Unknown

Dataset Information

0

Distributed deep learning networks among institutions for medical imaging.


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.

SUBMITTER: Chang K 

PROVIDER: S-EPMC6077811 | biostudies-literature | 2018 Aug

REPOSITORIES: biostudies-literature

altmetric image

Publications

Distributed deep learning networks among institutions for medical imaging.

Chang Ken K   Balachandar Niranjan N   Lam Carson C   Yi Darvin D   Brown James J   Beers Andrew A   Rosen Bruce B   Rubin Daniel L DL   Kalpathy-Cramer Jayashree J  

Journal of the American Medical Informatics Association : JAMIA 20180801 8


<h4>Objective</h4>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.<h4>Methods</h4>We simulate the dis  ...[more]

Similar Datasets

| S-EPMC5869052 | biostudies-other
| S-EPMC10035842 | biostudies-literature
| S-EPMC6548658 | biostudies-literature
| S-EPMC9565422 | biostudies-literature
| S-EPMC10575417 | biostudies-literature
| S-EPMC8027892 | biostudies-literature
| S-EPMC9343202 | biostudies-literature
| S-EPMC5729285 | biostudies-literature
| S-EPMC6500159 | biostudies-literature
| S-EPMC10394257 | biostudies-literature