File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: SplitAVG: A Heterogeneity-Aware Federated Deep Learning Method for Medical Imaging

TitleSplitAVG: A Heterogeneity-Aware Federated Deep Learning Method for Medical Imaging
Authors
KeywordsBiomedical imaging
data heterogeneity
federated learning
Issue Date2022
Citation
IEEE Journal of Biomedical and Health Informatics, 2022, v. 26, n. 9, p. 4635-4644 How to Cite?
AbstractFederated learning is an emerging research paradigm for enabling collaboratively training deep learning models without sharing patient data. However, the data from different institutions are usually heterogeneous across institutions, which may reduce the performance of models trained using federated learning. In this study, we propose a novel heterogeneity-aware federated learning method, SplitAVG, to overcome the performance drops from data heterogeneity in federated learning. Unlike previous federated methods that require complex heuristic training or hyper parameter tuning, our SplitAVG leverages the simple network split and feature map concatenation strategies to encourage the federated model training an unbiased estimator of the target data distribution. We compare SplitAVG with seven state-of-the-art federated learning methods, using centrally hosted training data as the baseline on a suite of both synthetic and real-world federated datasets. We find that the performance of models trained using all the comparison federated learning methods degraded significantly with the increasing degrees of data heterogeneity. In contrast, SplitAVG method achieves comparable results to the baseline method under all heterogeneous settings, that it achieves 96.2% of the accuracy and 110.4% of the mean absolute error obtained by the baseline in a diabetic retinopathy binary classification dataset and a bone age prediction dataset, respectively, on highly heterogeneous data partitions. We conclude that SplitAVG method can effectively overcome the performance drops from variability in data distributions across institutions. Experimental results also show that SplitAVG can be adapted to different base convolutional neural networks (CNNs) and generalized to various types of medical imaging tasks.
Persistent Identifierhttp://hdl.handle.net/10722/325569
ISSN
2023 Impact Factor: 6.7
2023 SCImago Journal Rankings: 1.964
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, Miao-
dc.contributor.authorQu, Liangqiong-
dc.contributor.authorSingh, Praveer-
dc.contributor.authorKalpathy-Cramer, Jayashree-
dc.contributor.authorRubin, Daniel L.-
dc.date.accessioned2023-02-27T07:34:22Z-
dc.date.available2023-02-27T07:34:22Z-
dc.date.issued2022-
dc.identifier.citationIEEE Journal of Biomedical and Health Informatics, 2022, v. 26, n. 9, p. 4635-4644-
dc.identifier.issn2168-2194-
dc.identifier.urihttp://hdl.handle.net/10722/325569-
dc.description.abstractFederated learning is an emerging research paradigm for enabling collaboratively training deep learning models without sharing patient data. However, the data from different institutions are usually heterogeneous across institutions, which may reduce the performance of models trained using federated learning. In this study, we propose a novel heterogeneity-aware federated learning method, SplitAVG, to overcome the performance drops from data heterogeneity in federated learning. Unlike previous federated methods that require complex heuristic training or hyper parameter tuning, our SplitAVG leverages the simple network split and feature map concatenation strategies to encourage the federated model training an unbiased estimator of the target data distribution. We compare SplitAVG with seven state-of-the-art federated learning methods, using centrally hosted training data as the baseline on a suite of both synthetic and real-world federated datasets. We find that the performance of models trained using all the comparison federated learning methods degraded significantly with the increasing degrees of data heterogeneity. In contrast, SplitAVG method achieves comparable results to the baseline method under all heterogeneous settings, that it achieves 96.2% of the accuracy and 110.4% of the mean absolute error obtained by the baseline in a diabetic retinopathy binary classification dataset and a bone age prediction dataset, respectively, on highly heterogeneous data partitions. We conclude that SplitAVG method can effectively overcome the performance drops from variability in data distributions across institutions. Experimental results also show that SplitAVG can be adapted to different base convolutional neural networks (CNNs) and generalized to various types of medical imaging tasks.-
dc.languageeng-
dc.relation.ispartofIEEE Journal of Biomedical and Health Informatics-
dc.subjectBiomedical imaging-
dc.subjectdata heterogeneity-
dc.subjectfederated learning-
dc.titleSplitAVG: A Heterogeneity-Aware Federated Deep Learning Method for Medical Imaging-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/JBHI.2022.3185956-
dc.identifier.pmid35749336-
dc.identifier.scopuseid_2-s2.0-85133757699-
dc.identifier.volume26-
dc.identifier.issue9-
dc.identifier.spage4635-
dc.identifier.epage4644-
dc.identifier.eissn2168-2208-
dc.identifier.isiWOS:000852247000029-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats