Accounting for data variability in multi-institutional distributed deep learning for medical imaging
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Objectives: Sharing patient data across institutions to train generalizable deep learning models is challenging due to regulatory and technical hurdles. Distributed learning, where model weights are shared instead of patient data, presents an attractive alternative. Cyclical weight transfer (CWT) has recently been demonstrated as an effective distributed learning method for medical imaging with homogeneous data across institutions. In this study, we optimize CWT to overcome performance losses from variability in training sample sizes and label distributions across institutions. Materials and Methods: Optimizations included proportional local training iterations, cyclical learning rate, locally weighted minibatch sampling, and cyclically weighted loss. We evaluated our optimizations on simulated distributed diabetic retinopathy detection and chest radiograph classification. Results: Proportional local training iteration mitigated performance losses from sample size variability, achieving 98.6% of the accuracy attained by centrally hosting in the diabetic retinopathy dataset split with highest sample size variance across institutions. Locally weighted minibatch sampling and cyclically weighted loss both mitigated performance losses from label distribution variability, achieving 98.6% and 99.1%, respectively, of the accuracy attained by centrally hosting in the diabetic retinopathy dataset split with highest label distribution variability across institutions. Discussion: Our optimizations to CWT improve its capability of handling data variability across institutions. Compared to CWT without optimizations, CWT with optimizations achieved performance significantly closer to performance from centrally hosting. Conclusion: Our work is the first to identify and address challenges of sample size and label distribution variability in simulated distributed deep learning for medical imaging. Future work is needed to address other sources of real-world data variability.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations
Sudre, C. H., Li, W., Vercauteren, T., Ourselin, S., & Jorge Cardoso, M. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-67558-9_28 · Cited by 2,829
Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., & Oermann, E. K. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002683 · Cited by 1,719 · cited 1×
“Further, it has been shown that models trained at a single institution have limited generalizability when applied to data from other institutions.(8,9) Thus it is desirable for multiple institutions with patient data to collaborate to pool data to create larger, more diverse datasets.”
Setio, A. A. A., Ciompi, F., Litjens, G., Gerke, P., Jacobs, C., van Riel, S. J., Wille, M. M. W., Naqibullah, M., Sanchez, C. I., & van Ginneken, B. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2536809 · Cited by 1,258
Brown, J. M., Campbell, J. P., Beers, A., Chang, K., Ostmo, S., Chan, R. V. P., Dy, J., Erdogmus, D., Ioannidis, S., Kalpathy-Cramer, J., et al. (2018) · JAMA Ophthalmology · doi:10.1001/jamaophthalmol.2018.1934 · Cited by 657
Self-citationAddressing the class imbalance problem in medical datasets
Rahman, M. M., & Davis, D. N. (2013) · International Journal of Machine Learning and Computing · doi:10.7763/ijmlc.2013.v3.307 · Cited by 387
Langlotz, C. P., Allen, B., Erickson, B. J., Kalpathy-Cramer, J., Bigelow, K., Cook, T. S., Flanders, A. E., Lungren, M. P., Mendelson, D. S., Rudie, J. D., et al. (2019) · Radiology · doi:10.1148/radiol.2019190613 · Cited by 368 · cited 1×
“Indeed, distributed learning has been highlighted as a foundational area of research within medical imaging.(13) Recently, data-distributed deep learning methods have been successfully developed for training medical image classification models with a cyclical weight transfer (CWT) approach.”
Self-citationDistributed deep learning networks among institutions for medical imaging
Chang, K., Balachandar, N., Lam, C., Yi, D., Brown, J., Beers, A., Rosen, B., Rubin, D. L., & Kalpathy-Cramer, J. (2018) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocy017 · Cited by 340
Self-citationDeep learning for segmentation of brain tumors: Impact of cross‐institutional training and testing
AlBadawy, E. A., Saha, A., & Mazurowski, M. A. (2018) · Medical Physics · doi:10.1002/mp.12752 · Cited by 208
Cited by
Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications
Aledhari, M., Razzak, R., Parizi, R. M., & Saeed, F. (2020) · IEEE Access · doi:10.1109/access.2020.3013541 · Cited by 733
Deep learning for chest X-ray analysis: A survey
Çallı, E., Sogancioglu, E., van Ginneken, B., van Leeuwen, K. G., & Murphy, K. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102125 · Cited by 506
Federated learning improves site performance in multicenter deep learning without data sharing
Sarma, K. V., Harmon, S., Sanford, T., Roth, H. R., Xu, Z., Tetreault, J., Xu, D., Flores, M. G., Raman, A. G., Kulkarni, R., et al. (2021) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaa341 · Cited by 242
Federated Learning in Robotic and Autonomous Systems
Xianjia, Y., Queralta, J. P., Heikkonen, J., & Westerlund, T. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.07.041 · Cited by 79
“Additionally, other research e ff orts are directed towards utilizing distributed DL for processing and learning from sensitive data such as health data [23] or medical data from multiple private or public institutions [24].”
Shobayo, O., & Saatchi, R. (2025) · Diagnostics · doi:10.3390/diagnostics15091072 · Cited by 53
“Many general-purpose computers do not have the means of delivering the required computational resources, and there is also the issue of the environmental aspects of using so much electricity to perform the required deep learning training [44,45].”
Metadata
- Authors
- Balachandar, N., Chang, K., Kalpathy-Cramer, J., & Rubin, D. L.
- Venue
- Journal of the American Medical Informatics Association
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-03-20
- Volume
- 27
- Issue
- 5
- Pages
- 700-708
- ISSN
- 1067-5027 (ISSN-L)
- 1527-974X
- OpenAlex
- W3011726479
- Cited by
- 61
- References
- 9
- FWCI
- 3.60
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Accounting for data variability in multi-institutional distributed deep learning for medical imaging. https://app.cochat.ai/papers/10.1093/jamia/ocaa017
- The paper
- Balachandar, N., Chang, K., Kalpathy-Cramer, J., & Rubin, D. L. (2020). Accounting for data variability in multi-institutional distributed deep learning for medical imaging. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocaa017
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.