Basic Study
Copyright ©The Author(s) 2020. Published by Baishideng Publishing Group Inc. All rights reserved.
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
Processing time: 108 Days and 10.4 Hours
Abstract
BACKGROUND

Digital pathology image (DPI) analysis has been developed by machine learning (ML) techniques. However, little attention has been paid to the reproducibility of ML-based histological classification in heterochronously obtained DPIs of the same hematoxylin and eosin (HE) slide.

AIM

To elucidate the frequency and preventable causes of discordant classification results of DPI analysis using ML for the heterochronously obtained DPIs.

METHODS

We created paired DPIs by scanning 298 HE stained slides containing 584 tissues twice with a virtual slide scanner. The paired DPIs were analyzed by our ML-aided classification model. We defined non-flipped and flipped groups as the paired DPIs with concordant and discordant classification results, respectively. We compared differences in color and blur between the non-flipped and flipped groups by L1-norm and a blur index, respectively.

RESULTS

We observed discordant classification results in 23.1% of the paired DPIs obtained by two independent scans of the same microscope slide. We detected 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.

CONCLUSION

Our results suggest that differences in the blur - not the color - of the paired DPIs may cause discordant classification results. 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.

Keywords: Machine learning; Digital pathology image; Automated image analysis; Blur; Color; Reproducibility

Core tip: Little attention has been paid to the reproducibility of machine learning (ML)-based histological classification in heterochronously obtained Digital pathology images (DPIs) of the same hematoxylin and eosin slide. This study elucidated the frequency and preventable causes of discordant classification results of DPI analysis using ML for the heterochronously obtained DPIs. We observed discordant classification results in 23.1% of the paired DPIs obtained by two independent scans of the same microscope slide. The group with discordant classification results showed a significantly higher blur index than the other group. Our results suggest that differences in the blur of the paired DPIs may cause discordant classification results.