Universität zu Köln

Flinner, Nadine, Gretser, Steffen, Quaas, Alexander, Bankov, Katrin ORCID: 0009-0005-4033-4966, Stoll, Alexander, Heckmann, Lara E., Mayer, Robin S., Doering, Claudia ORCID: 0000-0002-3727-8773, Demes, Melanie C., Buettner, Reinhard, Rueschoff, Josef and Wild, Peter J. (2022). Deep learning based on hematoxylin-eosin staining outperforms immunohistochemistry in predicting molecular subtypes of gastric adenocarcinoma. J. Pathol., 257 (2). S. 218 - 227. HOBOKEN: WILEY. ISSN 1096-9896

Full text not available from this repository.

Abstract

In gastric cancer (GC), there are four molecular subclasses that indicate whether patients respond to chemotherapy or immunotherapy, according to the TCGA. In clinical practice, however, not every patient undergoes molecular testing. Many laboratories have used well-implemented in situ techniques (IHC and EBER-ISH) to determine the subclasses in their cohorts. Although multiple stains are used, we show that a staining approach is unable to correctly discriminate all subclasses. As an alternative, we trained an ensemble convolutional neuronal network using bagging that can predict the molecular subclass directly from hematoxylin-eosin histology. We also identified patients with predicted intra-tumoral heterogeneity or with features from multiple subclasses, which challenges the postulated TCGA-based decision tree for GC subtyping. In the future, deep learning may enable targeted testing for molecular subtypes and targeted therapy for a broader group of GC patients. (c) 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Flinner, Nadine UNSPECIFIED UNSPECIFIED UNSPECIFIED Gretser, Steffen UNSPECIFIED UNSPECIFIED UNSPECIFIED Quaas, Alexander UNSPECIFIED UNSPECIFIED UNSPECIFIED Bankov, Katrin UNSPECIFIED orcid.org/0009-0005-4033-4966 UNSPECIFIED Stoll, Alexander UNSPECIFIED UNSPECIFIED UNSPECIFIED Heckmann, Lara E. UNSPECIFIED UNSPECIFIED UNSPECIFIED Mayer, Robin S. UNSPECIFIED UNSPECIFIED UNSPECIFIED Doering, Claudia UNSPECIFIED orcid.org/0000-0002-3727-8773 UNSPECIFIED Demes, Melanie C. UNSPECIFIED UNSPECIFIED UNSPECIFIED Buettner, Reinhard UNSPECIFIED UNSPECIFIED UNSPECIFIED Rueschoff, Josef UNSPECIFIED UNSPECIFIED UNSPECIFIED Wild, Peter J. UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-683568
DOI:	10.1002/path.5879
Journal or Publication Title:	J. Pathol.
Volume:	257
Number:	2
Page Range:	S. 218 - 227
Date:	2022
Publisher:	WILEY
Place of Publication:	HOBOKEN
ISSN:	1096-9896
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language EXPRESSION-BASED CLASSIFICATION; INTRATUMORAL HETEROGENEITY; MICROSATELLITE INSTABILITY; CANCER; PROTEIN; DIFFUSE Multiple languages Oncology; Pathology Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/68356