Difference between revisions of "2009 Winter Project Week:LesionSegmentationEfficiency"
From NAMIC Wiki
Hjbockholt (talk | contribs) |
|||
(2 intermediate revisions by one other user not shown) | |||
Line 13: | Line 13: | ||
Steve Piper | Steve Piper | ||
+ | |||
+ | Marco Ruiz | ||
+ | |||
+ | Luis Ibanez | ||
<div style="margin: 20px;"> | <div style="margin: 20px;"> | ||
Line 19: | Line 23: | ||
<h1>Objective</h1> | <h1>Objective</h1> | ||
− | Improve the running time and memory use of the new lesion segmentation method. | + | Improve the running time and memory use of the new lesion segmentation method as the current module takes 90-120 minutes and up to 2 Gb of RAM. |
</div> | </div> | ||
Line 36: | Line 40: | ||
<h1>Progress</h1> | <h1>Progress</h1> | ||
− | + | # Luiz provided an itk statistics filter to replace current custom, single threaded, un-optimized code. | |
+ | # Final piece on single threaded code in process of being replaced by a custom multi-threaded ITK filter. | ||
+ | # Prediction runtime reduced from between 1.5 - 2 hours to less than 9 minutes on a quad core machine. | ||
+ | # Prediction Memory footprint reduced from 2.5GB to 1.1GB | ||
+ | # With Marco's help our pipeline is now running on Grid Wizard | ||
</div> | </div> |
Latest revision as of 22:55, 8 January 2009
Home < 2009 Winter Project Week:LesionSegmentationEfficiency![]() Return to Project Week Main Page |
Key Investigators
Mark Scully, MIND
Jeremy Bockholt, MIND
Steve Piper
Marco Ruiz
Luis Ibanez
Objective
Improve the running time and memory use of the new lesion segmentation method as the current module takes 90-120 minutes and up to 2 Gb of RAM.
Approach, Plan
Review code to determine custom pieces that can be replaced with existing filters. Make the custom pieces that can't be replaced multi-thread capable. Locate inefficient memory use and improve it.
See what if anything could be made to work in GWE (Marcus)?
Progress
- Luiz provided an itk statistics filter to replace current custom, single threaded, un-optimized code.
- Final piece on single threaded code in process of being replaced by a custom multi-threaded ITK filter.
- Prediction runtime reduced from between 1.5 - 2 hours to less than 9 minutes on a quad core machine.
- Prediction Memory footprint reduced from 2.5GB to 1.1GB
- With Marco's help our pipeline is now running on Grid Wizard