Difference between revisions of "Seg EM"
From CMIC
(Created page with "seg_EM is a general purpose intensity based image segmentation tool. In it's simplest form, it takes in one 2D or 3D image and segments it in n classes. This function has impl...") |
|||
| Line 1: | Line 1: | ||
seg_EM is a general purpose intensity based image segmentation tool. In it's simplest form, it takes in one 2D or 3D image and segments it in n classes. This function has implemented several other improvements (Please click the hyperlinks to go to specific sections): | seg_EM is a general purpose intensity based image segmentation tool. In it's simplest form, it takes in one 2D or 3D image and segments it in n classes. This function has implemented several other improvements (Please click the hyperlinks to go to specific sections): | ||
| − | + | * Input anatomical priors, either as a series of images or as a 4D image. | |
| − | + | ** These priors should be pre-registered using for example [http://cmictig.cs.ucl.ac.uk/wiki/index.php/NiftyReg NiftyReg]. | |
| − | + | * Markov Random Field for spatial consistency | |
| − | + | * Bias field inhomogeneity correction to compensate for B0 non-uniformities as per Van Leemput et al. TMI (1999) [http://nmr.mgh.harvard.edu/~koen/VanLeemputTMI1999a.pdf PDF]. | |
| − | + | ** The Bias corrected image can also be outputted | |
| − | + | * Outlier detection as in Van Leemput et al. TMI (2001) [http://nmr.mgh.harvard.edu/~koen/VanLeemputTMI2001.pdf PDF] | |
| − | + | * Prior relaxation as in Cardoso et al. MICCAI (2011) [http://www.ncbi.nlm.nih.gov/pubmed/22906793 Link] | |
| − | + | * Semi-conjugate prior over the model parameters as explained in Cardoso et al. MICCAI (2011) [http://www.ncbi.nlm.nih.gov/pubmed/22906793 Link] | |
The help for this function can be obtained by running | The help for this function can be obtained by running | ||
seg_EM -h | seg_EM -h | ||
Revision as of 16:50, 8 June 2016
seg_EM is a general purpose intensity based image segmentation tool. In it's simplest form, it takes in one 2D or 3D image and segments it in n classes. This function has implemented several other improvements (Please click the hyperlinks to go to specific sections):
- Input anatomical priors, either as a series of images or as a 4D image.
- These priors should be pre-registered using for example NiftyReg.
- Markov Random Field for spatial consistency
- Bias field inhomogeneity correction to compensate for B0 non-uniformities as per Van Leemput et al. TMI (1999) PDF.
- The Bias corrected image can also be outputted
- Outlier detection as in Van Leemput et al. TMI (2001) PDF
- Prior relaxation as in Cardoso et al. MICCAI (2011) Link
- Semi-conjugate prior over the model parameters as explained in Cardoso et al. MICCAI (2011) Link
The help for this function can be obtained by running
seg_EM -h
