% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Saldanha:179696,
author = {O. L. Saldanha and P. Quirke and N. P. West and J. A. James
and M. B. Loughrey and H. I. Grabsch and M. Salto-Tellez and
E. Alwers$^*$ and D. Cifci and N. Ghaffari Laleh and T.
Seibel and R. Gray and G. G. A. Hutchins and H. Brenner$^*$
and M. van Treeck and T. Yuan$^*$ and T. J. Brinker$^*$ and
J. Chang-Claude$^*$ and F. Khader and A. Schuppert and T.
Luedde and C. Trautwein and H. S. Muti and S. Foersch and M.
Hoffmeister$^*$ and D. Truhn and J. N. Kather},
title = {{S}warm learning for decentralized artificial intelligence
in cancer histopathology.},
journal = {Nature medicine},
volume = {28},
number = {6},
issn = {1078-8956},
address = {New York, NY},
publisher = {Nature America Inc.},
reportid = {DKFZ-2022-00845},
pages = {1232-1239},
year = {2022},
note = {2022 Jun;28(6):1232-1239},
abstract = {Artificial intelligence (AI) can predict the presence of
molecular alterations directly from routine histopathology
slides. However, training robust AI systems requires large
datasets for which data collection faces practical, ethical
and legal obstacles. These obstacles could be overcome with
swarm learning (SL), in which partners jointly train AI
models while avoiding data transfer and monopolistic data
governance. Here, we demonstrate the successful use of SL in
large, multicentric datasets of gigapixel histopathology
images from over 5,000 patients. We show that AI models
trained using SL can predict BRAF mutational status and
microsatellite instability directly from hematoxylin and
eosin $(H\&E)-stained$ pathology slides of colorectal
cancer. We trained AI models on three patient cohorts from
Northern Ireland, Germany and the United States, and
validated the prediction performance in two independent
datasets from the United Kingdom. Our data show that
SL-trained AI models outperform most locally trained models,
and perform on par with models that are trained on the
merged datasets. In addition, we show that SL-based AI
models are data efficient. In the future, SL can be used to
train distributed AI models for any histopathology image
analysis task, eliminating the need for data transfer.},
cin = {C070 / C120 / HD01 / C140 / C020},
ddc = {610},
cid = {I:(DE-He78)C070-20160331 / I:(DE-He78)C120-20160331 /
I:(DE-He78)HD01-20160331 / I:(DE-He78)C140-20160331 /
I:(DE-He78)C020-20160331},
pnm = {313 - Krebsrisikofaktoren und Prävention (POF4-313)},
pid = {G:(DE-HGF)POF4-313},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:35469069},
doi = {10.1038/s41591-022-01768-5},
url = {https://inrepo02.dkfz.de/record/179696},
}