Universität zu Köln

Schoemig-Markiefka, Birgid, Pryalukhin, Alexey, Hulla, Wolfgang, Bychkov, Andrey ORCID: 0000-0002-4203-5696, Fukuoka, Junya, Madabhushi, Anant, Achter, Viktor, Nieroda, Lech, Buettner, Reinhard, Quaas, Alexander and Tolkach, Yuri (2021). Quality control stress test for deep learning-based diagnostic model in digital pathology. Mod. Pathol., 34 (12). S. 2098 - 2109. LONDON: SPRINGERNATURE. ISSN 1530-0285

Full text not available from this repository.

Abstract

Digital pathology provides a possibility for computational analysis of histological slides and automatization of routine pathological tasks. Histological slides are very heterogeneous concerning staining, sections' thickness, and artifacts arising during tissue processing, cutting, staining, and digitization. In this study, we digitally reproduce major types of artifacts. Using six datasets from four different institutions digitized by different scanner systems, we systematically explore artifacts' influence on the accuracy of the pre-trained, validated, deep learning-based model for prostate cancer detection in histological slides. We provide evidence that any histological artifact dependent on severity can lead to a substantial loss in model performance. Strategies for the prevention of diagnostic model accuracy losses in the context of artifacts are warranted. Stress-testing of diagnostic models using synthetically generated artifacts might be an essential step during clinical validation of deep learning-based algorithms.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Schoemig-Markiefka, Birgid UNSPECIFIED UNSPECIFIED UNSPECIFIED Pryalukhin, Alexey UNSPECIFIED UNSPECIFIED UNSPECIFIED Hulla, Wolfgang UNSPECIFIED UNSPECIFIED UNSPECIFIED Bychkov, Andrey UNSPECIFIED orcid.org/0000-0002-4203-5696 UNSPECIFIED Fukuoka, Junya UNSPECIFIED UNSPECIFIED UNSPECIFIED Madabhushi, Anant UNSPECIFIED UNSPECIFIED UNSPECIFIED Achter, Viktor UNSPECIFIED UNSPECIFIED UNSPECIFIED Nieroda, Lech UNSPECIFIED UNSPECIFIED UNSPECIFIED Buettner, Reinhard UNSPECIFIED UNSPECIFIED UNSPECIFIED Quaas, Alexander UNSPECIFIED UNSPECIFIED UNSPECIFIED Tolkach, Yuri UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-595163
DOI:	10.1038/s41379-021-00859-x
Journal or Publication Title:	Mod. Pathol.
Volume:	34
Number:	12
Page Range:	S. 2098 - 2109
Date:	2021
Publisher:	SPRINGERNATURE
Place of Publication:	LONDON
ISSN:	1530-0285
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language PROSTATE-CANCER; SHARPNESS ASSESSMENT; QUANTIFICATION; NORMALIZATION; BIOPSIES Multiple languages Pathology Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/59516