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...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
February 2024
|
| In: |
Medical image analysis
Year: 2024, Jahrgang: 92, Pages: 1-12 |
| ISSN: | 1361-8423 |
| DOI: | 10.1016/j.media.2023.103059 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1016/j.media.2023.103059 Verlag, kostenfrei, Volltext: https://www.sciencedirect.com/science/article/pii/S1361841523003195 
|
| Verfasserangaben: | 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 |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1883995167 | ||
| 003 | DE-627 | ||
| 005 | 20240703155347.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240321s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.media.2023.103059 |2 doi | |
| 035 | |a (DE-627)1883995167 | ||
| 035 | |a (DE-599)KXP1883995167 | ||
| 035 | |a (OCoLC)1443657644 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Truhn, Daniel |e VerfasserIn |0 (DE-588)1047348306 |0 (DE-627)778145913 |0 (DE-576)400927314 |4 aut | |
| 245 | 1 | 0 | |a Encrypted federated learning for secure decentralized collaboration in cancer image analysis |c 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 |
| 264 | 1 | |c February 2024 | |
| 300 | |b Illustrationen | ||
| 300 | |a 12 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Online verfügbar: 7. Dezember 2023, Artikelversion: 16. Dezember 2023 | ||
| 500 | |a Gesehen am 21.03.2024 | ||
| 520 | |a 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. | ||
| 650 | 4 | |a Artificial intelligence | |
| 650 | 4 | |a Federated learning | |
| 650 | 4 | |a Histopathology | |
| 650 | 4 | |a Homomorphic encryption | |
| 650 | 4 | |a Privacy-preserving deep learning | |
| 650 | 4 | |a Radiology | |
| 700 | 1 | |a Tayebi Arasteh, Soroosh |e VerfasserIn |0 (DE-588)1298471109 |0 (DE-627)1854454927 |4 aut | |
| 700 | 1 | |a Saldanha, Oliver Lester |d 1995- |e VerfasserIn |0 (DE-588)1308996705 |0 (DE-627)1869542878 |4 aut | |
| 700 | 1 | |a Müller-Franzes, Gustav |e VerfasserIn |4 aut | |
| 700 | 1 | |a Khader, Firas |d 1996- |e VerfasserIn |0 (DE-588)1298294681 |0 (DE-627)1854342223 |4 aut | |
| 700 | 1 | |a Quirke, Philip |e VerfasserIn |4 aut | |
| 700 | 1 | |a West, Nicholas P. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Gray, Richard |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hutchins, Gordon G. A. |e VerfasserIn |4 aut | |
| 700 | 1 | |a James, Jacqueline A. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Loughrey, Maurice B. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Salto-Tellez, Manuel |e VerfasserIn |0 (DE-588)173879993 |0 (DE-627)698781597 |0 (DE-576)134718429 |4 aut | |
| 700 | 1 | |a Brenner, Hermann |e VerfasserIn |0 (DE-588)1020516445 |0 (DE-627)691247005 |0 (DE-576)360642136 |4 aut | |
| 700 | 1 | |a Brobeil, Alexander |e VerfasserIn |0 (DE-588)108137795X |0 (DE-627)846032406 |0 (DE-576)454349661 |4 aut | |
| 700 | 1 | |a Yuan, Tanwei |d 1995- |e VerfasserIn |0 (DE-588)1299871909 |0 (DE-627)1857588649 |4 aut | |
| 700 | 1 | |a Chang-Claude, Jenny |e VerfasserIn |0 (DE-588)1049304993 |0 (DE-627)781626188 |0 (DE-576)168344475 |4 aut | |
| 700 | 1 | |a Hoffmeister, Michael |d 1973- |e VerfasserIn |0 (DE-588)134103726 |0 (DE-627)560880820 |0 (DE-576)277089565 |4 aut | |
| 700 | 1 | |a Försch, Sebastian |d 1985- |e VerfasserIn |0 (DE-588)1018553894 |0 (DE-627)682860832 |0 (DE-576)356024814 |4 aut | |
| 700 | 1 | |a Han, Tianyu |e VerfasserIn |0 (DE-588)1278510001 |0 (DE-627)1831430037 |4 aut | |
| 700 | 1 | |a Keil, Sebastian |d 1976- |e VerfasserIn |0 (DE-588)131734091 |0 (DE-627)513320873 |0 (DE-576)298706156 |4 aut | |
| 700 | 1 | |a Schulze-Hagen, Maximilian |d 1987- |e VerfasserIn |0 (DE-588)1051963516 |0 (DE-627)78721311X |0 (DE-576)407624155 |4 aut | |
| 700 | 1 | |a Isfort, Peter |d 1979- |e VerfasserIn |0 (DE-588)133907465 |0 (DE-627)557960983 |0 (DE-576)278359914 |4 aut | |
| 700 | 1 | |a Bruners, Philipp |d 1979- |e VerfasserIn |0 (DE-588)133025411 |0 (DE-627)530939320 |0 (DE-576)299573060 |4 aut | |
| 700 | 1 | |a Kaissis, Georgios |e VerfasserIn |0 (DE-588)1229551581 |0 (DE-627)1751629317 |4 aut | |
| 700 | 1 | |a Kuhl, Christiane |d 1966- |e VerfasserIn |0 (DE-588)1082384011 |0 (DE-627)847427994 |0 (DE-576)455377782 |4 aut | |
| 700 | 1 | |a Nebelung, Sven |d 1986- |e VerfasserIn |0 (DE-588)1029969981 |0 (DE-627)734545851 |0 (DE-576)377792241 |4 aut | |
| 700 | 1 | |a Kather, Jakob Nikolas |d 1989- |e VerfasserIn |0 (DE-588)1064064914 |0 (DE-627)812897587 |0 (DE-576)423589091 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medical image analysis |d Amsterdam [u.a.] : Elsevier Science, 1996 |g 92(2024) vom: Feb., Artikel-ID 103059, Seite 1-12 |h Online-Ressource |w (DE-627)306365081 |w (DE-600)1497450-2 |w (DE-576)091204941 |x 1361-8423 |7 nnas |a Encrypted federated learning for secure decentralized collaboration in cancer image analysis |
| 773 | 1 | 8 | |g volume:92 |g year:2024 |g month:02 |g elocationid:103059 |g pages:1-12 |g extent:12 |a Encrypted federated learning for secure decentralized collaboration in cancer image analysis |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.media.2023.103059 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://www.sciencedirect.com/science/article/pii/S1361841523003195 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20240321 | ||
| 993 | |a Article | ||
| 994 | |a 2024 | ||
| 998 | |g 1064064914 |a Kather, Jakob Nikolas |m 1064064914:Kather, Jakob Nikolas |d 910000 |d 910100 |e 910000PK1064064914 |e 910100PK1064064914 |k 0/910000/ |k 1/910000/910100/ |p 27 |y j | ||
| 998 | |g 134103726 |a Hoffmeister, Michael |m 134103726:Hoffmeister, Michael |d 50000 |e 50000PH134103726 |k 0/50000/ |p 17 | ||
| 998 | |g 1049304993 |a Chang-Claude, Jenny |m 1049304993:Chang-Claude, Jenny |d 50000 |e 50000PC1049304993 |k 0/50000/ |p 16 | ||
| 998 | |g 1299871909 |a Yuan, Tanwei |m 1299871909:Yuan, Tanwei |d 50000 |e 50000PY1299871909 |k 0/50000/ |p 15 | ||
| 998 | |g 108137795X |a Brobeil, Alexander |m 108137795X:Brobeil, Alexander |d 910000 |d 912000 |e 910000PB108137795X |e 912000PB108137795X |k 0/910000/ |k 1/910000/912000/ |p 14 | ||
| 998 | |g 1020516445 |a Brenner, Hermann |m 1020516445:Brenner, Hermann |d 850000 |d 851600 |d 50000 |e 850000PB1020516445 |e 851600PB1020516445 |e 50000PB1020516445 |k 0/850000/ |k 1/850000/851600/ |k 0/50000/ |p 13 | ||
| 999 | |a KXP-PPN1883995167 |e 4502671258 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"language":["eng"],"person":[{"display":"Truhn, Daniel","family":"Truhn","role":"aut","given":"Daniel"},{"display":"Tayebi Arasteh, Soroosh","family":"Tayebi Arasteh","given":"Soroosh","role":"aut"},{"display":"Saldanha, Oliver Lester","family":"Saldanha","role":"aut","given":"Oliver Lester"},{"role":"aut","given":"Gustav","display":"Müller-Franzes, Gustav","family":"Müller-Franzes"},{"family":"Khader","display":"Khader, Firas","given":"Firas","role":"aut"},{"role":"aut","given":"Philip","family":"Quirke","display":"Quirke, Philip"},{"family":"West","display":"West, Nicholas P.","role":"aut","given":"Nicholas P."},{"family":"Gray","display":"Gray, Richard","given":"Richard","role":"aut"},{"given":"Gordon G. A.","role":"aut","display":"Hutchins, Gordon G. A.","family":"Hutchins"},{"display":"James, Jacqueline A.","family":"James","given":"Jacqueline A.","role":"aut"},{"given":"Maurice B.","role":"aut","display":"Loughrey, Maurice B.","family":"Loughrey"},{"given":"Manuel","role":"aut","family":"Salto-Tellez","display":"Salto-Tellez, Manuel"},{"display":"Brenner, Hermann","family":"Brenner","given":"Hermann","role":"aut"},{"display":"Brobeil, Alexander","family":"Brobeil","given":"Alexander","role":"aut"},{"role":"aut","given":"Tanwei","family":"Yuan","display":"Yuan, Tanwei"},{"family":"Chang-Claude","display":"Chang-Claude, Jenny","given":"Jenny","role":"aut"},{"family":"Hoffmeister","display":"Hoffmeister, Michael","given":"Michael","role":"aut"},{"role":"aut","given":"Sebastian","family":"Försch","display":"Försch, Sebastian"},{"family":"Han","display":"Han, Tianyu","given":"Tianyu","role":"aut"},{"role":"aut","given":"Sebastian","family":"Keil","display":"Keil, Sebastian"},{"family":"Schulze-Hagen","display":"Schulze-Hagen, Maximilian","role":"aut","given":"Maximilian"},{"family":"Isfort","display":"Isfort, Peter","role":"aut","given":"Peter"},{"display":"Bruners, Philipp","family":"Bruners","given":"Philipp","role":"aut"},{"role":"aut","given":"Georgios","display":"Kaissis, Georgios","family":"Kaissis"},{"role":"aut","given":"Christiane","display":"Kuhl, Christiane","family":"Kuhl"},{"display":"Nebelung, Sven","family":"Nebelung","given":"Sven","role":"aut"},{"role":"aut","given":"Jakob Nikolas","display":"Kather, Jakob Nikolas","family":"Kather"}],"id":{"doi":["10.1016/j.media.2023.103059"],"eki":["1883995167"]},"recId":"1883995167","relHost":[{"note":["Gesehen am 16.05.23"],"origin":[{"publisherPlace":"Amsterdam [u.a.]","dateIssuedKey":"1996","publisher":"Elsevier Science","dateIssuedDisp":"1996-"}],"pubHistory":["1.1996/97 -"],"title":[{"title_sort":"Medical image analysis","title":"Medical image analysis"}],"disp":"Encrypted federated learning for secure decentralized collaboration in cancer image analysisMedical image analysis","type":{"media":"Online-Ressource","bibl":"periodical"},"physDesc":[{"extent":"Online-Ressource"}],"recId":"306365081","id":{"eki":["306365081"],"issn":["1361-8423"],"zdb":["1497450-2"]},"language":["eng"],"titleAlt":[{"title":"Medical image analysis online"}],"part":{"text":"92(2024) vom: Feb., Artikel-ID 103059, Seite 1-12","extent":"12","volume":"92","pages":"1-12","year":"2024"}}],"physDesc":[{"noteIll":"Illustrationen","extent":"12 S."}],"name":{"displayForm":["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"]},"type":{"bibl":"article-journal","media":"Online-Ressource"},"title":[{"title_sort":"Encrypted federated learning for secure decentralized collaboration in cancer image analysis","title":"Encrypted federated learning for secure decentralized collaboration in cancer image analysis"}],"origin":[{"dateIssuedDisp":"February 2024","dateIssuedKey":"2024"}],"note":["Online verfügbar: 7. Dezember 2023, Artikelversion: 16. Dezember 2023","Gesehen am 21.03.2024"]} | ||
| SRT | |a TRUHNDANIEENCRYPTEDF2024 | ||