Summer2009:Registration reproducibility in Slicer - Revision history

Fedorov: /* Key Investigators */

2009-12-20T23:37:33Z

Key Investigators

2009-06-23T19:25:45Z

Key Investigators

2009-06-22T13:06:25Z

Participate!

2009-06-22T13:04:18Z

Participate!

2009-06-22T12:59:25Z

Participate!

2009-06-22T12:57:27Z

Participate!

2009-06-22T02:14:49Z

2009-06-18T13:26:56Z

Test setup

2009-06-18T13:25:20Z

Reproducibility for RegisterImages module

2009-06-17T18:02:35Z

Reproducibility for RegisterImages module

@@ Line 45: / Line 45: @@
 * number of threads used apparently has impact on registration reproducibility, should be specified
 * Number of threads should not affect the result of registration; Luis reproduced the problem outside Slicer, confirmed as an ITK issue: NAMICSandbox/PNL/RegistrationTestBench/Testing
 </div>

@@ Line 44: / Line 44: @@
 * abused Slicer3 dashboard to collect the magnitude of difference on various platforms
 * number of threads used apparently has impact on registration reproducibility, should be specified
 </div>

@@ Line 90: / Line 90: @@
 Or use this version, which you can cut and paste into a Slicer3-build directory:
 <pre>
 ./Slicer3 --launch ./lib/Slicer3/Plugins/RigidRegistration --testingmode --initialtransform ../Slicer3/Testing/Data/Input/MRMeningioma01.tfm --fixedsmoothingfactor 0 --movingsmoothingfactor 0 --histogrambins 30 --spatialsamples 10000 --iterations 100,100,50,20 --learningrate 0.01,0.005,0.0005,0.0002 --translationscale 100 --outputtransform ./RigidRegistrationTransform-CLI.txt ../Slicer3/Testing/Data/Input/MRMeningioma0.nrrd ../Slicer3/Testing/Data/Input/MRMeningioma1.nrrd
 </pre>

@@ Line 131: / Line 131: @@
 </pre>
-* Steve Pieper's Mac Book Pro - dual core
+* transplant (Steve Pieper's Mac Book Pro - dual core)
 <pre>
 #Insight Transform File V1.0
@@ Line 140: / Line 140: @@
 ---
 Magnitude of error vector: 2.72849
 </pre>

@@ Line 127: / Line 127: @@
 Parameters: 0.00687841 0.00580804 0.0113849 0.999895 7.65038 5.16471 0.0120382
 FixedParameters: 0.00025 0.00025 -1.42109e-014
 ---
 Magnitude of error vector: 2.72849

@@ Line 87: / Line 87: @@
    --iterations 100,100,50,20 --learningrate 0.01,0.005,0.0005,0.0002 --translationscale 100
    --outputtransform ./RigidRegistrationTransform-CLI.txt MRMeningioma0.nrrd MRMeningioma1.nrrd
 </pre>

@@ Line 1: / Line 1: @@
 __NOTOC__
 <gallery>
-Image:PW2009-v3.png|[[2009_Summer_Project_Week|Project Week Main Page]]
+Image:PW2009-v3.png|[[2009_Summer_Project_Week#Projects|Projects List]]
 Image:transform-gui.jpg|Transform for test data/GUI registration
 Image:transform-cli.jpg|Transform for test data/CLI registration

@@ Line 67: / Line 67: @@
 </pre>
-. To get the actual difference in the corner of your image using one transform vs another, you can run RigidRegistration in the testing mode. '''Testing feature is not available in stable release -- you need to download nightly, or use your build from scratch!'''. In testing mode, initial transform is NOT used as the initial tranform, but is simply a "ground truth" transform to test reproducibility.
+. To get the actual difference in the corner of your image using one transform vs another, you can run RigidRegistration in the testing mode. '''Testing feature is not available in stable release -- you need to download nightly, or build from sources!'''. In testing mode, initial transform is NOT used as the initial tranform, but is simply a "ground truth" transform to test reproducibility.
 <pre>

@@ Line 141: / Line 141: @@
    MRMeningioma0.nrrd MRMeningioma1.nrrd
 </pre>
 |[[Image:register_images_reproducibility_setup.jpg|thumb|250px|RegisterImages initialization in GUI, which corresponds to the command line invocation]]
 |}