Joint Imaging Platform for Federated Clinical Data Analytics-Reference-Cited by-同舟云学术

Joint Imaging Platform for Federated Clinical Data Analytics

Published:2020-11 Issue:4 Volume: Page:1027-1038
ISSN:2473-4276
Container-title:JCO Clinical Cancer Informatics
language:en
Short-container-title:JCO Clinical Cancer Informatics

Author:

Scherer Jonas¹²^ORCID,Nolden Marco¹²³^ORCID,Kleesiek Jens²⁴⁵,Metzger Jasmin¹²,Kades Klaus¹²,Schneider Verena²⁴,Bach Michael²⁴,Sedlaczek Oliver²⁴⁶,Bucher Andreas M.²⁷^ORCID,Vogl Thomas J.²⁷,Grünwald Frank²⁸,Kühn Jens-Peter²⁹^ORCID,Hoffmann Ralf-Thorsten²⁹^ORCID,Kotzerke Jörg²¹⁰,Bethge Oliver²¹¹,Schimmöller Lars²¹¹^ORCID,Antoch Gerald²¹¹,Müller Hans-Wilhelm²¹²,Daul Andreas²¹³,Nikolaou Konstantin²¹³,la Fougère Christian²¹⁴^ORCID,Kunz Wolfgang G.²¹⁵,Ingrisch Michael²¹⁵^ORCID,Schachtner Balthasar²¹⁵¹⁶^ORCID,Ricke Jens²¹⁵,Bartenstein Peter²¹⁷,Nensa Felix²¹⁸,Radbruch Alexander²¹⁸,Umutlu Lale²¹⁸,Forsting Michael²¹⁸,Seifert Robert²¹⁹^ORCID,Herrmann Ken²¹⁹^ORCID,Mayer Philipp²⁶^ORCID,Kauczor Hans-Ulrich²⁶¹⁶,Penzkofer Tobias²²⁰^ORCID,Hamm Bernd²²⁰,Brenner Winfried²²¹,Kloeckner Roman²²²^ORCID,Düber Christoph²²²,Schreckenberger Mathias²²³,Braren Rickmer²²⁴,Kaissis Georgios²³²⁴²⁵^ORCID,Makowski Marcus²²⁴,Eiber Matthias²²⁶,Gafita Andrei²²⁶,Trager Rupert²²⁶,Weber Wolfgang A.²²⁶,Neubauer Jakob²²⁷,Reisert Marco²²⁷,Bock Michael²²⁷^ORCID,Bamberg Fabian²²⁷,Hennig Jürgen²²⁷^ORCID,Meyer Philipp Tobias²²⁸,Ruf Juri²²⁸,Haberkorn Uwe²²⁹,Schoenberg Stefan O.²³⁰,Kuder Tristan²³¹^ORCID,Neher Peter¹²^ORCID,Floca Ralf¹²³^ORCID,Schlemmer Heinz-Peter³²²⁴,Maier-Hein Klaus¹³^ORCID

Affiliation:

1. Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany

2. German Cancer Consortium, Heidelberg, Germany

3. Pattern Analysis and Learning Group, Radio-oncology and Clinical Radiotherapy, Heidelberg University Hospital, Heidelberg, Germany

4. Division of Radiology, German Cancer Research Center, Heidelberg, Germany

5. Institut für Künstliche Intelligenz in der Medizin, Universitätsklinikum Essen, Essen, Germany

6. Klinik Diagnostische und Interventionelle Radiologie der Universität Heidelberg, Heidelberg, Germany

7. Institut für Diagnostische und Interventionelle Radiologie, Universitätsklinikum Frankfurt, Frankfurt, Germany

8. Klinik für Nuklearmedizin, Universitätsklinikum Frankfurt, Frankfurt, Germany

9. Institut und Poliklinik für Diagnostische und Interventionelle Radiologie, Universitätsklinikum Carl Gustav Carus Dresden, Dresden, Germany

10. Klinik und Poliklinik für Nuklearmedizin, Universitätsklinikum Carl Gustav Carus Dresden, Dresden, Germany

11. Medical Faculty, Department of Diagnostic and Interventional Radiology, University Düsseldorf, Düsseldorf, Germany

12. Klinik für Nuklearmedizin, Universitätsklinikum Düsseldorf, Düsseldorf, Germany

13. Klinik für Diagnostische und Interventionelle Radiologie, Universitätsklinikum Tübingen, Tübingen, Germany

14. Klinik für Nuklearmedizin und Klinische Molekulare Bildgebung, Universitätsklinikum Tübingen, Tübingen, Germany

15. Department of Radiology, University Hospital, Ludwig Maximilian University Munich, Munich, Germany

16. German Center of Lung Research, Heidelberg, Germany

17. Klinik und Poliklinik für Nuklearmedizin, Klinikum der Universität München, München, Germany

18. Institut für Diagnostische und Interventionelle Radiologie und Neuroradiologie, Universitätsklinikum Essen, Essen, Germany

19. Klinik für Nuklearmedizin, Universitätsklinikum Essen, Essen, Germany

20. Klinik für Radiologie (mit dem Bereich Kinderradiologie), Charité Universitätsmedizin Berlin, Berlin, Germany

21. Klinik für Nuklearmedizin, Charité–Universitätsmedizin Berlin, Berlin, Germany

22. Klinik und Poliklinik für Diagnostische und Interventionelle Radiologie, Universitätsmedizin Mainz, Mainz, Germany

23. Klinik und Poliklinik für Nuklearmedizin, Universitätsmedizin Mainz, Mainz, Germany

24. Institut für Diagnostische und Interventionelle Radiologie, Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany

25. Department of Computing, Imperial College London, London, United Kingdom

26. Klinik und Poliklinik für Nuklearmedizin, Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany

27. Department of Diagnostic and Interventional Radiology, Medical Center–University of Freiburg, University of Freiburg, Freiburg, Germany

28. Klinik für Nuklearmedizin, Universitätsklinikum Freiburg, Freiburg, Germany

29. Klinische Kooperationseinheit Nuklearmedizin, Deutsches Krebsforschungszentrum Heidelberg, Heidelberg, Germany

30. Universitätsmedizin Mannheim, Medizinische Fakultät Mannheim der Universität Heidelberg, Heidelberg, Germany

31. Medizinische Physik in der Radiologie, Deutsches Krebsforschungszentrum Heidelberg, Heidelberg, Germany

32. Medical Faculty Heidelberg, University of Heidelberg, Heidelberg, Germany

Abstract

PURPOSE Image analysis is one of the most promising applications of artificial intelligence (AI) in health care, potentially improving prediction, diagnosis, and treatment of diseases. Although scientific advances in this area critically depend on the accessibility of large-volume and high-quality data, sharing data between institutions faces various ethical and legal constraints as well as organizational and technical obstacles. METHODS The Joint Imaging Platform (JIP) of the German Cancer Consortium (DKTK) addresses these issues by providing federated data analysis technology in a secure and compliant way. Using the JIP, medical image data remain in the originator institutions, but analysis and AI algorithms are shared and jointly used. Common standards and interfaces to local systems ensure permanent data sovereignty of participating institutions. RESULTS The JIP is established in the radiology and nuclear medicine departments of 10 university hospitals in Germany (DKTK partner sites). In multiple complementary use cases, we show that the platform fulfills all relevant requirements to serve as a foundation for multicenter medical imaging trials and research on large cohorts, including the harmonization and integration of data, interactive analysis, automatic analysis, federated machine learning, and extensibility and maintenance processes, which are elementary for the sustainability of such a platform. CONCLUSION The results demonstrate the feasibility of using the JIP as a federated data analytics platform in heterogeneous clinical information technology and software landscapes, solving an important bottleneck for the application of AI to large-scale clinical imaging data.

Publisher

American Society of Clinical Oncology (ASCO)

Subject

General Medicine

Link

https://ascopubs.org/doi/pdfdirect/10.1200/CCI.20.00045

Reference39 articles.

1. Image-based biomarkers for solid tumor quantification

2. Machine Learning methods for Quantitative Radiomic Biomarkers

3. Dynamic Risk Profiling Using Serial Tumor Biomarkers for Personalized Outcome Prediction

4. Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study

5. The Potential of Radiomic-Based Phenotyping in Precision Medicine

Cited by 46 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. AI-derived body composition parameters as prognostic factors in patients with HCC undergoing TACE in a multicenter study;JHEP Reports;2024-08

2. Value of MRI - T2 Mapping to Differentiate Clinically Significant Prostate Cancer;Journal of Imaging Informatics in Medicine;2024-06-26

3. Secure and Privacy-Preserving Federated Learning With Explainable Artificial Intelligence for Smart Healthcare Systems;Advances in Healthcare Information Systems and Administration;2024-04-19

4. Federated learning for prostate cancer detection in biparametric MRI: optimization of rounds, epochs, and aggregation strategy;Medical Imaging 2024: Computer-Aided Diagnosis;2024-04-03

5. Body composition analysis by radiological imaging – methods, applications, and prospects;RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren;2024-04-03