Access the full text.
Sign up today, get DeepDyve free for 14 days.
DE Rex, JQ Ma, AW Toga (2003)
The LONI pipeline processing environmentNeuroImage, 19
AR Gray, SG MacDonell (1997)
A comparison of techniques for developing predictive models of software metricsInformation and Software Technology, 39
DS Marcus, TR Olsen, M Ramaratnam, RL Buckner (2005)
XNAT: a software framework for manging neuroimaging laboratory data
K Dejaeger, W Verbeke, D Martens, B Baesens (2012)
Data mining techniques for software effort estimation: a comparative studySoftware Engineering, IEEE Transactions on, 38
L Breiman (1984)
Classification and regression trees
K Konstantinides, J Rasure (1994)
The Khoros software development environment for image and signal processingImage Processing, IEEE Transactions on, 3
MJ McAuliffe, FM Lalonde, D McGarry, W Gandler, K Csaky, BL Trus (2001)
Medical image processing, analysis & visualization in clinical researchComputer-Based Medical Systems, IEEE Symposium on, 0
B Sheehan, S Fuller, M Pique, M Yeager (1996)
AVS software for visualization in molecular microscopyJournal of Structural Biology, 116
B Lucas, J Bogovic, A Carass, P-L Bazin, J Prince, D Pham (2010)
The Java Image Science Toolkit (JIST) for rapid prototyping and publishing of neuroimaging softwareNeuroinformatics, 8
Medical imaging analysis processes often involve the concatenation of many steps (e.g., multi-stage scripts) to integrate and realize advancements from image acquisition, image processing, and computational analysis. With the dramatic increase in data size for medical imaging studies (e.g., improved resolution, higher throughput acquisition, shared databases), interesting study designs are becoming intractable or impractical on individual workstations and servers. Modern pipeline environments provide control structures to distribute computational load in high performance computing (HPC) environments. However, high performance computing environments are often shared resources, and scheduling computation across these resources necessitates higher level modeling of resource utilization. Submission of ‘jobs’ requires an estimate of the CPU runtime and memory usage. The resource requirements for medical image processing algorithms are difficult to predict since the requirements can vary greatly between different machines, different execution instances, and different data inputs. Poor resource estimates can lead to wasted resources in high performance environments due to incomplete executions and extended queue wait times. Hence, resource estimation is becoming a major hurdle for medical image processing algorithms to efficiently leverage high performance computing environments. Herein, we present our implementation of a resource estimation system to overcome these difficulties and ultimately provide users with the ability to more efficiently utilize high performance computing resources.
Neuroinformatics – Springer Journals
Published: Jun 7, 2014
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.