Recent changes to Home

Home modified by Sean Colby

Sean Colby — Tue, 30 Dec 2014 21:32:37 -0000

--- v2
+++ v3
@@ -3,5 +3,4 @@

 Please refer to the [Installation] page for information regarding setup. The [Usage] page will provide instructions on executing the code.

-[[members limit=20]]
 [[download_button]]

Home modified by Sean Colby

Sean Colby — Tue, 30 Dec 2014 21:28:42 -0000

--- v1
+++ v2
@@ -1,8 +1,7 @@
-Welcome to your wiki!
+reg_stack is an extension to the open source project, NiftyReg, for the coregistration of a series of 2D images representing a 3D block tissue subjected to histological serial sectioning. The software performs a series of nonlinear image transformations across a kernel of user-specified size to restore data continuity, as the sectioning process results in misalignments and distortions.
+The NiftyReg package also includes optimizations for parallelization on either the CPU or GPU. reg_stack leverages this feature and extends it to include support for running simultaneous instances of reg_f3d (NiftyReg) on multiple GPUs.

-This is the default page, edit it as you see fit. To add a new page simply reference it within brackets, e.g.: [SamplePage].
-
-The wiki uses [Markdown](/p/regstack/wiki/markdown_syntax/) syntax.
+Please refer to the [Installation] page for information regarding setup. The [Usage] page will provide instructions on executing the code.

 [[members limit=20]]
 [[download_button]]

Discussion for Home page

Sean Colby — Tue, 30 Dec 2014 16:36:19 -0000

[Overview]
reg_stack is an extension to the open source project, NiftyReg, for the coregistration of a series of 2D images representing a 3D block tissue subjected to histological serial sectioning. The software performs a series of nonlinear image transformations across a kernel of user-specified size to restore data continuity, as the sectioning process results in misalignments and distortions.
[Instructions]
1.) Install the modified NiftyReg version, provided on the reg_stack SourceForge page. Installation instructions can be found at http://cmictig.cs.ucl.ac.uk/wiki/index.php/NiftySeg_install, as well as further documentation. Note that for the GPU implementation, a CUDA capable GPU must be installed with appropriate drivers and CUDA SDK. Special consideration must be taken to enable GPU usage when building NiftyReg.
2.) Install Python 2.7.X along with the following packages:
-NumPy
-SciPy
-PyDICOM
-Python Imaging Library (or Pillow)
-nose
-sphinx
-NiBabel
3.) Download the latest reg_stack.py file.
[Usage]
1.) Run reg_stack.py with Python 2.7.X, passing the NiftyReg install directory, the directory containing your images, and a registration window size as command line arguments.
2.) Pass additional Nifty-related arguments (such as the -gpu flag for GPU usage) last--they will find their way into reg_f3d. Keep in mind, though, that the required flags (-ref, -flo, -res, -cpp) are handled automatically. Only optional flags used to tweak the registration algorithm should be passed.
3.) That's it! You should find several new folders alongside your input images folder. 'Result' contains the results of the initial transformations, 'CPP' contains the initial deformation fields, 'averagedCPP' contains a comprehensive deformation field for each image, and 'averagedResult' contains a single resultant image after applying the averaged transformation.

Home modified by Sean Colby

Sean Colby — Mon, 29 Dec 2014 22:15:04 -0000

Welcome to your wiki!

This is the default page, edit it as you see fit. To add a new page simply reference it within brackets, e.g.: [SamplePage].

The wiki uses Markdown syntax.

Project Members:

Sean Colby (admin)