3 d@sldZddlmZmZmZmZmZddlmZddlm Z GdddeZ Gdd d eZ Gd d d eZ d S) z Nipype interface for seg_EM. The em module provides higher-level interfaces to some of the operations that can be performed with the seg_em command-line program. Examples -------- See the docstrings of the individual classes for examples. ) TraitedSpecFiletraitsCommandLineInputSpecInputMultiPath)NiftySegCommand)get_custom_pathc@sNeZdZdZeddddddZedddd Zejd dd d d gdZ edddddd gdZ e ddddd gdZ ejdddddZ ejdddddZejdddddZejdd d!Zd"Zejd#ddedZd$Zejd%ed!Zd&Zejejejd'ed!Zd(Zejejejd)ed!Zed*gd+d,d-d.Zed*gd/d0d1d.Zed*gd2d3d4d.Zd5S)6 EMInputSpeczInput Spec for EM.z-in %sTzInput image to segment)argstrexists mandatorydescpositionz-mask %sz$Filename of the ROI for label fusion)r r rz -nopriors %sz&Number of classes to use without priorprior_4Dpriors)r rrxorz -prior4D %sz4D file containing the priorsno_prior)r r rrrz%szList of priors filepaths.z -max_iter %sdzMaximum number of iterations)r default_valueZ usedefaultrz -min_iter %szMinimum number of iterationsz -bc_order %sz#Polynomial order for the bias fieldz -mrf_beta %sz!Weight of the Markov Random Field)r rzeBias field correction will run only if the ratio of improvement is below bc_thresh. (default=0 [OFF])z -bc_thresh %szMAmount of regularization over the diagonal of the covariance matrix [above 1]z-reg %szOutlier detection as in (Van Leemput TMI 2003). is the Mahalanobis threshold [recommended between 3 and 7] is a convergence ratio below which the outlier detection is going to be done [recommended 0.01]z-outlier %s %szwRelax Priors [relaxation factor: 00 (recommended=2.0)] /only 3D/z -rf %s %sin_filez %s_em.nii.gzz-out %szOutput segmentation)Z name_sourceZ name_templater rz%s_bc_em.nii.gzz -bc_out %szOutput bias corrected imagez%s_outlier_em.nii.gzz-out_outlier %szOutput outlierness imageN)__name__ __module__ __qualname____doc__rrZ mask_filerZIntrrrrZmax_iterZmin_iterZ bc_order_valZFloatZ mrf_beta_valrZ bc_thresh_valZreg_valTupleZ outlier_valZ relax_priorsout_file out_bc_fileout_outlier_filer"r"?/tmp/pip-build-7vycvbft/nipype/nipype/interfaces/niftyseg/em.pyr s     r c@s.eZdZdZeddZeddZeddZdS) EMOutputSpeczOutput Spec for EM.zOutput segmentation)rzOutput bias corrected imagezOutput outlierness imageN)rrrrrrr r!r"r"r"r#r$s  r$cs8eZdZdZedddZdZeZe Z fddZ Z S)EMaInterface for executable seg_EM from NiftySeg platform. 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. `Source code `_ | `Documentation `_ Examples -------- >>> from nipype.interfaces import niftyseg >>> node = niftyseg.EM() >>> node.inputs.in_file = 'im1.nii' >>> node.inputs.no_prior = 4 >>> node.cmdline 'seg_EM -in im1.nii -bc_order 3 -bc_thresh 0 -max_iter 100 -min_iter 0 -nopriors 4 -bc_out im1_bc_em.nii.gz -out im1_em.nii.gz -out_outlier im1_outlier_em.nii.gz' Zseg_EMZ NIFTYSEGDIR)Zenv_dirZ_emcsB|dkr*t|jj}d|dj|jjfStt|j|||SdS)z/Convert input to appropriate format for seg_EM.rz -priors %d %s N)leninputsrjoinsuperr% _format_arg)selfoptspecvalZ _nb_priors) __class__r"r#r+s zEM._format_arg) rrrrr Z_cmd_suffixr Z input_specr$Z output_specr+ __classcell__r"r")r0r#r%s  r%N) rbaserrrrrrZ niftyreg.baser r r$r%r"r"r"r# s   q