TY  - JOUR
A1  - Flinner, Nadine
A1  - Gretser, Steffen
A1  - Quaas, Alexander
A1  - Bankov, Katrin
A1  - Stoll, Alexander
A1  - Heckmann, Lara E.
A1  - Mayer, Robin S.
A1  - Döring, Claudia
A1  - Demes, Melanie Christin
A1  - Büttner, Reinhard
A1  - Rüschoff, Josef
A1  - Wild, Peter Johannes
T1  - Deep learning based on hematoxylin–eosin staining outperforms immunohistochemistry in predicting molecular subtypes of gastric adenocarcinoma
T2  - The journal of pathology
N2  - 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. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
KW  - stomach neoplasms
KW  - deep learning
KW  - molecular typing
KW  - molecular diagnostic techniques
KW  - histology
KW  - computational pathology
KW  - ensemble cNN
Y1  - 2022
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/75428
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30:3-754281
SN  - 1096-9896
VL  - 257
IS  - 2
SP  - 218
EP  - 226
PB  - Wiley
CY  - Bognor Regis [u.a.]
ER  -