Loading presentation...

Present Remotely

Send the link below via email or IM


Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.



an introduction to the history, content and applications of advanced normalization tools - by Brian Avants & Nick Tustison

antsr questions

on 20 July 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of ANTs

Advanced Normalization Tools
Bias Correction
Functional MRI
Cortical Thickness
lungomics, cardiomics ...
Atropos + N4
Pure tissue
weight mask
antsAtroposN4.sh iterates between N4 <-> Atropos to improve segmentation results.


antsAtroposN4.sh -d imageDimension
-a inputImage
-x maskImage
-m n4AtroposIterations
-n atroposIterations
-c numberOfClasses
-l posteriorLabelForN4Mask
-o outputPrefix

bash /Users/ntustison/Pkg/ANTs/bin/bin/antsAtroposN4.sh -d 3 -i t1.nii.gz -x mask.nii.gz -l segmentationTemplate.nii.gz -p segmentationPriors%d.nii.gz -o output

Required arguments:

-d: image dimension 2 or 3 (for 2- or 3-dimensional image)
-a: input image Anatomical image, typically T1. If more than one anatomical image
is specified, subsequently specified images are used during the
segmentation process.
-x: mask image Mask defining the region of interest.
-m: max. N4 <-> Atropos iterations Maximum number of (outer loop) iterations between N4 <-> Atropos.
-n: max. Atropos iterations Maximum number of (inner loop) iterations in Atropos.
-c: number of segmentation classes Number of classes defining the segmentation
-l: posterior label for N4 weight mask Which posterior probability image should be used to define the
N4 weight mask. Can also specify multiple posteriors in which
case the chosen posteriors are added.
-o: output prefix The following images are created:
* /Users/ntustison/Desktop//tmp2517//tmpN4Corrected.nii.gz
* /Users/ntustison/Desktop//tmp2517//tmpSegmentation.nii.gz
* /Users/ntustison/Desktop//tmp2517//tmpSegmentationPosteriors.nii.gz

Optional arguments:

-p: segmentation priors Prior probability images initializing the segmentation.
Specified using c-style formatting, e.g. -p labelsPriors%02d.nii.gz.
-r: mrf Specifies MRF prior (of the form '[weight,neighborhood]', e.g.
'[0.1,1x1x1]' which is default).
-s: image file suffix Any of the standard ITK IO formats e.g. nrrd, nii.gz (default), mhd
-k: keep temporary files Keep temporary files on disk (default = false).
-w: Atropos prior segmentation weight Atropos spatial prior probability weight for the segmentation (default = 0)
We minimize the contribution of
partial voluming in estimating the
bias field.
Full transcript