Federated and secure cloud services for building medical image classifiers on an intercontinental infrastructure

Medical data processing has found a new dimension with the extensive use of machine-learning techniques to classify and extract features. Machine learning strongly benefits from computing accelerators. However, such accelerators are not easily available at hospital premises, although they can be eas...

Full description

Saved in:

Bibliographic Details
Published in:	Future generation computer systems Vol. 110; pp. 119 - 134
Main Authors:	Blanquer, Ignacio, Brasileiro, Francisco, Brito, Andrey, Calatrava, Amanda, Carvalho, André, Fetzer, Christof, Figueiredo, Flavio, Guimarães, Ronny Petterson, Marinho, Leandro, Meira, Wagner, Silva, Altigran, Alberich-Bayarri, Ángel, Camacho-Ramos, Eduardo, Jimenez-Pastor, Ana, Ribeiro, Antonio Luiz L., Nascimento, Bruno Ramos, Silva, Fábio
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01-09-2020
Subjects:	Federated clouds Medical imaging Trustworthy cloud services Trustworthy cloud services Medical imaging Federated clouds
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Medical data processing has found a new dimension with the extensive use of machine-learning techniques to classify and extract features. Machine learning strongly benefits from computing accelerators. However, such accelerators are not easily available at hospital premises, although they can be easily found on public cloud infrastructures or research centers. Nevertheless, the sensitivity of medical data poses several challenges on the access to such data, requiring security guarantees and isolation. In this paper we present an architecture that addresses this problem. It keeps critical data encrypted in memory and disk, which can only be accessed inside trusted execution environments protected by hardware extensions. Data is anonymized inside these environments and securely transferred to external sites that host accelerator devices, keeping the same network space and reducing security risks even in untrusted cloud backends. Results on the processing of data in different scenarios are presented and discussed. The results are demonstrated on a geographically-wide deployment provided by the ATMOSPHERE project. •Medical data processing in an international collaboration poses challenged on managing different levels of sensitive data.•The use of Trusted execution environments and federated networks can overcome some of those problems.•The use of federated clouds can be used to gather the resources needed for high performance and high security.
ISSN:	0167-739X 1872-7115
DOI:	10.1016/j.future.2020.04.012