AFQ.tasks.structural
====================

.. py:module:: AFQ.tasks.structural


Attributes
----------

.. autoapisummary::

   AFQ.tasks.structural.logger


Functions
---------

.. autoapisummary::

   AFQ.tasks.structural.configure_ncpus_nthreads
   AFQ.tasks.structural.onnx_kwargs
   AFQ.tasks.structural.synthseg_model
   AFQ.tasks.structural.mx_model
   AFQ.tasks.structural.t1w_brain_mask
   AFQ.tasks.structural.t1_masked
   AFQ.tasks.structural.t1_subcortex
   AFQ.tasks.structural.get_structural_plan


Module Contents
---------------

.. py:data:: logger

.. py:function:: configure_ncpus_nthreads(numba_n_threads=None, low_memory=False)

   
   Configure the number of threads to use for Numba,
   and whether to use low-memory versions of algorithms
   where available


   :Parameters:

       **numba_n_threads** : int, optional
           The number of threads to use for Numba and DIPY tracking.
           If None, uses the number of available CPUs minus one.
           Default: None

       **low_memory** : bool, optional
           Whether to use low-memory versions of algorithms
           where available.
           Default: False














   ..
       !! processed by numpydoc !!

.. py:function:: onnx_kwargs(low_mem, onnx_execution_provider='CPUExecutionProvider', onnx_inter_threads=1)

   
   The execution provider to use for onnx models


   :Parameters:

       **onnx_execution_provider** : str, optional
           The execution provider to use for onnx models.
           By default this is set to CPUExecutionProvider
           which should work on all systems. If you have a
           compatible GPU and the appropriate onnxruntime installed
           you can set this to "CUDAExecutionProvider" or
           "OpenVINOExecutionProvider" for potentially faster
           inference.
           Default: "CPUExecutionProvider"

       **onnx_inter_threads** : int, optional
           The number of inter threads to use for onnx models.
           Increasing will increase memory usage significantly.
           Default: 1














   ..
       !! processed by numpydoc !!

.. py:function:: synthseg_model(t1_masked, citations, onnx_kwargs)

   
   full path to the synthseg2 model segmentations












   .. rubric:: References

   [1] Billot, Benjamin, et al. "Robust machine learning segmentation
       for large-scale analysis of heterogeneous clinical brain MRI
       datasets." Proceedings of the National Academy of Sciences 120.9
       (2023): e2216399120.
   [2] Billot, Benjamin, et al. "SynthSeg: Segmentation of brain MRI scans
       of any contrast and resolution without retraining." Medical image
       analysis 86 (2023): 102789.

   .. only:: latex

      




   ..
       !! processed by numpydoc !!

.. py:function:: mx_model(t1_file, t1w_brain_mask, citations, onnx_kwargs)

   
   full path to the multi-axial model for brain extraction
   outputs












   .. rubric:: References

   [1] Birnbaum, Andrew M., et al. "Full-head segmentation of MRI
       with abnormal brain anatomy: model and data release." Journal of
       Medical Imaging 12.5 (2025): 054001-054001.

   .. only:: latex

      




   ..
       !! processed by numpydoc !!

.. py:function:: t1w_brain_mask(t1_file, citations, onnx_kwargs, brain_mask_definition=None)

   
   full path to a nifti file containing brain mask from T1w image


   :Parameters:

       **brain_mask_definition** : instance from `AFQ.definitions.image`, optional
           This will be used to create
           the brain mask, which gets applied before registration to a
           template.
           If you want no brain mask to be applied, use FullImage.
           If None, use Brainchop Mindgrab model.
           Default: None










   .. rubric:: References

   [1] Masoud, M., Hu, F., & Plis, S. (2023). Brainchop: In-browser MRI
       volumetric segmentation and rendering. Journal of Open Source
       Software, 8(83), 5098.
       https://doi.org/10.21105/joss.05098

   .. only:: latex

      




   ..
       !! processed by numpydoc !!

.. py:function:: t1_masked(t1_file, t1w_brain_mask)

   
   full path to a nifti file containing the T1w masked
















   ..
       !! processed by numpydoc !!

.. py:function:: t1_subcortex(t1_masked, citations, onnx_kwargs)

   
   full path to a nifti file containing segmentation of
   subcortical structures from T1w image using Brainchop












   .. rubric:: References

   [1] Masoud, M., Hu, F., & Plis, S. (2023). Brainchop: In-browser MRI
       volumetric segmentation and rendering. Journal of Open Source
       Software, 8(83), 5098.
       https://doi.org/10.21105/joss.05098

   .. only:: latex

      




   ..
       !! processed by numpydoc !!

.. py:function:: get_structural_plan(kwargs)