Ogura M, Kiyuna T, Yoshida H. Impact of blurs on machine-learning aided digital pathology image analysis. Artif Intell Cancer 2020; 1(1): 31-38 [DOI: 10.35713/aic.v1.i1.31]
Corresponding Author of This Article
Hiroshi Yoshida, MD, PhD, Staff Physician, Department of Diagnostic Pathology, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, Japan. hiroyosh@ncc.go.jp
Research Domain of This Article
Pathology
Article-Type of This Article
Basic Study
Open-Access Policy of This Article
This article is an open-access article which was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/
Artif Intell Cancer. Jun 28, 2020; 1(1): 31-38 Published online Jun 28, 2020. doi: 10.35713/aic.v1.i1.31
Impact of blurs on machine-learning aided digital pathology image analysis
Maki Ogura, Tomoharu Kiyuna, Hiroshi Yoshida
Maki Ogura, Tomoharu Kiyuna, Digital Healthcare Business Development Office, NEC Corporation, Tokyo 108-8001, Japan
Hiroshi Yoshida, Department of Diagnostic Pathology, National Cancer Center Hospital, Tokyo 104-0045, Japan
Author contributions: Ogura M, Kiyuna T, and Yoshida H drafted and revised the manuscript and prepared the figures; Ogura M collected the pathological data; Kiyuna T performed all the image analysis; all the authors have read and approved the final manuscript.
Institutional review board statement: The study was conducted in accordance with the Declaration of Helsinki and with the approval of the Institutional Review Board of the National Cancer Center, Tokyo, Japan.
Conflict-of-interest statement: All authors have no competing interests to be declared.
Data sharing statement: No additional data are available.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/
Corresponding author: Hiroshi Yoshida, MD, PhD, Staff Physician, Department of Diagnostic Pathology, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, Japan. hiroyosh@ncc.go.jp
Received: March 21, 2020 Peer-review started: March 21, 2020 First decision: April 22, 2020 Revised: May 2, 2020 Accepted: June 7, 2020 Article in press: June 7, 2020 Published online: June 28, 2020
ARTICLE HIGHLIGHTS
Research background
Little attention has been paid to the frequency and preventable causes of discordant classification results of digital pathological image (DPI) analysis using machine learning (ML) for the heterochronously obtained DPIs.
Research motivation
Authors compared the classification results between paired DPIs of the same microscope slide obtained from two independent scans using the same slide scanner.
Research objectives
In this study, the authors elucidated the frequency and preventable causes of discordant classification results of DPI analysis using ML for the heterochronously obtained DPIs.
Research methods
Authors created paired DPIs by scanning 298 hematoxylin and eosin stained slides containing 584 tissues twice with a virtual slide scanner. The paired DPIs were analyzed by our ML-aided classification model. Differences in color and blur between the non-flipped and flipped groups were compared by L1-norm and a blur index.
Research results
Discordant classification results in 23.1% of the paired DPIs obtained by two independent scans of the same microscope slide were observed. No significant difference in the L1-norm of each color channel between the two groups; however, the flipped group showed a significantly higher blur index than the non-flipped group.
Research conclusions
The results suggest that differences in the blur - not the color - of the paired DPIs may cause discordant classification results.
Research perspectives
An ML-aided classification model for DPI should be tested for this potential cause of the reduced reproducibility of the model. In a future study, a slide scanner and/or a preprocessing method of minimizing DPI blur should be developed.
