brainles-preprocessing 0.3.2

Tool for preprocessing tasks in biomedical imaging, with a focus on (but not limited to) multi-modal brain MRI

BrainLes-Preprocessing

BrainLes preprocessing is a comprehensive tool for preprocessing tasks in biomedical imaging, with a focus on (but not limited to) multi-modal brain MRI. It can be used to build modular preprocessing pipelines:

This includes normalization, co-registration, atlas registration and skulstripping / brain extraction.

BrainLes is written backend-agnostic meaning it allows to swap the registration, brain extraction tools and defacing tools.

Installation

With a Python 3.10+ environment you can install directly from pypi.org:

pip install brainles-preprocessing

Usage

A minimal example to register (to the standard atlas using ANTs) and skull strip (using HDBet) a t1c image (center modality) with 1 moving modality (flair) could look like this:

from pathlib import Path
from brainles_preprocessing.modality import Modality, CenterModality
from brainles_preprocessing.normalization.percentile_normalizer import (
    PercentileNormalizer,
)
from brainles_preprocessing.preprocessor import Preprocessor

patient_folder = Path("/home/marcelrosier/preprocessing/patient")

# specify a normalizer
percentile_normalizer = PercentileNormalizer(
    lower_percentile=0.1,
    upper_percentile=99.9,
    lower_limit=0,
    upper_limit=1,
)

# define center and moving modalities
center = CenterModality(
    modality_name="t1c",
    input_path=patient_folder / "t1c.nii.gz",
    normalizer=percentile_normalizer,
    # specify the output paths for the raw and normalized images of each step - here only for atlas registered and brain extraction
    raw_skull_output_path="patient/raw_skull_dir/t1c_skull_raw.nii.gz",
    raw_bet_output_path="patient/raw_bet_dir/t1c_bet_raw.nii.gz",
    raw_defaced_output_path="patient/raw_defaced_dir/t1c_defaced_raw.nii.gz",
    normalized_skull_output_path="patient/norm_skull_dir/t1c_skull_normalized.nii.gz",
    normalized_bet_output_path="patient/norm_bet_dir/t1c_bet_normalized.nii.gz",
    normalized_defaced_output_path="patient/norm_defaced_dir/t1c_defaced_normalized.nii.gz",
    # specify output paths for the brain extraction and defacing masks
    bet_mask_output_path="patient/masks/t1c_bet_mask.nii.gz",
    defacing_mask_output_path="patient/masks/t1c_defacing_mask.nii.gz",
)

moving_modalities = [
    Modality(
        modality_name="flair",
        input_path=patient_folder / "flair.nii.gz",
        normalizer=percentile_normalizer,
        # specify the output paths for the raw and normalized images of each step - here only for atlas registered and brain extraction
        raw_skull_output_path="patient/raw_skull_dir/fla_skull_raw.nii.gz",
        raw_bet_output_path="patient/raw_bet_dir/fla_bet_raw.nii.gz",
        raw_defaced_output_path="patient/raw_defaced_dir/fla_defaced_raw.nii.gz",
        normalized_skull_output_path="patient/norm_skull_dir/fla_skull_normalized.nii.gz",
        normalized_bet_output_path="patient/norm_bet_dir/fla_bet_normalized.nii.gz",
        normalized_defaced_output_path="patient/norm_defaced_dir/fla_defaced_normalized.nii.gz",
    )
]

# instantiate and run the preprocessor using defaults for registration/ brain extraction/ defacing backends
preprocessor = Preprocessor(
    center_modality=center,
    moving_modalities=moving_modalities,
)

preprocessor.run()

The package allows to choose registration backends, brain extraction tools and defacing methods.
An example notebook with 4 modalities and further outputs and customizations can be found following these badges:

For further information please have a look at our Jupyter Notebook tutorials in our tutorials repo (WIP).

Documentation

We provide a (WIP) documentation. Have a look here

FAQ

Please credit the authors by citing their work.

Registration

We currently provide support for ANTs (default), Niftyreg (Linux), eReg (experimental)

Atlas Reference

We provide the SRI-24 atlas from this publication. However, custom atlases in NIfTI format are supported.

Brain extraction

We currently provide support for HD-BET.

Defacing

We currently provide support for Quickshear.