Cover Image

Encrypted federated learning for secure decentralized collaboration in cancer image analysis

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 possib...

Full description

Saved in:
Bibliographic Details
Main Authors: Truhn, Daniel (Author) , Tayebi Arasteh, Soroosh (Author) , Saldanha, Oliver Lester (Author) , Müller-Franzes, Gustav (Author) , Khader, Firas (Author) , Quirke, Philip (Author) , West, Nicholas P. (Author) , Gray, Richard (Author) , Hutchins, Gordon G. A. (Author) , James, Jacqueline A. (Author) , Loughrey, Maurice B. (Author) , Salto-Tellez, Manuel (Author) , Brenner, Hermann (Author) , Brobeil, Alexander (Author) , Yuan, Tanwei (Author) , Chang-Claude, Jenny (Author) , Hoffmeister, Michael (Author) , Försch, Sebastian (Author) , Han, Tianyu (Author) , Keil, Sebastian (Author) , Schulze-Hagen, Maximilian (Author) , Isfort, Peter (Author) , Bruners, Philipp (Author) , Kaissis, Georgios (Author) , Kuhl, Christiane (Author) , Nebelung, Sven (Author) , Kather, Jakob Nikolas (Author)
Format: Article (Journal)
Language:English
Published: February 2024
In: Medical image analysis
Year: 2024, Volume: 92, Pages: 1-12
ISSN:1361-8423
DOI:10.1016/j.media.2023.103059
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.1016/j.media.2023.103059
Verlag, kostenfrei, Volltext: https://www.sciencedirect.com/science/article/pii/S1361841523003195
Get full text
Author Notes:Daniel Truhn, Soroosh Tayebi Arasteh, Oliver Lester Saldanha, Gustav Müller-Franzes, Firas Khader, Philip Quirke, Nicholas P. West, Richard Gray, Gordon G. A. Hutchins, Jacqueline A. James, Maurice B. Loughrey, Manuel Salto-Tellez, Hermann Brenner, Alexander Brobeil, Tanwei Yuan, Jenny Chang-Claude, Michael Hoffmeister, Sebastian Foersch, Tianyu Han, Sebastian Keil, Maximilian Schulze-Hagen, Peter Isfort, Philipp Bruners, Georgios Kaissis, Christiane Kuhl, Sven Nebelung, Jakob Nikolas Kather
Description
Summary: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.
Item Description:Online verfügbar: 7. Dezember 2023, Artikelversion: 16. Dezember 2023
Gesehen am 21.03.2024
Physical Description:Online Resource
ISSN:1361-8423
DOI:10.1016/j.media.2023.103059

Similar Items