Back to Search Start Over

Distributed autoencoder classifier network for small‐scale and scattered COVID‐19 dataset classification.

Authors :
Yang, Yuan
Zhang, Lin
Ren, Lei
Wang, Xiaohan
Source :
International Journal of Imaging Systems & Technology. Nov2023, Vol. 33 Issue 6, p1870-1881. 12p.
Publication Year :
2023

Abstract

In healthcare, small‐scare data are stored with individual entities, such as hospitals, and they are not shared. However, data with one entity are not sufficient for training a machine learning model and therefore cannot be fully utilized. Given that a large amount of small‐scale data is widely distributed between hospitals/individuals, it is necessary to deploy an easy, scalable, and secure distributed computational framework. We aim to aggregate these scattered and small‐scale data to train neural networks and achieve classification and detection on coronavirus disease 2019 (COVID‐19) datasets. We propose a distributed autoencoder (AE) classifier network for this purpose. It contains a central classifier and multiple distributed AEs. The AEs are used as generators. A local generator uses an actual COVID‐19 computed tomography image as the input and outputs a synthetic image. The well‐trained generator provides an image to train the central classifier model. The central classifier network model learns information from all the generated COVID‐19 data using the distributed AE. Experiments are performed using some COVID‐19 datasets. The distributed AE classifier network outperforms all the models that use a single subset, and its performance is similar to that of a regular classifier. The proposed network solves the problem of using small‐scale and scattered COVID‐19 data to train neural networks while ensuring data privacy. The accuracy of the network is the same as that achieved using the entire data. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
08999457
Volume :
33
Issue :
6
Database :
Academic Search Index
Journal :
International Journal of Imaging Systems & Technology
Publication Type :
Academic Journal
Accession number :
173369084
Full Text :
https://doi.org/10.1002/ima.22972