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 language | English (US) |
---|---|
Article number | 7548994 |
Pages (from-to) | 21-35 |
Number of pages | 15 |
Journal | Computing in Science and Engineering |
Volume | 18 |
Issue number | 5 |
DOIs | |
State | Published - Sep 1 2016 |
Keywords
- MR atlases
- cloud computation
- image informatics
- image segmentation
- magnetic resonance atlases
- scientific computing
- software as a service
ASJC Scopus subject areas
- General Computer Science
- General Engineering