic] United States
• PMID: 33172897 (Publication Type: Journal Article, Research Support, Non-U.S. Gov't, Validation Study)
• Copyright: ©2020 American Association for Cancer Research.

Topics

• Adult
• Aged
• Aged, 80 and over
• Biopsy (statistics & numerical data)
• Deep Learning
• Feasibility Studies
• Female
• Gastric Mucosa (diagnostic imaging, pathology)
• Gastroscopy (statistics & numerical data)
• Humans
• Image Interpretation, Computer-Assisted (methods, statistics & numerical data)
• Male
• Middle Aged
• Observer Variation
• Pathologists (statistics & numerical data)
• Prospective Studies
• Retrospective Studies
• Sensitivity and Specificity
• Stomach Neoplasms (diagnosis, pathology)