A cloud infrastructure for scalable computing on population imaging databanks

Abstract

This article describes the software architecture designed to cope with the computing demand of research usage of complex data from the imaging biobank of the Regional Ministry of Health in the Valencia Region (CS). It proposes the use of self-configured virtual clusters on top of on-premise and public cloud infrastructures. It uses a model based on recipes and autoconfiguration to deploy virtual elastic clusters that adjust themselves to the actual workload of the study, therefore reducing operating costs and preventing the need of up-front investments both at the level of the imaging biobank or the final user. All the software used is released under open-source licenses.