This documentation is intended to provide the basic steps needed for installation and running the "ODVBA" project which has been designed for group analysis of medical images. In the proposed framework, Nonnegative Discriminative Projection (NDP) is introduced to find the optimal discriminative direction in each learning set constructed by the neighborhood centered at the given voxel. Subsequently, each voxel’s statistic is determined by a composition of all the smoothing directions which are associated with the given voxel. Finally permutation tests are used to obtain the statistical significance of the resulting ODVBA maps. The following information is provided by this document:
See the copyright notices for more information.
There are some
sub-folders as follows:
Before starting installation of the package you need to make sure that the following dependencies have been correctly installed. You will also need to assure that the executables of these required modules are placed in your PATH environmental variable:
1) Obtain a copy of the ODVBA source package and put it to a new directory. In the following we assume ~/ODVBA-src as the root directory of the source package.
2) make a build directory outside of the directory of the source package:
mkdir ~/ODVBA-build
3) Change to the "build" directory and run ccmake from the parent directory:
cd ~/ODVBA-build
ccmake ~/ODVBA-build
4) Push the "c" button several times until you are given the option to put "g". You can ignore warning messages in this stage by pressing
"e".
5) Push the "g" button so that you can generate the "Makefile" and quit afterward.
6) Now make the project by typing:
make
Finally, all the executable files are created in ~/ODVBA-build/bin/.
After the executables are created, it is necessary that they would be copied into the required final directories specified by CMAKE_INSTALL_PREFIX on user's machine.
Installation is invoked by the command:
make install
Further
details on usage can be found in "UserManual"
found under the Doc folder of the project.
|
Tianhao Zhang and Christos Davatzikos,
“Optimally-Discriminative Voxel-based Analysis”, In
Proceeding of 13th International Conference on Medical Image Computing and
Computer Assisted Intervention, Vol. 6362, pp: 257-265, 2010. |
Section
of Biomedical Image Analysis
Department of Radiology
University of Pennsylvania
3600 Market Street Suite 380
Philadelphia, PA 19104