
Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/3124 |
scores. This work presents a unified method for local shape analysis that can accomodate different number of variates and contrasts. It also allows to include any number of associated variables in the statistical analysis of the data. Several cases of study are given to clarify the explanation of the different types of data that can be analyzed and the parameters that can be used to tune the program shapeAnalysisMANCOVA. This tool has been designed to interact seamlessly with the existing UNC SPHARM-PDM based shape analysis toolbox.







These authors have developed a tool that we were in the early stages of developing ourselves. It looks very much like what we had in mind, and we think it is worth trying on our data. Besides the source code, some binary executables and sample input/output data would have been very helpful. (Greedy users.)
Also, I might mis-understand how the tool currently works, but it would also be nice if you could output the B matrices for each node from the GLM part for later use in alternative hypotheses. Our surfaces have 70,000 nodes, so recomputing the betas each time would be a non-trivial runtime burden.
Hypothesis:The authors assume users are doing 3D shape analyses using surface meshes.
Evidence:The authors describe three example applications and provide figures showing the output vecors/significance maps.
Open Science:The authors publish their paper and source code in the ITK journal.
Reproducibility:I downloaded the source, but did not compile. While we have the ITK libraries, a few other libraries are required, and I am not up to the task of building them. I hope I can get binaries from the authors. So I haven't run it yet.
Rather than reproduce their results, I am interested in running on my own data.
Use of Open Source Software:The authors use ITK.
Open source Contributions:Yes -- a source tree is provided.
Code Quality :I haven't read it yet.
Quality of the data :I didn't see any data, but I would like to. They do publish the mesh list in the paper, which is the more important input, for my purposes. I am hopeful we won't have much trouble converting VTK to ITK spatial object format.
Interest:My boss, David Van Essen, asked this question: Could we use it for dependent variables other than 3D coordinates. I don't see why not, but I noted that the selection of avaiable tests seemed tailored to 3D coordinate analyses.
Free comment :Thank you for sharing this important resource. I think it could be very useful to our lab's morphometry applications, and we have several of them.
Resources
![]() |
|
Download All | |
Download Paper , View Paper | |
Download Source code | |
Github |
Statistics more
![]() |
|
Global rating: | ![]() ![]() ![]() ![]() ![]() |
Review rating: | ![]() ![]() ![]() ![]() ![]() |
Code rating: | |
Paper Quality: |
![]() ![]() |
Information more
![]() |
|
Categories: | Mathematics, Statistical shape models |
Keywords: | Statistical shape analysis, MANCOVA, Multiple comparison problem, permutation tests, SPHARM |
Toolkits: | ITK, CMake, VTK |
Export citation: |
Share
![]() |
Linked Publications more
![]() |
||
![]() by Vercauteren T., Pennec X., Perchant A., Ayache N.
|
||
![]() by Li W., Magnotta V.
|
View license
Send a message to the author
