Distributed deep learning networks among institutions for medical imaging
Top Cited Papers
Open Access
- 1 August 2018
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 25 (8), 945-954
- https://doi.org/10.1093/jamia/ocy017
Abstract
Objective: Deep learning has become a promising approach for automated support for clinical diagnosis. When medical data samples are limited, collaboration among multiple institutions is necessary to achieve high algorithm performance. However, sharing patient data often has limitations due to technical, legal, or ethical concerns. In this study, we propose methods of distributing deep learning models as an attractive alternative to sharing patient data. Methods: We simulate the distribution of deep learning models across 4 institutions using various training heuristics and compare the results with a deep learning model trained on centrally hosted patient data. The training heuristics investigated include ensembling single institution models, single weight transfer, and cyclical weight transfer. We evaluated these approaches for image classification in 3 independent image collections (retinal fundus photos, mammography, and ImageNet). Results: We find that cyclical weight transfer resulted in a performance that was comparable to that of centrally hosted patient data. We also found that there is an improvement in the performance of cyclical weight transfer heuristic with a high frequency of weight transfer. Conclusions: We show that distributing deep learning models is an effective alternative to sharing patient data. This finding has implications for any collaborative deep learning study.Keywords
Funding Information
- National Institutes of Health Blueprint for Neuroscience Research (T90DA022759/R90DA023427)
- NIH
- National Institute of Biomedical Imaging and Bioengineering
- National Institutes of Health
- National Institutes of Health (U01CA154601, U24CA180927, U24CA180918, U01CA190214, U01CA187947)
This publication has 14 references indexed in Scilit:
- Multi-center machine learning in imaging psychiatry: A meta-model approachNeuroImage, 2017
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus PhotographsJama-Journal Of The American Medical Association, 2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health RecordsScientific Reports, 2016
- Deep learningNature, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Neural network ensemblesIeee Transactions On Pattern Analysis and Machine Intelligence, 1990