Federated learning for decentralized artificial intelligence in melanoma diagnostics
The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where c...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
February 7, 2024
|
| In: |
JAMA dermatology
Year: 2024, Jahrgang: 160, Heft: 3, Pages: 303-311 |
| ISSN: | 2168-6084 |
| DOI: | 10.1001/jamadermatol.2023.5550 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1001/jamadermatol.2023.5550
|
| Verfasserangaben: | Sarah Haggenmüller, MSc, Max Schmitt, MSc, Eva Krieghoff-Henning, PhD, Achim Hekler, MSc, Roman C. Maron, MSc, Christoph Wies, MSc, Jochen S. Utikal, MD, Friedegund Meier, MD, Sarah Hobelsberger, MD, Frank F. Gellrich, MD, Mildred Sergon, MD, Axel Hauschild, MD, Lars E. French, MD, Lucie Heinzerling, MD, Justin G. Schlager, MD, Kamran Ghoreschi, MD, Max Schlaak, MD, Franz J. Hilke, PhD, Gabriela Poch, MD, Sören Korsing, MD, Carola Berking, MD, Markus V. Heppt, MD, Michael Erdmann, MD, Sebastian Haferkamp, MD, Konstantin Drexler, MD, Dirk Schadendorf, MD, Wiebke Sondermann, MD, Matthias Goebeler, MD, Bastian Schilling, MD, Jakob N. Kather, MD, Stefan Fröhling, MD, Titus J. Brinker, MD |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1892399091 | ||
| 003 | DE-627 | ||
| 005 | 20241205144913.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240628s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1001/jamadermatol.2023.5550 |2 doi | |
| 035 | |a (DE-627)1892399091 | ||
| 035 | |a (DE-599)KXP1892399091 | ||
| 035 | |a (OCoLC)1475301003 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Haggenmüller, Sarah |d 1995- |e VerfasserIn |0 (DE-588)1231946709 |0 (DE-627)1755618042 |4 aut | |
| 245 | 1 | 0 | |a Federated learning for decentralized artificial intelligence in melanoma diagnostics |c Sarah Haggenmüller, MSc, Max Schmitt, MSc, Eva Krieghoff-Henning, PhD, Achim Hekler, MSc, Roman C. Maron, MSc, Christoph Wies, MSc, Jochen S. Utikal, MD, Friedegund Meier, MD, Sarah Hobelsberger, MD, Frank F. Gellrich, MD, Mildred Sergon, MD, Axel Hauschild, MD, Lars E. French, MD, Lucie Heinzerling, MD, Justin G. Schlager, MD, Kamran Ghoreschi, MD, Max Schlaak, MD, Franz J. Hilke, PhD, Gabriela Poch, MD, Sören Korsing, MD, Carola Berking, MD, Markus V. Heppt, MD, Michael Erdmann, MD, Sebastian Haferkamp, MD, Konstantin Drexler, MD, Dirk Schadendorf, MD, Wiebke Sondermann, MD, Matthias Goebeler, MD, Bastian Schilling, MD, Jakob N. Kather, MD, Stefan Fröhling, MD, Titus J. Brinker, MD |
| 264 | 1 | |c February 7, 2024 | |
| 300 | |b Illustrationen | ||
| 300 | |a 9 | ||
| 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 veröffentlicht: 7. Februar 2024 | ||
| 500 | |a Gesehen am 28.06.2024 | ||
| 520 | |a The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals.To investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics.This multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023.All whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care.The area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity.The study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479).The findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond. | ||
| 700 | 1 | |a Schmitt, Max |e VerfasserIn |4 aut | |
| 700 | 1 | |a Krieghoff-Henning, Eva |d 1976- |e VerfasserIn |0 (DE-588)132407914 |0 (DE-627)52267786X |0 (DE-576)299126706 |4 aut | |
| 700 | 1 | |a Hekler, Achim |e VerfasserIn |0 (DE-588)1196829314 |0 (DE-627)1678721344 |4 aut | |
| 700 | 1 | |a Maron, Roman C. |e VerfasserIn |0 (DE-588)1198959851 |0 (DE-627)1681173867 |4 aut | |
| 700 | 1 | |a Wies, Christoph |e VerfasserIn |0 (DE-588)1307730442 |0 (DE-627)1868667650 |4 aut | |
| 700 | 1 | |a Utikal, Jochen |d 1974- |e VerfasserIn |0 (DE-588)1026463750 |0 (DE-627)726765015 |0 (DE-576)371816580 |4 aut | |
| 700 | 1 | |a Meier, Friedegund |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hobelsberger, Sarah |e VerfasserIn |4 aut | |
| 700 | 1 | |a Gellrich, Frank F. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Sergon, Mildred |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hauschild, Axel |e VerfasserIn |0 (DE-588)120701200 |0 (DE-627)080838448 |0 (DE-576)292346670 |4 aut | |
| 700 | 1 | |a French, Lars E. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Heinzerling, Lucie |d 1969- |e VerfasserIn |0 (DE-588)124732755 |0 (DE-627)537985638 |0 (DE-576)29447224X |4 aut | |
| 700 | 1 | |a Schlager, Justin G. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Ghoreschi, Kamran |e VerfasserIn |4 aut | |
| 700 | 1 | |a Schlaak, Max |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hilke, Franz J. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Poch, Gabriela |e VerfasserIn |4 aut | |
| 700 | 1 | |a Korsing, Sören |e VerfasserIn |4 aut | |
| 700 | 1 | |a Berking, Carola |e VerfasserIn |4 aut | |
| 700 | 1 | |a Heppt, Markus V. |d 1987- |e VerfasserIn |0 (DE-588)1072242346 |0 (DE-627)827081111 |0 (DE-576)43371767X |4 aut | |
| 700 | 1 | |a Erdmann, Michael |e VerfasserIn |4 aut | |
| 700 | 1 | |a Haferkamp, Sebastian |e VerfasserIn |4 aut | |
| 700 | 1 | |a Drexler, Konstantin |e VerfasserIn |4 aut | |
| 700 | 1 | |a Schadendorf, Dirk |d 1960- |e VerfasserIn |0 (DE-588)11142576X |0 (DE-627)499566076 |0 (DE-576)289702275 |4 aut | |
| 700 | 1 | |a Sondermann, Wiebke |e VerfasserIn |4 aut | |
| 700 | 1 | |a Goebeler, Matthias |e VerfasserIn |4 aut | |
| 700 | 1 | |a Schilling, Bastian |e VerfasserIn |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 | |
| 700 | 1 | |a Fröhling, Stefan |d 1969- |e VerfasserIn |0 (DE-588)120890046 |0 (DE-627)080950302 |0 (DE-576)188733930 |4 aut | |
| 700 | 1 | |a Brinker, Titus Josef |d 1990- |e VerfasserIn |0 (DE-588)1156309395 |0 (DE-627)1018860487 |0 (DE-576)502097434 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t JAMA dermatology |d Chicago, Ill. : American Medical Association, 2013 |g 160(2024), 3, Seite 303-311 |h Online-Ressource |w (DE-627)736006052 |w (DE-600)2701763-1 |w (DE-576)378725068 |x 2168-6084 |7 nnas |a Federated learning for decentralized artificial intelligence in melanoma diagnostics |
| 773 | 1 | 8 | |g volume:160 |g year:2024 |g number:3 |g pages:303-311 |g extent:9 |a Federated learning for decentralized artificial intelligence in melanoma diagnostics |
| 856 | 4 | 0 | |u https://doi.org/10.1001/jamadermatol.2023.5550 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20240628 | ||
| 993 | |a Article | ||
| 994 | |a 2024 | ||
| 998 | |g 1156309395 |a Brinker, Titus Josef |m 1156309395:Brinker, Titus Josef |d 50000 |e 50000PB1156309395 |k 0/50000/ |p 32 |y j | ||
| 998 | |g 120890046 |a Fröhling, Stefan |m 120890046:Fröhling, Stefan |d 50000 |e 50000PF120890046 |k 0/50000/ |p 31 | ||
| 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 30 | ||
| 998 | |g 11142576X |a Schadendorf, Dirk |m 11142576X:Schadendorf, Dirk |d 50000 |e 50000PS11142576X |k 0/50000/ |p 26 | ||
| 998 | |g 1026463750 |a Utikal, Jochen |m 1026463750:Utikal, Jochen |d 60000 |e 60000PU1026463750 |k 0/60000/ |p 7 | ||
| 998 | |g 1307730442 |a Wies, Christoph |m 1307730442:Wies, Christoph |d 50000 |e 50000PW1307730442 |k 0/50000/ |p 6 | ||
| 998 | |g 1231946709 |a Haggenmüller, Sarah |m 1231946709:Haggenmüller, Sarah |d 60000 |e 60000PH1231946709 |k 0/60000/ |p 1 |x j | ||
| 999 | |a KXP-PPN1892399091 |e 454300549X | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"id":{"doi":["10.1001/jamadermatol.2023.5550"],"eki":["1892399091"]},"recId":"1892399091","relHost":[{"note":["Gesehen am 12.10.17"],"pubHistory":["149.2013 -"],"origin":[{"dateIssuedKey":"2013","publisher":"American Medical Association","dateIssuedDisp":"2013-","publisherPlace":"Chicago, Ill."}],"title":[{"title":"JAMA dermatology","title_sort":"JAMA dermatology"}],"disp":"Federated learning for decentralized artificial intelligence in melanoma diagnosticsJAMA dermatology","type":{"media":"Online-Ressource","bibl":"periodical"},"recId":"736006052","physDesc":[{"extent":"Online-Ressource"}],"id":{"eki":["736006052"],"zdb":["2701763-1"],"issn":["2168-6084"]},"corporate":[{"role":"isb","display":"American Medical Association"}],"language":["eng"],"part":{"year":"2024","pages":"303-311","issue":"3","text":"160(2024), 3, Seite 303-311","volume":"160","extent":"9"}}],"physDesc":[{"extent":"9 S.","noteIll":"Illustrationen"}],"name":{"displayForm":["Sarah Haggenmüller, MSc, Max Schmitt, MSc, Eva Krieghoff-Henning, PhD, Achim Hekler, MSc, Roman C. Maron, MSc, Christoph Wies, MSc, Jochen S. Utikal, MD, Friedegund Meier, MD, Sarah Hobelsberger, MD, Frank F. Gellrich, MD, Mildred Sergon, MD, Axel Hauschild, MD, Lars E. French, MD, Lucie Heinzerling, MD, Justin G. Schlager, MD, Kamran Ghoreschi, MD, Max Schlaak, MD, Franz J. Hilke, PhD, Gabriela Poch, MD, Sören Korsing, MD, Carola Berking, MD, Markus V. Heppt, MD, Michael Erdmann, MD, Sebastian Haferkamp, MD, Konstantin Drexler, MD, Dirk Schadendorf, MD, Wiebke Sondermann, MD, Matthias Goebeler, MD, Bastian Schilling, MD, Jakob N. Kather, MD, Stefan Fröhling, MD, Titus J. Brinker, MD"]},"type":{"media":"Online-Ressource","bibl":"article-journal"},"title":[{"title_sort":"Federated learning for decentralized artificial intelligence in melanoma diagnostics","title":"Federated learning for decentralized artificial intelligence in melanoma diagnostics"}],"note":["Online veröffentlicht: 7. Februar 2024","Gesehen am 28.06.2024"],"origin":[{"dateIssuedDisp":"February 7, 2024","dateIssuedKey":"2024"}],"language":["eng"],"person":[{"display":"Haggenmüller, Sarah","family":"Haggenmüller","given":"Sarah","role":"aut"},{"role":"aut","given":"Max","family":"Schmitt","display":"Schmitt, Max"},{"display":"Krieghoff-Henning, Eva","family":"Krieghoff-Henning","role":"aut","given":"Eva"},{"given":"Achim","role":"aut","family":"Hekler","display":"Hekler, Achim"},{"display":"Maron, Roman C.","family":"Maron","given":"Roman C.","role":"aut"},{"display":"Wies, Christoph","family":"Wies","role":"aut","given":"Christoph"},{"given":"Jochen","role":"aut","family":"Utikal","display":"Utikal, Jochen"},{"role":"aut","given":"Friedegund","display":"Meier, Friedegund","family":"Meier"},{"role":"aut","given":"Sarah","family":"Hobelsberger","display":"Hobelsberger, Sarah"},{"role":"aut","given":"Frank F.","family":"Gellrich","display":"Gellrich, Frank F."},{"role":"aut","given":"Mildred","family":"Sergon","display":"Sergon, Mildred"},{"given":"Axel","role":"aut","family":"Hauschild","display":"Hauschild, Axel"},{"given":"Lars E.","role":"aut","display":"French, Lars E.","family":"French"},{"family":"Heinzerling","display":"Heinzerling, Lucie","role":"aut","given":"Lucie"},{"given":"Justin G.","role":"aut","family":"Schlager","display":"Schlager, Justin G."},{"given":"Kamran","role":"aut","family":"Ghoreschi","display":"Ghoreschi, Kamran"},{"display":"Schlaak, Max","family":"Schlaak","given":"Max","role":"aut"},{"family":"Hilke","display":"Hilke, Franz J.","role":"aut","given":"Franz J."},{"given":"Gabriela","role":"aut","display":"Poch, Gabriela","family":"Poch"},{"display":"Korsing, Sören","family":"Korsing","role":"aut","given":"Sören"},{"given":"Carola","role":"aut","display":"Berking, Carola","family":"Berking"},{"family":"Heppt","display":"Heppt, Markus V.","role":"aut","given":"Markus V."},{"display":"Erdmann, Michael","family":"Erdmann","given":"Michael","role":"aut"},{"given":"Sebastian","role":"aut","family":"Haferkamp","display":"Haferkamp, Sebastian"},{"family":"Drexler","display":"Drexler, Konstantin","role":"aut","given":"Konstantin"},{"family":"Schadendorf","display":"Schadendorf, Dirk","given":"Dirk","role":"aut"},{"given":"Wiebke","role":"aut","family":"Sondermann","display":"Sondermann, Wiebke"},{"family":"Goebeler","display":"Goebeler, Matthias","given":"Matthias","role":"aut"},{"family":"Schilling","display":"Schilling, Bastian","role":"aut","given":"Bastian"},{"role":"aut","given":"Jakob Nikolas","family":"Kather","display":"Kather, Jakob Nikolas"},{"family":"Fröhling","display":"Fröhling, Stefan","given":"Stefan","role":"aut"},{"display":"Brinker, Titus Josef","family":"Brinker","role":"aut","given":"Titus Josef"}]} | ||
| SRT | |a HAGGENMUELFEDERATEDL7202 | ||