MRICloud: Delivering high-throughput MRI neuroinformatics as cloud-based software as a service

Susumu Mori, Dan Wu, Can Ceritoglu, Yue Li, Anthony Kolasny, Marc A. Vaillant, Andreia V. Faria, Kenichi Oishi, Michael I. Miller

Research output: Contribution to journalArticle

Abstract

Image analysis tools for brain magnetic resonance imaging (MRI) have become increasingly important for computer-aided diagnosis that involves large amounts of medical image data. The authors of this article have endeavored to develop software tools to serve the clinical research community, starting with a stand-alone executable, hybrid local computation model for today's modern architecture of cloud services, which they call MRICloud. MRICloud provides a high-throughput neuroinformatics platform for automated brain MRI segmentation and analytical tools for quantification via distributed remote computation and Web-based user interfaces. There are several key, inherent advantages to a cloud-based software as a service - in particular, how it improves the efficiency of software implementation, upgrades, and maintenance. The client-server model is also ideal for high-performance computing, allowing for distribution of computational servers across the world. This article introduces the basic functions and utilities of MRICloud, its developmental history and future perspectives, its infrastructures, and the benefits of this cloud service framework.

Original languageEnglish (US)
Article number7548994
Pages (from-to)21-35
Number of pages15
JournalComputing in Science and Engineering
Volume18
Issue number5
DOIs
StatePublished - Sep 1 2016

Keywords

  • cloud computation
  • image informatics
  • image segmentation
  • magnetic resonance atlases
  • MR atlases
  • scientific computing
  • software as a service

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'MRICloud: Delivering high-throughput MRI neuroinformatics as cloud-based software as a service'. Together they form a unique fingerprint.

  • Cite this