Abstract
Federated Learning (FL) is a novel technique that allows for performing the training of a global model without sharing data between entities. This research focused on the analysis of existing solutions for Federated Learning in the context of medical image classification. Selected frameworks: TensorFlow Federated, PySyft and Flower were tested and their usability was assessed. Additionally, experiments on classification of X-ray lung images with the use of the Flower framework were performed in a fully distributed setting using Google Cloud Platform.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Covid-19 radiography database. https://www.kaggle.com/tawsifurrahman/covid19-radiography-database
GRPC: A high performance, open source universal RPC framework. https://grpc.io/
Tensorflow federated. https://www.tensorflow.org/federated
Beutel, D.J., et al.: Flower: a friendly federated learning research framework (2021)
Dou, Q., et al.: Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study. NPJ Digit. Med. 4(1), 60 (2021). https://doi.org/10.1038/s41746-021-00431-6, http://www.nature.com/articles/s41746-021-00431-6
Kaissis, G.A., Makowski, M.R., Rückert, D., Braren, R.F.: Secure, privacy-preserving and federated machine learning in medical imaging. Nat. Mach. Intell. 2(6), 305–311 (2020)
Liu, B., Yan, B., Zhou, Y., Yang, Y., Zhang, Y.: Experiments of federated learning for COVID-19 chest X-ray images (2020)
McMahan, H.B., Moore, E., Ramage, D., Hampson, S.: y Arcas. Communication-efficient learning of deep networks from decentralized data, B.A. (2017)
Ryffel, T., et al.: A generic framework for privacy preserving deep learning. CoRR abs/1811.04017 (2018). http://arxiv.org/abs/1811.04017
Sarma, K.V., et al.: Federated learning improves site performance in multicenter deep learning without data sharing. J. Am. Med. Inform. Assoc. 28(6), 1259-1264 (2021). https://doi.org/10.1093/jamia/ocaa341, https://academic.oup.com/jamia/advance-article/doi/10.1093/jamia/ocaa341/6127556
Sheller, M.J., et al.: Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Sci. Rep. 10(1), 1–12 (2020)
Silva, S., Altmann, A., Gutman, B., Lorenzi, M.: Fed-biomed: a general open-source frontend framework for federated learning in healthcare. In: Albarqouni, S., et al. (eds.) Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning, pp. 201–210. Springer International Publishing, Cham (2020). https://doi.org/10.1007/978-3-030-60548-3_20
Acknowledgments
This publication is partly supported by the EU H2020 grant “Sano” No 857533, and by the project “Sano” carried out within the International Research Agendas Programme of the Foundation for Polish Science, co-financed by the European Regional Development Fund.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Jabłecki, P., Ślazyk, F., Malawski, M. (2021). Federated Learning in the Cloud for Analysis of Medical Images - Experience with Open Source Frameworks. In: Oyarzun Laura, C., et al. Clinical Image-Based Procedures, Distributed and Collaborative Learning, Artificial Intelligence for Combating COVID-19 and Secure and Privacy-Preserving Machine Learning. DCL PPML LL-COVID19 CLIP 2021 2021 2021 2021. Lecture Notes in Computer Science(), vol 12969. Springer, Cham. https://doi.org/10.1007/978-3-030-90874-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-90874-4_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90873-7
Online ISBN: 978-3-030-90874-4
eBook Packages: Computer ScienceComputer Science (R0)
