3 XdB@s@dZddlZddlmZddlmZmZmZmZm Z m Z ddlm Z m Z m Z Gd d d e ZGd d d eZGd dde ZGddde ZGdddeZGddde ZGddde ZGdddeZGddde ZGddde ZGdddeZGdd d e ZGd!d"d"e ZGd#d$d$eZGd%d&d&e ZdS)'zQThe ants module provides basic functions for interfacing with ants functions. N) ensure_list) TraitedSpecFileStrtraitsInputMultiPath isdefined) ANTSCommandANTSCommandInputSpecLOCAL_DEFAULT_NUMBER_OF_THREADSc @seZdZejddddddZeedddd d Zeeddd dd d Z ej ejdddddddddd Z ej ej dgddgdddZ ej ejdgdddZeddddddZejdd d!d"d#d ddd Zej d$gdd%Zejd&gdd%Zej d'gdd%Zej d(gdd%Zejd ddd)Zej ejd*d+d,Zej ejd-d+d,Zej ejd.d+d,Zej ej d d/Zej ejd0d+d,Zejd1d2d dd3Zej d4gdd%Zej d4gdd%Z ej ejd5d+d,Z!d6S)7 ANTSInputSpecrrz%dr zimage dimension (2 or 3))argstrpositiondescT)existsz)image to which the moving image is warped) mandatoryrz%szEimage to apply transformation to (generally a coregisteredfunctional))rrrCCMISMIPRSSDMSQPSEg?metriczIthe metric weight(s) for each stage. The weights must sum to 1 per stage.)value usedefaultrequiresrrznradius of the region (i.e. number of layers around a voxel/pixel) that is used for computing cross correlation)r rroutz--output-naming %s)rrrrZDiffZElastZExpz Greedy ExpSyNtransformation_model)r rgradient_step_lengthnumber_of_time_steps delta_time)r default_valuerz--number-of-iterations %sx)rsepz--gaussian-smoothing-sigmas %sz--subsampling-factors %s)rz--MI-option %sZGaussZDMFFD)rrregularizationz --number-of-affine-iterations %sN)"__name__ __module__ __qualname__rEnum dimensionr r fixed_image moving_imageListrFloat metric_weightIntradiusroutput_transform_prefixr#r$r%r& symmetry_typeBooluse_histogram_matchingnumber_of_iterationssmoothing_sigmasZsubsampling_factorsaffine_gradient_descent_optionZ mi_optionr*#regularization_gradient_field_sigma®ularization_deformation_field_sigmaZnumber_of_affine_iterationsr@r@U/var/www/html/virt/lib/python3.6/site-packages/nipype/interfaces/ants/registration.pyr sv   rc@sHeZdZedddZedddZedddZedddZedddZdS) ANTSOutputSpecTzAffine transform file)rrzWarping deformation fieldz!Inverse warping deformation fieldzVTK metaheader .mhd filezVTK metaheader .raw fileN) r+r,r-raffine_transformwarp_transforminverse_warp_transformZ metaheaderZmetaheader_rawr@r@r@rArBys     rBcsTeZdZdZdZeZeZddZ ddZ ddZ dd Z fd d Z d d ZZS)ANTSaANTS wrapper for registration of images (old, use Registration instead) Examples -------- >>> from nipype.interfaces.ants import ANTS >>> ants = ANTS() >>> ants.inputs.dimension = 3 >>> ants.inputs.output_transform_prefix = 'MY' >>> ants.inputs.metric = ['CC'] >>> ants.inputs.fixed_image = ['T1.nii'] >>> ants.inputs.moving_image = ['resting.nii'] >>> ants.inputs.metric_weight = [1.0] >>> ants.inputs.radius = [5] >>> ants.inputs.transformation_model = 'SyN' >>> ants.inputs.gradient_step_length = 0.25 >>> ants.inputs.number_of_iterations = [50, 35, 15] >>> ants.inputs.use_histogram_matching = True >>> ants.inputs.mi_option = [32, 16000] >>> ants.inputs.regularization = 'Gauss' >>> ants.inputs.regularization_gradient_field_sigma = 3 >>> ants.inputs.regularization_deformation_field_sigma = 0 >>> ants.inputs.number_of_affine_iterations = [10000,10000,10000,10000,10000] >>> ants.cmdline 'ANTS 3 --MI-option 32x16000 --image-metric CC[ T1.nii, resting.nii, 1, 5 ] --number-of-affine-iterations 10000x10000x10000x10000x10000 --number-of-iterations 50x35x15 --output-naming MY --regularization Gauss[3.0,0.0] --transformation-model SyN[0.25] --use-Histogram-Matching 1' c Csg}ddddddg}ddg}xztt|jjD]f}|jj||kr|jd |jj||jj||jj||jj||jj|fq.|jj||kr.q.Wd j |S) NrrrrrrrZJTBz#--image-metric %s[ %s, %s, %g, %d ] ) rangeleninputsr1rappendr0r4r6join)selfretvalZintensity_basedZpoint_set_basediir@r@rA_image_metric_constructors    zANTS._image_metric_constructorc Cs|jj}|jj}|jj}|jj}|jj}d|g}g}x,||||fD]}|tjk rD|jd|qDWt |dkrt |dkrdj |}n dj |}|jd|dj |S)Nz--transformation-model %sz%#.2grr ,rz[%s]) rJr#r$r%r&r8r UndefinedrKrIrL) rMmodelZ step_lengthZ time_stepr&r8rN parameterselemr@r@rA_transformation_constructors       z ANTS._transformation_constructorcCsdj|jj|jj|jjS)Nz--regularization {0}[{1},{2}])formatrJr*r>r?)rMr@r@rA_regularization_constructorsz ANTS._regularization_constructorc s|jj}ddddgxszDANTS._affine_gradient_descent_option_constructor..z --affine-gradient-descent-optionrG)rJr=rHrI IndexError_format_xarrayrL)rMvaluesrOrTrNr@)r[rA+_affine_gradient_descent_option_constructors  z0ANTS._affine_gradient_descent_option_constructorcsl|dkr|jS|dkr |jS|dkr0|jS|dkr@|jS|dkrX|jjrTdSdStt|j|||S)Nr1r#r*r=r:z--use-Histogram-Matching 1z--use-Histogram-Matching 0) rPrVrXrarJr:superrF _format_arg)rMoptspecval) __class__r@rArcszANTS._format_argcCsX|jj}tjj|jjd|d<tjj|jjd|d<tjj|jjd|d<|S)Nz Affine.txtrCz Warp.nii.gzrDzInverseWarp.nii.gzrE)_outputsgetospathabspathrJr7)rMoutputsr@r@rA _list_outputss zANTS._list_outputs)r+r,r-__doc___cmdr input_specrB output_specrPrVrXrarcrn __classcell__r@r@)rgrArFs rFc@seZdZejddddddZeeddddd Zedd d d gd dZ eej deddddgddZ eeddddd Z eddgd dgddZ eej deddddgddZeddddZeddddZeeddd d d!gd"Zeejd#gd$d!gd%Zejd&d'dd d#gd(d)Zejd*d+d,d-d.d/Zej eejeZejedd0d Zejd1dd2Zej eejeZejed1gdd3gdd4d5Zejd6dd2Zej eejeZejed6gdd7gd8d9Z ejd:d;dd?Z#ej ej$d@d1dAd=Z%ej e%eje%Z&eje&dBgdCd?Z'ejejdDdEZ(ej ejejejd dFdddGdHZ)ejdIdJdKdLdMdNdOdPdQdRd ddS Z*ej ej+ejej+ejejej+ej,Z-ejdTdddDdUZ.ejdVdddWdUZ/ejdXdddYdUZ0ejdZdd[d\Z1ejejd]d^d_d`dadOdbdcdddedfdgdh d ddiZ2ejej ej+ejej+ejejejej+ejejejejej+ejejejejejejej+ejejejejej+ejejejejejZ3ejejej$d@d1dAdjdEZ4ejejejZ5ejejejddkZ6ejejdldmdngdodpZ7ejejejddkZ8ejejdqgd'drgddsZ9ejejdtgd'dugddsZ:e,dvdd dDdwZ;ej ejeddDdxZej$d@d1d@d dd}d|Z?ejd~ddddZ@d=S)RegistrationInputSpecrrz--dimensionality %dTzimage dimension (2 or 3))rrr)rzQImage to which the moving_image should be transformed(usually a structural image))rrz%sz2.1.0fixed_image_maskszIMask used to limit metric sampling region of the fixed imagein all stages)rrmax_verxorrNULLz2.2.0fixed_image_maskzMasks used to limit metric sampling region of the fixed image, defined per registration stage(Use "NULL" to omit a mask at a given stage))Zmin_verrwrz{Image that will be registered to the space of fixed_image. This is theimage on which the transformations will be applied tomoving_image_maskszJmask used to limit metric sampling region of the moving imagein all stages)rr rvrwrmoving_image_maskzMasks used to limit metric sampling region of the moving image, defined per registration stage(Use "NULL" to omit a mask at a given stage)z--save-state %sFzEFilename for saving the internal restorable state of the registration)rrrz--restore-state %szHFilename for restoring the internal restorable state of the registrationzA transform or a list of transforms that should be applied before the registration begins. Note that, when a list is given, the transformations are applied in reverse order.initial_moving_transform_com)rrrwinitial_moving_transformzOne boolean or a list of booleans that indicatewhether the inverse(s) of the transform(s) definedin initial_moving_transform should be used.)r rrwrr zAlign the moving_image and fixed_image before registration using the geometric center of the images (=0), the image intensities (=1), or the origin of the images (=2).)rrwrr MeanSquaresDemonsGCrMatteszvthe metric(s) to use for each stage. Note that multiple metrics per stage are not supported in ANTS 1.9.1 and earlier.g?)rrzIthe metric weight(s) for each stage. The weights must sum to 1 per stage.)rrr rrr4z[the number of bins in each stage for the MI and Mattes metric, the radius for other metrics)rrr rNoneRegularRandomNz8the metric sampling strategy (strategies) for each stage)traitr rg)lowhighsampling_strategyz7the metric sampling percentage(s) to use for each stager)r)rz/Histogram match the images before registration.)defaultrrZLinearZNearestNeighborZCosineWindowedSincZWelchWindowedSincZHammingWindowedSincZLanczosWindowedSincBSpline MultiLabelGaussian GenericLabel)rrz--write-composite-transform %d)rr'rrz--collapse-output-transforms %dzCollapse output transforms. Specifically, enabling this option combines all adjacent linear transforms and composes all adjacent displacement field transforms before writing the results to disk.z$--initialize-transforms-per-stage %dabInitialize linear transforms from the previous stage. By enabling this option, the current linear stage transform is directly intialized from the previous stages linear transform; this allows multiple linear stages to be run where each stage directly updates the estimated linear transform from the previous stage. (e.g. Translation -> Rigid -> Affine). z --float %dz-Use float instead of double for computations.)rr'rRigidAffineCompositeAffine Similarity TranslationZGaussianDisplacementFieldZTimeVaryingVelocityFieldZTimeVaryingBSplineVelocityFieldr"Z BSplineSyNZ ExponentialZBSplineExponential)rraThis option allows the user to restrict the optimization of the displacement field, translation, rigid or affine transform on a per-component basis. For example, if one wants to limit the deformation or rotation of 3-D volume to the first two dimensions, this is possible by specifying a weight vector of '1x1x0' for a deformation field or '1x1x0x1x1x0' for a rigid transformation. Low-dimensional restriction only works if there are no preceding transformations.)rmmZvoxr<zunits for smoothing sigmas)r rgư>r;)rrZminlenr r convergence_threshold transform)rrr) hash_filesroutput_warped_image)rr rz'The Upper quantile to clip image ranges)rrrrrrz'The Lower quantile to clip image rangesz-v)rr'rZnohash)Ar+r,r-rr.r/r rr0ryEitherrur1r{rz save_stateZ restore_stater}r9invert_initial_moving_transformr|Zmetric_item_traitr2Zmetric_stage_traitrr3Zmetric_weight_item_traitZmetric_weight_stage_traitr4r5Zradius_bins_item_traitZradius_bins_stage_traitradius_or_number_of_binsZsampling_strategy_item_traitZsampling_strategy_stage_traitrRangeZsampling_percentage_item_traitZsampling_percentage_stage_traitsampling_percentageuse_estimate_learning_rate_oncer: interpolationTuplerinterpolation_parameterswrite_composite_transformcollapse_output_transformsZinitialize_transforms_per_stagefloat transformstransform_parametersrestrict_deformationr;r< sigma_unitsshrink_factorsrconvergence_window_sizer7routput_inverse_warped_imagewinsorize_upper_quantilewinsorize_lower_quantileverboser@r@r@rArts       rtc@seZdZejeddddZejeddddZejeddddZejej ddZ ejej ddZ ejej d dZ edd d Z ed dZed dZeddZeddZejddZejddZdS)RegistrationOutputSpecT)rz2List of output transforms for forward registration)rzRList of output transforms for forward registration reversed for antsApplyTransformz2List of output transforms for reverse registrationz5List of flags corresponding to the forward transformszUList of flags corresponding to the forward transforms reversed for antsApplyTransformz5List of flags corresponding to the reverse transformszComposite transform file)rrz Inverse composite transform filezOutputs warped imagez'Outputs the inverse of the warped imagez+The saved registration state to be restoredzthe final value of metricz*the total elapsed time as reported by ANTsN)r+r,r-rr2rforward_transformsreverse_forward_transformsreverse_transformsr9forward_invert_flagsreverse_forward_invert_flagsreverse_invert_flagscomposite_transforminverse_composite_transform warped_imageinverse_warped_imagerr3 metric_value elapsed_timer@r@r@rArRs*      rcseZdZdZdZdZeZeZ dZ ddddd gZ fd d Z d&fd d Z ddZeddZddZddZd'ddZddZddZddZfdd Zd(d!d"Zd#d$ZZS)) Registrationa\ANTs Registration command for registration of images `antsRegistration `_ registers a ``moving_image`` to a ``fixed_image``, using a predefined (sequence of) cost function(s) and transformation operations. The cost function is defined using one or more 'metrics', specifically local cross-correlation (``CC``), Mean Squares (``MeanSquares``), Demons (``Demons``), global correlation (``GC``), or Mutual Information (``Mattes`` or ``MI``). ANTS can use both linear (``Translation``, ``Rigid``, ``Affine``, ``CompositeAffine``, or ``Translation``) and non-linear transformations (``BSpline``, ``GaussianDisplacementField``, ``TimeVaryingVelocityField``, ``TimeVaryingBSplineVelocityField``, ``SyN``, ``BSplineSyN``, ``Exponential``, or ``BSplineExponential``). Usually, registration is done in multiple *stages*. For example first an Affine, then a Rigid, and ultimately a non-linear (Syn)-transformation. antsRegistration can be initialized using one ore more transforms from moving_image to fixed_image with the ``initial_moving_transform``-input. For example, when you already have a warpfield that corrects for geometrical distortions in an EPI (functional) image, that you want to apply before an Affine registration to a structural image. You could put this transform into 'intial_moving_transform'. The Registration-interface can output the resulting transform(s) that map moving_image to fixed_image in a single file as a ``composite_transform`` (if ``write_composite_transform`` is set to ``True``), or a list of transforms as ``forwards_transforms``. It can also output inverse transforms (from ``fixed_image`` to ``moving_image``) in a similar fashion using ``inverse_composite_transform``. Note that the order of ``forward_transforms`` is in 'natural' order: the first element should be applied first, the last element should be applied last. Note, however, that ANTS tools always apply lists of transformations in reverse order (the last transformation in the list is applied first). Therefore, if the output forward_transforms is a list, one can not directly feed it into, for example, ``ants.ApplyTransforms``. To make ``ants.ApplyTransforms`` apply the transformations in the same order as ``ants.Registration``, you have to provide the list of transformations in reverse order from ``forward_transforms``. ``reverse_forward_transforms`` outputs ``forward_transforms`` in reverse order and can be used for this purpose. Note also that, because ``composite_transform`` is always a single file, this output is preferred for most use-cases. More information can be found in the `ANTS manual `_. See below for some useful examples. Examples -------- Set up a Registration node with some default settings. This Node registers 'fixed1.nii' to 'moving1.nii' by first fitting a linear 'Affine' transformation, and then a non-linear 'SyN' transformation, both using the Mutual Information-cost metric. The registration is initialized by first applying the (linear) transform trans.mat. >>> import copy, pprint >>> from nipype.interfaces.ants import Registration >>> reg = Registration() >>> reg.inputs.fixed_image = 'fixed1.nii' >>> reg.inputs.moving_image = 'moving1.nii' >>> reg.inputs.output_transform_prefix = "output_" >>> reg.inputs.initial_moving_transform = 'trans.mat' >>> reg.inputs.transforms = ['Affine', 'SyN'] >>> reg.inputs.transform_parameters = [(2.0,), (0.25, 3.0, 0.0)] >>> reg.inputs.number_of_iterations = [[1500, 200], [100, 50, 30]] >>> reg.inputs.dimension = 3 >>> reg.inputs.write_composite_transform = True >>> reg.inputs.collapse_output_transforms = False >>> reg.inputs.initialize_transforms_per_stage = False >>> reg.inputs.metric = ['Mattes']*2 >>> reg.inputs.metric_weight = [1]*2 # Default (value ignored currently by ANTs) >>> reg.inputs.radius_or_number_of_bins = [32]*2 >>> reg.inputs.sampling_strategy = ['Random', None] >>> reg.inputs.sampling_percentage = [0.05, None] >>> reg.inputs.convergence_threshold = [1.e-8, 1.e-9] >>> reg.inputs.convergence_window_size = [20]*2 >>> reg.inputs.smoothing_sigmas = [[1,0], [2,1,0]] >>> reg.inputs.sigma_units = ['vox'] * 2 >>> reg.inputs.shrink_factors = [[2,1], [3,2,1]] >>> reg.inputs.use_estimate_learning_rate_once = [True, True] >>> reg.inputs.use_histogram_matching = [True, True] # This is the default >>> reg.inputs.output_warped_image = 'output_warped_image.nii.gz' >>> reg.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 0 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' >>> reg.run() # doctest: +SKIP Same as reg1, but first invert the initial transform ('trans.mat') before applying it. >>> reg.inputs.invert_initial_moving_transform = True >>> reg1 = copy.deepcopy(reg) >>> reg1.inputs.winsorize_lower_quantile = 0.025 >>> reg1.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.025, 1.0 ] --write-composite-transform 1' >>> reg1.run() # doctest: +SKIP Clip extremely high intensity data points using winsorize_upper_quantile. All data points higher than the 0.975 quantile are set to the value of the 0.975 quantile. >>> reg2 = copy.deepcopy(reg) >>> reg2.inputs.winsorize_upper_quantile = 0.975 >>> reg2.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 0.975 ] --write-composite-transform 1' Clip extremely low intensity data points using winsorize_lower_quantile. All data points lower than the 0.025 quantile are set to the original value at the 0.025 quantile. >>> reg3 = copy.deepcopy(reg) >>> reg3.inputs.winsorize_lower_quantile = 0.025 >>> reg3.inputs.winsorize_upper_quantile = 0.975 >>> reg3.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.025, 0.975 ] --write-composite-transform 1' Use float instead of double for computations (saves memory usage) >>> reg3a = copy.deepcopy(reg) >>> reg3a.inputs.float = True >>> reg3a.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --float 1 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' Force to use double instead of float for computations (more precision and memory usage). >>> reg3b = copy.deepcopy(reg) >>> reg3b.inputs.float = False >>> reg3b.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --float 0 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' 'collapse_output_transforms' can be used to put all transformation in a single 'composite_transform'- file. Note that forward_transforms will now be an empty list. >>> # Test collapse transforms flag >>> reg4 = copy.deepcopy(reg) >>> reg4.inputs.save_state = 'trans.mat' >>> reg4.inputs.restore_state = 'trans.mat' >>> reg4.inputs.initialize_transforms_per_stage = True >>> reg4.inputs.collapse_output_transforms = True >>> outputs = reg4._list_outputs() >>> pprint.pprint(outputs) # doctest: +ELLIPSIS, {'composite_transform': '...data/output_Composite.h5', 'elapsed_time': , 'forward_invert_flags': [], 'forward_transforms': [], 'inverse_composite_transform': '...data/output_InverseComposite.h5', 'inverse_warped_image': , 'metric_value': , 'reverse_forward_invert_flags': [], 'reverse_forward_transforms': [], 'reverse_invert_flags': [], 'reverse_transforms': [], 'save_state': '...data/trans.mat', 'warped_image': '...data/output_warped_image.nii.gz'} >>> reg4.cmdline 'antsRegistration --collapse-output-transforms 1 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 1 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --restore-state trans.mat --save-state trans.mat --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' >>> # Test collapse transforms flag >>> reg4b = copy.deepcopy(reg4) >>> reg4b.inputs.write_composite_transform = False >>> outputs = reg4b._list_outputs() >>> pprint.pprint(outputs) # doctest: +ELLIPSIS, {'composite_transform': , 'elapsed_time': , 'forward_invert_flags': [False, False], 'forward_transforms': ['...data/output_0GenericAffine.mat', '...data/output_1Warp.nii.gz'], 'inverse_composite_transform': , 'inverse_warped_image': , 'metric_value': , 'reverse_forward_invert_flags': [False, False], 'reverse_forward_transforms': ['...data/output_1Warp.nii.gz', '...data/output_0GenericAffine.mat'], 'reverse_invert_flags': [True, False], 'reverse_transforms': ['...data/output_0GenericAffine.mat', '...data/output_1InverseWarp.nii.gz'], 'save_state': '...data/trans.mat', 'warped_image': '...data/output_warped_image.nii.gz'} >>> reg4b.aggregate_outputs() # doctest: +SKIP >>> reg4b.cmdline 'antsRegistration --collapse-output-transforms 1 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 1 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --restore-state trans.mat --save-state trans.mat --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 0' One can use multiple similarity metrics in a single registration stage.The Node below first performs a linear registation using only the Mutual Information ('Mattes')-metric. In a second stage, it performs a non-linear registration ('Syn') using both a Mutual Information and a local cross-correlation ('CC')-metric. Both metrics are weighted equally ('metric_weight' is .5 for both). The Mutual Information- metric uses 32 bins. The local cross-correlations (correlations between every voxel's neighborhoods) is computed with a radius of 4. >>> # Test multiple metrics per stage >>> reg5 = copy.deepcopy(reg) >>> reg5.inputs.fixed_image = 'fixed1.nii' >>> reg5.inputs.moving_image = 'moving1.nii' >>> reg5.inputs.metric = ['Mattes', ['Mattes', 'CC']] >>> reg5.inputs.metric_weight = [1, [.5,.5]] >>> reg5.inputs.radius_or_number_of_bins = [32, [32, 4] ] >>> reg5.inputs.sampling_strategy = ['Random', None] # use default strategy in second stage >>> reg5.inputs.sampling_percentage = [0.05, [0.05, 0.10]] >>> reg5.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 0.5, 32, None, 0.05 ] --metric CC[ fixed1.nii, moving1.nii, 0.5, 4, None, 0.1 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' ANTS Registration can also use multiple modalities to perform the registration. Here it is assumed that fixed1.nii and fixed2.nii are in the same space, and so are moving1.nii and moving2.nii. First, a linear registration is performed matching fixed1.nii to moving1.nii, then a non-linear registration is performed to match fixed2.nii to moving2.nii, starting from the transformation of the first step. >>> # Test multiple inputS >>> reg6 = copy.deepcopy(reg5) >>> reg6.inputs.fixed_image = ['fixed1.nii', 'fixed2.nii'] >>> reg6.inputs.moving_image = ['moving1.nii', 'moving2.nii'] >>> reg6.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 0.5, 32, None, 0.05 ] --metric CC[ fixed2.nii, moving2.nii, 0.5, 4, None, 0.1 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' Different methods can be used for the interpolation when applying transformations. >>> # Test Interpolation Parameters (BSpline) >>> reg7a = copy.deepcopy(reg) >>> reg7a.inputs.interpolation = 'BSpline' >>> reg7a.inputs.interpolation_parameters = (3,) >>> reg7a.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation BSpline[ 3 ] --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' >>> # Test Interpolation Parameters (MultiLabel/Gaussian) >>> reg7b = copy.deepcopy(reg) >>> reg7b.inputs.interpolation = 'Gaussian' >>> reg7b.inputs.interpolation_parameters = (1.0, 1.0) >>> reg7b.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Gaussian[ 1.0, 1.0 ] --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' BSplineSyN non-linear registration with custom parameters. >>> # Test Extended Transform Parameters >>> reg8 = copy.deepcopy(reg) >>> reg8.inputs.transforms = ['Affine', 'BSplineSyN'] >>> reg8.inputs.transform_parameters = [(2.0,), (0.25, 26, 0, 3)] >>> reg8.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform BSplineSyN[ 0.25, 26, 0, 3 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' Mask the fixed image in the second stage of the registration (but not the first). >>> # Test masking >>> reg9 = copy.deepcopy(reg) >>> reg9.inputs.fixed_image_masks = ['NULL', 'fixed1.nii'] >>> reg9.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ trans.mat, 1 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --masks [ NULL, NULL ] --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --masks [ fixed1.nii, NULL ] --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' Here we use both a warpfield and a linear transformation, before registration commences. Note that the first transformation that needs to be applied ('ants_Warp.nii.gz') is last in the list of 'initial_moving_transform'. >>> # Test initialization with multiple transforms matrices (e.g., unwarp and affine transform) >>> reg10 = copy.deepcopy(reg) >>> reg10.inputs.initial_moving_transform = ['func_to_struct.mat', 'ants_Warp.nii.gz'] >>> reg10.inputs.invert_initial_moving_transform = [False, False] >>> reg10.cmdline 'antsRegistration --collapse-output-transforms 0 --dimensionality 3 --initial-moving-transform [ func_to_struct.mat, 0 ] [ ants_Warp.nii.gz, 0 ] --initialize-transforms-per-stage 0 --interpolation Linear --output [ output_, output_warped_image.nii.gz ] --transform Affine[ 2.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32, Random, 0.05 ] --convergence [ 1500x200, 1e-08, 20 ] --smoothing-sigmas 1.0x0.0vox --shrink-factors 2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --transform SyN[ 0.25, 3.0, 0.0 ] --metric Mattes[ fixed1.nii, moving1.nii, 1, 32 ] --convergence [ 100x50x30, 1e-09, 20 ] --smoothing-sigmas 2.0x1.0x0.0vox --shrink-factors 3x2x1 --use-estimate-learning-rate-once 1 --use-histogram-matching 1 --winsorize-image-intensities [ 0.0, 1.0 ] --write-composite-transform 1' rZantsRegistrationFrrrrrc s"tt|jf|d|_d|_dS)N)rbr__init__ _elapsed_time _metric_value)rMrJ)rgr@rArszRegistration.__init__rcstt|j|}|jp|j}|r|jd}xZ|ddd D]H}|jjdrdt|jj dd|_ q:d|kr:t|jdd|_ Pq:W|S) N r zTotal elapsed time:zTotal elapsed time: rZ DIAGNOSTICrQr) rbr_run_interfacestdoutmergedsplitstrip startswithrreplacerr)rMruntimeZcorrect_return_codesoutputlinesl)rgr@rArs  zRegistration._run_interfacec sjj|}tjjdjjd|jj|jj|jj|d}tjjrtjjrtjj|}|rt||d<tjj rjj rjj |}|r||d<t |t rht |j }t t dt|}t }x|D]tfdd|D} tjjdkrjjd| d<njj| d<tjjdkrHjjd| d <njj| d <|j| qWn|g}fd d|DS) z Format the antsRegistration -m metric argument(s). Parameters ---------- index: the stage index r)r0r1rweightradius_or_binsoptionalrrcsg|]\}}||fqSr@r@)rYkv)ir@rAr\5sz/Registration._format_metric..r r0r1csg|]}jf|qSr@)_format_metric_argument)rYre)rMr@rAr\Fs)rJrdictr0r1r4rr rr isinstancelistitemsrHrIrK) rMrZZ name_inputZ stage_inputsrrrZindexesspecstempr@)rrMrA_format_metric s@           zRegistration._format_metriccKsd|d|d|d|d|df}d|kr8|d}nd|krHtj}nd}|rt|d |7}d|krt|d |d7}|d 7}|S) Nz%s[ %s, %s, %g, %drr0r1rrrrz, %sz, %gz ])rDEF_SAMPLING_STRATEGY)kwargsrNrr@r@rArHs"   z$Registration._format_metric_argumentcCsXg}|jd|jj|djdd|jj|D}|jd||jddj|S)Nz%s[ z, cSsg|] }t|qSr@)str)rYelementr@r@rAr\isz2Registration._format_transform..z%sz ]r)rKrJrrLr)rMrZrNrTr@r@rA_format_transformes zRegistration._format_transformc Csg}xtt|jjD]}|jd|j|x |j|D]}|jd|q>W|jd|j|t|jj r|jd|j |jj ||jj |fn|jd|j |jj ||jd|j |jj |t|jj r|jd|jj |t|jjr:t|jjtr |jj}n |jj|}|jd|t|jjrd|jd |j |jj|tt|jjt|jjfrt|jjrt|jj}|t|d kr|nd }nd }t|jjrt|jj}|t|d kr|nd }nd }|jd ||fqWdj|S)Nz--transform %sz --metric %sz--convergence %sz--smoothing-sigmas %s%sz--smoothing-sigmas %sz--shrink-factors %sz$--use-estimate-learning-rate-once %dz--use-histogram-matching %dz--restrict-deformation %sr rrxz--masks [ %s, %s ]rG)rHrIrJrrKrr_format_convergencer rr_r<rrr:rboolranyrurzrrL) rMrNrOrZhistvalZ fixed_masksZ fixed_maskZ moving_masksZ moving_maskr@r@rA_format_registrationosV       z!Registration._format_registrationcCsxd}|s>t|jjr:|jjr:|jj}t|tr:d|jj}|Sd}t|jjrt|jjrt|jj}t|trtd|jj}|S)Nz%s_Warped.nii.gzz%s_InverseWarped.nii.gz)r rJrrrr7r)rMinverseZoutput_filenameZinv_output_filenamer@r@rA_get_outputfilenamess      z!Registration._get_outputfilenamescCst|j|jj|}t|jj|kr0|jj|}n |jjd}t|jj|krZ|jj|}n |jjd}d|||fS)Nrz[ %s, %g, %d ])r_rJr;rIrr)rMrOZconvergence_iterZconvergence_valueZconvergence_wsr@r@rArs  z Registration._format_convergencecCsB|jj|jjks(td|jj|jjfd|_d|jj|jjfS)Nz2Upper bound MUST be more than lower bound: %g > %gTz(--winsorize-image-intensities [ %s, %s ])rJrr RuntimeError_quantilesDone)rMr@r@rA#_format_winsorize_image_intensitiess z0Registration._format_winsorize_image_intensitiescCsjt|jj}dg|}t|jjrBt|jj|kr:td|jj}ddt|jj|D}djdg|S)NrzcInputs "initial_moving_transform" and "invert_initial_moving_transform"should have the same length.cSs g|]\}}d|t|fqS)z [ %s, %d ])int)rYZxfmflagr@r@rAr\szARegistration._get_initial_transform_filenames..rGz--initial-moving-transform)rIrJr}r r ExceptionziprL)rMZ n_transformsZ invert_flagsrNr@r@rA _get_initial_transform_filenamess   z-Registration._get_initial_transform_filenamescs|dkr8t|jjr(d|jj|jjfSd|jjSnB|dkrH|jS|dkrX|jS|dkrt|jjrt|jjnd}d|jjd|jjd|fS|d kr|jj dkrt|jj rd|jj dj dd|jj DfSd|jj Sn|dkrL|j dd}|j dd}|r(|r(d|jj ||fS|r>d|jj |fSd|jj Sn.|dks`|dkrz|jsp|jSd|_dStt|j|||S)Nryz--masks [ %s, %s ]z --masks %srr}r|rz)--initial-moving-transform [ %s, %s, %d ]rrrrrz--interpolation %s[ %s ]z, cSsg|] }t|qSr@)r)rYparamr@r@rAr\sz,Registration._format_arg..z--interpolation %sr7F)rTz--output [ %s, %s, %s ]z--output [ %s, %s ]z --output %srrr)rrrr)r rJr{ryrrr|r0r1rrrLrr7rrrbrrc)rMrdrerfZdo_center_of_mass_init out_filenameinv_out_filename)rgr@rArcs`         zRegistration._format_argc Cs^ddddddddd|_|t|jjkr:|j|}|}nd }|rHd }nd }d |||f|fS) Nz Rigid.matz Affine.matzGenericAffine.matzSimilarity.matzTranslation.matz BSpline.txtz#DerivedInitialMovingTranslation.mat)rr GenericAffinerrrrInitialFzInverseWarp.nii.gzz Warp.nii.gzz%s%d%s)Zlow_dimensional_transform_maprkeys)rMprefixcountrrsuffixZ inverse_moder@r@rA_output_filenames9s   zRegistration._output_filenamescsjj}g|d<g|d<g|d<g|d<dgtjj}tjjrRjj}jjrjjd}t j j ||d<jjd}t j j ||d <nĈjj sXd }tjjr|djj7<|d|7<jj|d|d<d d |D|d|d<|tjj7}ntjj rjjj|d \}}jjj|d d\}}|djt j j ||djd|djd t j j ||djd d|d7}xttjjD]} jjj|jj| \}}jjj|jj| d\}}|djt j j ||dj||djd t j j ||djd ||d7}qWnd }fdd jjD} g} tjjstjj r| jd dt| r| jdt| s| jdx| D]} jjj|| dd\}}jjj|| dd\}}|djt j j ||dj||djt j j ||dj||d7}qWjdd} jdd}| rt j j | |d<|rt j j ||d<tjjrt j j jj|d<jr҈j|d<jrj|d<|dddd|d<|dddd|d<|S)NrrrrFz Composite.h5rzInverseComposite.h5rrcSsg|] }| qSr@r@)rYer@r@rAr\ssz.Registration._list_outputs..rTr csg|]}|jkqSr@)_linear_transform_names)rYt)rMr@rAr\srr")rrrrrrrrrr)rhrirIrJr}r rrr7rjrkrlrr|rrKinsertrHrrallrrrr)rMrmrfilenameZtransform_countZforward_filenameZforward_inversemodeZreverse_filenameZreverse_inversemoderZ is_linearZ collapse_listrrrr@)rMrArnOs                         zRegistration._list_outputsr)r)F)F)r+r,r-rorrprtrqrrrrrrrr staticmethodrrrrrrrrcrrnrsr@r@)rgrArps4s >  >   B rc @seZdZejdddddddZeddd d Zeddd d Zejd d dddddddZ ej dgddddZ ej dgdddZ ejddddgdddZejejddd dgdd!dZeddd"d#Zedd$gd%d&Zd'S)(MeasureImageSimilarityInputSpecrrr]z--dimensionality %dr z-Dimensionality of the fixed/moving image pair)rrrTz)Image to which the moving image is warped)rrrzFImage to apply transformation to (generally a coregistered functional)rrrr~rrz%s)rrrg?z(The "metricWeight" variable is not used.)r r'rrz^The number of bins in each stage for the MI and Mattes metric, or the radius for other metrics)r rrrrrzManner of choosing point set over which to optimize the metric. Defaults to "None" (i.e. a dense sampling of one sample per voxel).)r rrg)rrz[Percentage of points accessible to the sampling strategy over which to optimize the metric.z>> from nipype.interfaces.ants import MeasureImageSimilarity >>> sim = MeasureImageSimilarity() >>> sim.inputs.dimension = 3 >>> sim.inputs.metric = 'MI' >>> sim.inputs.fixed_image = 'T1.nii' >>> sim.inputs.moving_image = 'resting.nii' >>> sim.inputs.metric_weight = 1.0 >>> sim.inputs.radius_or_number_of_bins = 5 >>> sim.inputs.sampling_strategy = 'Regular' >>> sim.inputs.sampling_percentage = 1.0 >>> sim.inputs.fixed_image_mask = 'mask.nii' >>> sim.inputs.moving_image_mask = 'mask.nii.gz' >>> sim.cmdline 'MeasureImageSimilarity --dimensionality 3 --masks ["mask.nii","mask.nii.gz"] --metric MI["T1.nii","resting.nii",1.0,5,Regular,1.0]' c Cs8dj|jj|jj|jj|jj|jj|jj|jjd}|S)Nz--metric {metric}["{fixed_image}","{moving_image}",{metric_weight},{radius_or_number_of_bins},{sampling_strategy},{sampling_percentage}])rr0r1r4rrr) rWrJrr0r1r4rrr)rMrNr@r@rA_metric_constructor9s z*MeasureImageSimilarity._metric_constructorcCs4|jjr dj|jj|jjd}ndj|jjd}|S)Nz4--masks ["{fixed_image_mask}","{moving_image_mask}"])ryr{z--masks "{fixed_image_mask}")ry)rJr{rWry)rMrNr@r@rA_mask_constructorHs z(MeasureImageSimilarity._mask_constructorcs4|dkr|jS|dkr |jStt|j|||S)Nrry)rrrbrrc)rMrdrerf)rgr@rArcTs z"MeasureImageSimilarity._format_argNcCs&|j}|jjd}t|d|_|S)Nrr)rhrrrr)rMrZneeded_outputsrmrr@r@rAaggregate_outputs[s z(MeasureImageSimilarity.aggregate_outputs)NN)r+r,r-rorprrqrrrrrrcrrsr@r@)rgrArs rc @seZdZejddddddZeeddddd d Zeedddd d d Z e d ddddZ ej e ddddZejddddddddddd Zejddd d!Zej d"dd#d$d%Zej d&dd'd(d%Zejd)d*d+d,ddZd-S).RegistrationSynQuickInputSpecrrz-d %dTzimage dimension (2 or 3))rrr)rz-f %s...z.Fixed image or source image or reference image)rrrz-m %s...zMoving image or target imagerz-o %sz.A prefix that is prepended to all output files)rrrzNumber of threads (default = 1)z-n %d)r'rrrsrrasrbbrz-t %szTransform type * t: translation * r: rigid * a: rigid + affine * s: rigid + affine + deformable syn (default) * sr: rigid + deformable syn * b: rigid + affine + deformable b-spline syn * br: rigid + deformable b-spline syn )rrrFz-j %dzuse histogram matching)rr z-r %dzbhistogram bins for mutual information in SyN stage (default = 32))r'rrrz-s %dzespline distance for deformable B-spline SyN transform (default = 26)doublerz-p %sz!precision type (default = double)N)r+r,r-rr.r/r rr0r1r output_prefixr5r num_threadstransform_typer9r:Zhistogram_binsZspline_distanceprecision_typer@r@r@rAr bsf  r c@sHeZdZedddZedddZedddZedddZedddZdS) RegistrationSynQuickOutputSpecTz Warped image)rrzInverse warped imagez Affine matrixzForward warp fieldzInverse warp fieldN) r+r,r-rrr out_matrixforward_warp_fieldinverse_warp_fieldr@r@r@rArs     rcs<eZdZdZdZeZeZddZ fddZ ddZ Z S) RegistrationSynQuickaL Registration using a symmetric image normalization method (SyN). You can read more in Avants et al.; Med Image Anal., 2008 (https://www.ncbi.nlm.nih.gov/pubmed/17659998). Examples -------- >>> from nipype.interfaces.ants import RegistrationSynQuick >>> reg = RegistrationSynQuick() >>> reg.inputs.fixed_image = 'fixed1.nii' >>> reg.inputs.moving_image = 'moving1.nii' >>> reg.inputs.num_threads = 2 >>> reg.cmdline 'antsRegistrationSyNQuick.sh -d 3 -f fixed1.nii -r 32 -m moving1.nii -n 2 -o transform -p d -s 26 -t s' >>> reg.run() # doctest: +SKIP example for multiple images >>> from nipype.interfaces.ants import RegistrationSynQuick >>> reg = RegistrationSynQuick() >>> reg.inputs.fixed_image = ['fixed1.nii', 'fixed2.nii'] >>> reg.inputs.moving_image = ['moving1.nii', 'moving2.nii'] >>> reg.inputs.num_threads = 2 >>> reg.cmdline 'antsRegistrationSyNQuick.sh -d 3 -f fixed1.nii -f fixed2.nii -r 32 -m moving1.nii -m moving2.nii -n 2 -o transform -p d -s 26 -t s' >>> reg.run() # doctest: +SKIP zantsRegistrationSyNQuick.shcCsdS)z antsRegistrationSyNQuick.sh ignores environment variables, so override environment update from ANTSCommand class Nr@)rMr@r@rA_num_threads_updatesz(RegistrationSynQuick._num_threads_updatecs*|dkr|j|dStt|j|||S)Nrr)rrbrrc)rMnamerer)rgr@rArcsz RegistrationSynQuick._format_argcCsh|jj}tjj|jj}|d|d<|d|d<|d|d<|jjdkrd|d |d <|d |d <|S)Nz Warped.nii.gzrzInverseWarped.nii.gzrz0GenericAffine.matrrr r z 1Warp.nii.gzrz1InverseWarp.nii.gzr)rr r )rrrirjrkrlrJrr)rMrmZout_baser@r@rArns       z"RegistrationSynQuick._list_outputs) r+r,r-rorpr rqrrrrrcrnrsr@r@)rgrArs rc@s\eZdZejdddddddZedd d d d Zeedd dddddZ e ddd dddZ dS)CompositeTransformUtilInputSpecassemble disassemblez--%sr Tz>What to do with the transform inputs (assemble or disassemble))rrrrFz%srz-Output file path (only used for disassembly).)rrrr)rz%s...rzInput transform file(s))rrrrrr]zHA prefix that is prepended to all output files (only used for assembly).)rrrrN) r+r,r-rr.processrout_filer in_filerrr@r@r@rArs0rc@s*eZdZeddZeddZeddZdS) CompositeTransformUtilOutputSpeczAffine transform component)rzDisplacement field componentzCompound transformation fileN)r+r,r-rrCdisplacement_fieldr"r@r@r@rAr$s  r$cs<eZdZdZdZeZeZddZ fddZ ddZ Z S)CompositeTransformUtila ANTs utility which can combine or break apart transform files into their individual constituent components. Examples -------- >>> from nipype.interfaces.ants import CompositeTransformUtil >>> tran = CompositeTransformUtil() >>> tran.inputs.process = 'disassemble' >>> tran.inputs.in_file = 'output_Composite.h5' >>> tran.cmdline 'CompositeTransformUtil --disassemble output_Composite.h5 transform' >>> tran.run() # doctest: +SKIP example for assembling transformation files >>> from nipype.interfaces.ants import CompositeTransformUtil >>> tran = CompositeTransformUtil() >>> tran.inputs.process = 'assemble' >>> tran.inputs.out_file = 'my.h5' >>> tran.inputs.in_file = ['AffineTransform.mat', 'DisplacementFieldTransform.nii.gz'] >>> tran.cmdline 'CompositeTransformUtil --assemble my.h5 AffineTransform.mat DisplacementFieldTransform.nii.gz ' >>> tran.run() # doctest: +SKIP cCsdS)z CompositeTransformUtil ignores environment variables, so override environment update from ANTSCommand class Nr@)rMr@r@rAr:sz*CompositeTransformUtil._num_threads_updatecsD|dkr|jjdkrdS|dkr0|jjdkr0dStt|j|||S)Nrrrr"r )rJr!rbr&rc)rMrrer)rgr@rArcAs z"CompositeTransformUtil._format_argcCsp|jj}|jjdkrLtjjdj|jj|d<tjjdj|jj|d<|jjdkrltjj|jj |d<|S)Nr z00_{}_AffineTransform.matrCz'01_{}_DisplacementFieldTransform.nii.gzr%rr") rrrirJr!rjrkrlrWrr")rMrmr@r@rArnHs   z$CompositeTransformUtil._list_outputs) r+r,r-rorprrqr$rrrrcrnrsr@r@)rgrAr&s r&)rorjZutils.filemaniprbaserrrrr r r r rrrBrFrtrrrrrr rrrr$r&r@r@r@rAs8  mRs<EO<