| |  Online-Ressource |
|---|
| Verfasst von: | Truhn, Daniel [VerfasserIn]  |
|---|
| | Tayebi Arasteh, Soroosh [VerfasserIn] |
|---|
| | Saldanha, Oliver Lester [VerfasserIn] |
|---|
| | Müller-Franzes, Gustav [VerfasserIn] |
|---|
| | Khader, Firas [VerfasserIn] |
|---|
| | Quirke, Philip [VerfasserIn] |
|---|
| | West, Nicholas P. [VerfasserIn] |
|---|
| | Gray, Richard [VerfasserIn] |
|---|
| | Hutchins, Gordon G. A. [VerfasserIn] |
|---|
| | James, Jacqueline A. [VerfasserIn] |
|---|
| | Loughrey, Maurice B. [VerfasserIn] |
|---|
| | Salto-Tellez, Manuel [VerfasserIn] |
|---|
| | Brenner, Hermann [VerfasserIn] |
|---|
| | Brobeil, Alexander [VerfasserIn] |
|---|
| | Yuan, Tanwei [VerfasserIn] |
|---|
| | Chang-Claude, Jenny [VerfasserIn] |
|---|
| | Hoffmeister, Michael [VerfasserIn] |
|---|
| | Försch, Sebastian [VerfasserIn] |
|---|
| | Han, Tianyu [VerfasserIn] |
|---|
| | Keil, Sebastian [VerfasserIn] |
|---|
| | Schulze-Hagen, Maximilian [VerfasserIn] |
|---|
| | Isfort, Peter [VerfasserIn] |
|---|
| | Bruners, Philipp [VerfasserIn] |
|---|
| | Kaissis, Georgios [VerfasserIn] |
|---|
| | Kuhl, Christiane [VerfasserIn] |
|---|
| | Nebelung, Sven [VerfasserIn] |
|---|
| | Kather, Jakob Nikolas [VerfasserIn] |
|---|
| Titel: | Encrypted federated learning for secure decentralized collaboration in cancer image analysis |
|---|
| Verf.angabe: | 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 |
|---|
| E-Jahr: | 2024 |
|---|
| Jahr: | February 2024 |
|---|
| Umfang: | 12 S. |
|---|
| Illustrationen: | Illustrationen |
|---|
| Fussnoten: | Online verfügbar: 7. Dezember 2023, Artikelversion: 16. Dezember 2023 ; Gesehen am 21.03.2024 |
|---|
| Titel Quelle: | Enthalten in: Medical image analysis |
|---|
| Ort Quelle: | Amsterdam [u.a.] : Elsevier Science, 1996 |
|---|
| Jahr Quelle: | 2024 |
|---|
| Band/Heft Quelle: | 92(2024) vom: Feb., Artikel-ID 103059, Seite 1-12 |
|---|
| ISSN Quelle: | 1361-8423 |
|---|
| 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. |
|---|
| DOI: | doi:10.1016/j.media.2023.103059 |
|---|
| URL: | Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.
kostenfrei: Volltext: https://doi.org/10.1016/j.media.2023.103059 |
|---|
| | kostenfrei: Volltext: https://www.sciencedirect.com/science/article/pii/S1361841523003195 |
|---|
| | DOI: https://doi.org/10.1016/j.media.2023.103059 |
|---|
| Datenträger: | Online-Ressource |
|---|
| Sprache: | eng |
|---|
| Sach-SW: | Artificial intelligence |
|---|
| | Federated learning |
|---|
| | Histopathology |
|---|
| | Homomorphic encryption |
|---|
| | Privacy-preserving deep learning |
|---|
| | Radiology |
|---|
| K10plus-PPN: | 1883995167 |
|---|
| Verknüpfungen: | → Zeitschrift |
|---|
Encrypted federated learning for secure decentralized collaboration in cancer image analysis / Truhn, Daniel [VerfasserIn]; February 2024 (Online-Ressource)
