Distributed deep learning networks among institutions for medical imaging

Abstract

ObjectiveDeep 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.MethodsWe 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).ResultsWe 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.ConclusionsWe show that distributing deep learning models is an effective alternative to sharing patient data. This finding has implications for any collaborative deep learning study.

How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalize to rare congenital heart diseases for surgical planning?

“…There is still the problem of rare pathologies with small available datasets, and the results indicate that it is necessary to finetune on them to make reasonable predictions. Maybe the idea of federated and distributed learning as applied by Ken et al 12 could overcome the problem of rare datasets and pathologies by sharing the network weights across distributed institutions.…”

“…Current guidelines for the timing of a heart valve replacement, more specifically of pulmonary valve replacement, are mainly based on enlarged ventricular volumes and depressed ventricular function (cf., 12 ). Technically, these information can be obtained by segmentation of cardiac magnetic resonance (CMR) images.…”

An overview of deep learning in medical imaging focusing on MRI

“…See [339] for a recent survey. There are a few examples of these ideas entering the medical machine learning community, as in [340] where the distribution of deep learning models among several medical institutions was investigated, but then 49 Lipton: Machine Learning: The Opportunity and the Opportunists https://www.technologyreview.com/video/ 612109, Jordan: Artificial Intelligence -The Revolution Hasn't Happened Yet https://medium.com/@mijordan3/ artificial-intelligence-the-revolution-hasnt-happened-yet-5e1d5812e1e7 50 See for example https://ai.googleblog.com/2017/04/federated-learning-collaborative.html without considering the above privacy issues. As machine learning systems in medicine grows to larger scales, perhaps even including computations and learning on the "edge", federated learning and differential privacy will likely become the focus of much research in our community.…”

Artificial intelligence in cancer imaging: Clinical challenges and applications

“…Furthermore, access to available data sets should be improved to promote intellectual collaboration. Institutional, professional, and government groups should be encouraged to share validated data to support the development of AI algorithms, which requires overcoming certain fundamental technical, legal, and perhaps ethical concerns . For example, the National Institutes of Health recently shared chest x‐ray and CT repositories to help AI scientists .…”