conditional_shape

nighres.segmentation.conditional_shape(target_images, structures, contrasts, background=1, shape_atlas_probas=None, shape_atlas_labels=None, intensity_atlas_hist=None, skeleton_atlas_probas=None, skeleton_atlas_labels=None, map_to_atlas=None, map_to_target=None, atlas_file=None, max_iterations=80, max_difference=0.1, ngb_size=4, intensity_prior=1.0, save_data=False, overwrite=False, output_dir=None, file_name=None)[source]

Conditioanl Shape Parcellation

Estimates subcortical structures based on a multi-atlas approach on shape

Parameters:
  • target_images ([niimg]) – Input images to perform the parcellation from
  • structures (int) – Number of structures to parcellate
  • contrasts (int) – Number of image intensity contrasts
  • background (int) – Number of background tissue classes (default is 1)
  • shape_atlas_probas (niimg) – Pre-computed shape atlas from the shape levelsets (replacing them)
  • shape_atlas_labels (niimg) – Pre-computed shape atlas from the shape levelsets (replacing them)
  • intensity_atlas_hist (niimg) – Pre-computed intensity atlas from the contrast images (replacing them)
  • skeleton_atlas_probas (niimg) – Pre-computed skeleton atlas from the shape levelsets (replacing them)
  • skeleton_atlas_labels (niimg) – Pre-computed skeleton atlas from the shape levelsets (replacing them)
  • map_to_atlas (niimg) – Coordinate mapping from the target to the atlas (opt)
  • map_to_target (niimg) – Coordinate mapping from the atlas to the target (opt)
  • atlas_file (json) – File with atlas labels and metadata (opt)
  • max_iterations (int) – Maximum number of diffusion iterations to perform
  • max_difference (float) – Maximum difference between diffusion steps
  • ngb_size (int) – Number of neighbors to consider in the diffusion (default is 4)
  • intensity_prior (float) – Importance scaling factor for the intensities in [0,1] (default is 1.0)
  • save_data (bool) – Save output data to file (default is False)
  • overwrite (bool) – Overwrite existing results (default is False)
  • output_dir (str, optional) – Path to desired output directory, will be created if it doesn’t exist
  • file_name (str, optional) – Desired base name for output files with file extension (suffixes will be added)
Returns:

Dictionary collecting outputs under the following keys (suffix of output files in brackets)

  • max_spatial_proba (niimg): Maximum spatial probability map (_cspmax-sproba)
  • max_spatial_label (niimg): Maximum spatial probability labels (_cspmax-slabel)
  • max_combined_proba (niimg): Maximum spatial and intensity combined probability map (_cspmax-cproba)
  • max_combined_label (niimg): Maximum spatial and intensity combined probability labels (_cspmax-clabel)
  • max_proba (niimg): Maximum probability map (_cspmax-proba)
  • max_label (niimg): Maximum probability labels (_cspmax-label)
  • neighbors (niimg): Local neighborhood maps (_cspmax-ngb)
Return type:

dict

Notes

Original Java module by Pierre-Louis Bazin.