% 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{Truhn:286250,
author = {D. Truhn and S. Tayebi Arasteh and O. L. Saldanha and G.
Müller-Franzes and F. Khader and P. Quirke and N. P. West
and R. Gray and G. G. A. Hutchins and J. A. James and M. B.
Loughrey and M. Salto-Tellez and H. Brenner$^*$ and A.
Brobeil and T. Yuan$^*$ and J. Chang-Claude$^*$ and M.
Hoffmeister$^*$ and S. Foersch and T. Han and S. Keil and M.
Schulze-Hagen and P. Isfort and P. Bruners and G. Kaissis
and C. Kuhl and S. Nebelung and J. N. Kather},
title = {{E}ncrypted federated learning for secure decentralized
collaboration in cancer image analysis.},
journal = {Medical image analysis},
volume = {92},
issn = {1361-8415},
address = {Amsterdam [u.a.]},
publisher = {Elsevier Science},
reportid = {DKFZ-2023-02741},
pages = {103059},
year = {2023},
abstract = {Artificial intelligence (AI) has a multitude of
applications in cancer research and oncology. However, the
training of AI systems is impeded by the limited
availability of large datasets due to data protection
requirements and other regulatory obstacles. Federated and
swarm learning represent possible solutions to this problem
by collaboratively training AI models while avoiding data
transfer. However, in these decentralized methods, weight
updates are still transferred to the aggregation server for
merging the models. This leaves the possibility for a breach
of data privacy, for example by model inversion or
membership inference attacks by untrusted servers.
Somewhat-homomorphically-encrypted federated learning
(SHEFL) is a solution to this problem because only encrypted
weights are transferred, and model updates are performed in
the encrypted space. Here, we demonstrate the first
successful implementation of SHEFL in a range of clinically
relevant tasks in cancer image analysis on multicentric
datasets in radiology and histopathology. We show that SHEFL
enables the training of AI models which outperform locally
trained models and perform on par with models which are
centrally trained. In the future, SHEFL can enable multiple
institutions to co-train AI models without forsaking data
governance and without ever transmitting any decryptable
data to untrusted servers.},
keywords = {Artificial intelligence (Other) / Federated learning
(Other) / Histopathology (Other) / Homomorphic encryption
(Other) / Privacy-preserving deep learning (Other) /
Radiology (Other)},
cin = {C070 / C120 / HD01 / C020},
ddc = {610},
cid = {I:(DE-He78)C070-20160331 / I:(DE-He78)C120-20160331 /
I:(DE-He78)HD01-20160331 / 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:38104402},
doi = {10.1016/j.media.2023.103059},
url = {https://inrepo02.dkfz.de/record/286250},
}