Institutionally Distributed Deep Learning Networks

09/10/2017
by   Ken Chang, et al.
0

Deep learning has become a promising approach for automated medical diagnoses. 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 such cases, sharing a deep learning model is a more attractive alternative. The best method of performing such a task is unclear, however. In this study, we simulate the dissemination of learning deep learning network models across four institutions using various heuristics and compare the results with a deep learning model trained on centrally hosted patient data. The heuristics investigated include ensembling single institution models, single weight transfer, and cyclical weight transfer. We evaluated these approaches for image classification in three independent image collections (retinal fundus photos, mammography, and ImageNet). We find that cyclical weight transfer resulted in a performance (testing accuracy = 77.3 closest to that of centrally hosted patient data (testing accuracy = 78.7 also found that there is an improvement in the performance of cyclical weight transfer heuristic with high frequency of weight transfer.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/10/2018

Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation

Deep learning models for semantic segmentation of images require large a...
research
03/27/2021

Addressing catastrophic forgetting for medical domain expansion

Model brittleness is a key concern when deploying deep learning models i...
research
12/21/2019

A Deep Learning Model for Chilean Bills Classification

Automatic bill classification is an attractive task with many potential ...
research
12/03/2018

Split learning for health: Distributed deep learning without sharing raw patient data

Can health entities collaboratively train deep learning models without s...
research
12/04/2018

Privacy-Preserving Distributed Deep Learning for Clinical Data

Deep learning with medical data often requires larger samples sizes than...
research
03/06/2023

A Comparison of Methods for Neural Network Aggregation

Deep learning has been successful in the theoretical aspect. For deep le...
research
05/01/2023

Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity

Modern machine learning increasingly supports paradigms that are multi-i...

Please sign up or login with your details

Forgot password? Click here to reset