Open AccessDigital image analysis in pathologist‐selected regions of interest predicts survival more accurately than whole‐slide analysis: a direct comparison study in 153 gastric carcinomas
Author(s) -
Heo You Jeong,
Lee Taebum,
Byeon SunJu,
Kim Eun Ji,
Shin Hyeong Chan,
Kim Binnari,
Kang So Young,
Ha Sang Yun,
Kim KyoungMee
Publication year - 2021
Publication title -
the journal of pathology: clinical research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.849
H-Index - 21
ISSN - 2056-4538
DOI - 10.1002/cjp2.179
Subject(s) - magnification , cd8 , medicine , pathology , digital image analysis , immunohistochemistry , digital pathology , antigen , immunology , artificial intelligence , computer science , computer vision
Automatic quantification of biomarkers such as tumor‐infiltrating lymphocytes and PD‐L1 is one of the most studied topics in digital pathology image analysis (DIA). However, direct comparison between the DIA of a whole‐slide image (WSI) and that of regions of interest (ROIs) chosen by pathologists has not been performed. In this study, we aimed to compare the prognostic value of tumor microenvironment markers CD8 and PD‐L1, measured by DIA of WSIs and ROIs. We selected 153 primary gastric cancer tissues and stained them with CD8 and PD‐L1. All IHC slides were scanned at ×200 magnification and ratios of CD8 and PD‐L1 were measured in WSIs and ROIs from the invasive front, within the tumor, and the mucosa. Patients with high CD8 and PD‐L1 ratios showed more favorable outcomes compared to those with low ratios. Pathologist‐aided DIA predicted the survival of patients more accurately than WSI analysis (CD8, p = 0.025 versus p = 0.068; PD‐L1, p = 0.008 versus p = 0.2). Although a high density of CD8+ T cells at the invasive front correlated best with patient survival, CD8 ratio in the mucosa could also predict patient outcome. In conclusion, CD8 and PD‐L1 ratios measured by pathologist‐aided DIA predicted survival more accurately than WSI analyses and ROIs at the invasive front correlated best with patient outcome.