dipy_brain_mask

Synopsis

Unified brain masking workflow supporting multiple methods.

Applies brain masking on each file found by ‘globing’ input_files and saves the results in a directory specified by out_dir.

Usage

dipy_brain_mask [OPTIONS] input_files

Input Parameters

• input_files

  Path to the input volumes. This path may contain wildcards to process multiple inputs at once.

General Options

• --method

  Brain masking method. Options are:

  • ‘median_otsu’: Classical median Otsu segmentation, DWI-focused.

  • ‘evac’: Deep learning EVACPlus method, T1-focused.

  • ‘synthseg’: Deep learning SynthSeg method, works for all modalities.

  (default: synthseg)

• --bvalues_files

  Path to the b-values files. Used only for ‘median_otsu’ method. This path may contain wildcards to process multiple inputs at once. (default: None)

• --b0_threshold

  Threshold to consider a volume as b0. Used only if bvalues_files is provided with ‘median_otsu’ method. (default: 50)

• --median_radius

  Radius (in voxels) of the applied median filter. Used only for ‘median_otsu’ method. (default: 2)

• --numpass

  Number of pass of the median filter. Used only for ‘median_otsu’ method. (default: 5)

• --vol_idx

  1D array representing indices of axis=-1 of a 4D input_volume. From the command line use something like ‘1,2,3-5,7’. Used only for ‘median_otsu’ method. This input is required for 4D volumes if bval files are not provided. If bval files are provided, vol_idx is ignored and b0 volumes are used for mask computation. (default: None)

• --dilate

  Number of iterations for binary dilation. Used only for ‘median_otsu’ method. (default: None)

• --finalize_mask

  Whether to remove potential holes or islands. Useful for solving minor errors. Used only for ‘median_otsu’ method. (default: False)

• --save_masked

  Save the masked volume in addition to the mask. (default: False)

• --use_cuda

  Use CUDA for GPU acceleration. Used only for ‘evac’ and ‘synthseg’ methods. (default: False)

Output Options

• --out_dir

  Output directory. (default: current directory)

• --out_mask

  Name of the mask volume to be saved. (default: brain_mask.nii.gz)

• --out_masked

  Name of the masked volume to be saved. (default: brain_masked.nii.gz)

References

Garyfallidis, E., M. Brett, B. Amirbekian, A. Rokem, S. Van Der Walt, M. Descoteaux, and I. Nimmo-Smith. Dipy, a library for the analysis of diffusion MRI data. Frontiers in Neuroinformatics, 1-18, 2014.