Dataset Information

Digital image analysis in pathologist-selected regions of interest predicts survival more accurately than whole-slide analysis: a direct comparison study in 153 gastric carcinomas.

ABSTRACT: 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.

SUBMITTER: Heo YJ

PROVIDER: S-EPMC7737754 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Digital image analysis in pathologist-selected regions of interest predicts survival more accurately than whole-slide analysis: a direct comparison study in 153 gastric carcinomas.

Heo You Jeong YJ Lee Taebum T Byeon Sun-Ju SJ Kim Eun Ji EJ Shin Hyeong Chan HC Kim Binnari B Kang So Young SY Ha Sang Yun SY Kim Kyoung-Mee KM

The journal of pathology. Clinical research 20200904 1

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 ...[more]

PMID: 32885920

Similar Datasets

Project description:For a method to be widely adopted in medical research or clinical practice, it needs to be reproducible so that clinicians and regulators can have confidence in its use. Machine learning and deep learning have a particular set of challenges around reproducibility. Small differences in the settings or the data used for training a model can lead to large differences in the outcomes of experiments. In this work, three top-performing algorithms from the Camelyon grand challenges are reproduced using only information presented in the associated papers and the results are then compared to those reported. Seemingly minor details were found to be critical to performance and yet their importance is difficult to appreciate until the actual reproduction is attempted. We observed that authors generally describe the key technical aspects of their models well but fail to maintain the same reporting standards when it comes to data preprocessing which is essential to reproducibility. As an important contribution of the present study and its findings, we introduce a reproducibility checklist that tabulates information that needs to be reported in histopathology ML-based work in order to make it reproducible. Author summary For a method to be used a lot in medical research or clinical practice, it needs to be able to be reproduced so that people can trust it. Machine learning and deep learning have some challenges around this. For example, small changes in how a model is trained can lead to significant changes in the results of experiments. This makes it essential that researchers report how they do things in enough detail for the results of their experiments to be reproducible. In this work, we looked at three different algorithms used for digital pathology image analysis. We tried to reproduce them using only the information reported in their papers. We confirmed that even minor details could be essential. Authors often do not report all the details needed to reproduce their work. We also created a checklist of things that need to be reported to help other researchers make their work reproducible.

Dataset Information

Digital image analysis in pathologist-selected regions of interest predicts survival more accurately than whole-slide analysis: a direct comparison study in 153 gastric carcinomas.

Publications

Digital image analysis in pathologist-selected regions of interest predicts survival more accurately than whole-slide analysis: a direct comparison study in 153 gastric carcinomas.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets