mri_ca_train - create a GCA from MNI and xfm files


mri_ca_train [options] <subject 1> <subject 2> ... <output gca fname>


Positional Arguments

<subject 1>

subject 1

<subject 2>

subject 2

<output file>

output file

Required Flagged Arguments


segmentation directory (path relative to $subject/mri

Optional Flagged Arguments


spacing of classifiers in canonical space


use intensity gradient as input to classifier

-mask volname

use volname as a mask


spacing of classifiers in canonical space i.e. memory you devote to intensity distribution


spacing of class priors in canonical space i.e. memory you devote to prior probabity distributions

-input name

specifying training data (path relative to $subject/mri). can specify multiple inputs. If not specified, "orig" is used. Using orig is sufficient for an atlas created with MPRAGES, but for other data types (i.e. multi-echo flash) this volume should be choosen more carefully, see example 2.


input volume (i.e. nu, norm.mgz etc)


specifies the atlas as either single-echo or multi-echo


reference transform


<output file>

gca file - gaussian class array file, in this instance essentially a probabilistic map


Example 1

mri_ca_train -prior_spacing 2 \
  -node_spacing 8 \
  -mask brain \
  -parc_dir esegatlast \
  -xform manual_registration.xfm \
  -T1 nu subject1 single_one.gca

Example 2

mri_ca_train -node_spacing 4 \
  -prior_spacing 2 \
  -parc_dir esegatlast \
  -xform talairach_one.m3d \
  -input flash30_avg.mgz \
  -input flash5_avg.mgz \
  $SUBJECTS multi_one.gca

See Also

SubcorticalSegmentation, mri_em_register, mri_ca_normalize


Reporting Bugs

Report bugs to <>



mri_ca_train (last edited 2008-04-29 11:45:06 by localhost)