rootlets¶
Segmentation of spinal nerve rootlets for T2w and MP2RAGE contrasts (T1w-INV1, T1w-INV2, and UNIT1)
This segmentation model for spinal nerve rootlets segmentation uses a 3D U-Net architecture, and was trained with the nnUNetV2 framework. It is a multiclass model, outputting a single segmentation image containing 8 classes representing the C2-T1 dorsal and ventral spinal cord nerve rootlets. Training data included images from healthy subjects across three datasets: spine-generic multi-subject (3T T2w, n=21), OpenNeuro ds004507 (3T T2w, n=7, 10 images), and private data (7T MP2RAGE, n=15, 3 contrasts per subject, 45 images).
Reference¶
@misc{krejci2025rootletsegdeeplearningmethod,
title={RootletSeg: Deep learning method for spinal rootlets segmentation across MRI contrasts},
author={Katerina Krejci and Jiri Chmelik and Sandrine Bédard and Falk Eippert and Ulrike Horn and Virginie Callot and Julien Cohen-Adad and Jan Valosek},
year={2025},
eprint={2509.16255},
archivePrefix={arXiv},
primaryClass={q-bio.TO},
url={https://arxiv.org/abs/2509.16255},
}
Project URL: https://github.com/ivadomed/model-spinal-rootlets
usage: sct_deepseg rootlets [-i <file> [<file> ...]] [-o <str>] [-install]
[-custom-url CUSTOM_URL [CUSTOM_URL ...]]
[-largest {0,1}] [-fill-holes {0,1}]
[-remove-small REMOVE_SMALL [REMOVE_SMALL ...]]
[-qc <folder>] [-qc-dataset <str>]
[-qc-subject <str>] [-qc-seg <file>] [-h] [-v <int>]
[-r {0,1}] [-test-time-aug]
INPUT/OUTPUT¶
- -i
Image filename(s) to segment. If segmenting multiple files, separate filenames with a space.
- -o
Output file name. The chosen filename will be used as a base name, and model-specific suffixes will be added to the end depending on the type of output (e.g. ‘_cord.nii.gz’, ‘_gm.nii.gz’, etc.).
TASKS¶
- -install
Install models that are required for specified task.
Default:
False- -custom-url
URL(s) pointing to the
.zipasset for a model release. This option can be used with-installto install a specific version of a model. To use this option, navigate to the ‘Releases’ page of the model, find release you wish to install, and right-click + copy the URL of the.ziplisted under ‘Assets’. Example:sct_deepseg rootlets -install -custom-url CUSTOM_URLsct_deepseg rootlets -i t2.nii.gz
PARAMETERS¶
- -largest
Possible choices: 0, 1
Keep the largest connected object from each output segmentation; if not set, all objects are kept.
Default:
0- -fill-holes
Possible choices: 0, 1
If set, small holes in the segmentation will be filled in automatically.
Default:
0- -remove-small
Minimal object size to keep with unit (mm3 or vox). A single value can be provided or one value per prediction class. Single value example: 1mm3, 5vox. Multiple values example: 10 20 10vox (remove objects smaller than 10 voxels for class 1 and 3, and smaller than 20 voxels for class 2).
- -test-time-aug
Perform test-time augmentation (TTA) by flipping the input image along all axes and averaging the resulting predictions. Note: The time it takes to run the model will increase due to the additional predictions.
Default:
False
MISC ARGUMENTS¶
- -qc
The path where the quality control generated content will be saved.
- -qc-dataset
If provided, this string will be mentioned in the QC report as the dataset the process was run on.
- -qc-subject
If provided, this string will be mentioned in the QC report as the subject the process was run on.
- -qc-seg
Segmentation file to use for cropping the QC. This option is useful when you want to QC a region that is different from the output segmentation. For example, it might be useful to provide a dilated cord segmentation to expand the QC field of view.
- -v
Possible choices: 0, 1, 2
Verbosity. 0: Display only errors/warnings, 1: Errors/warnings + info messages, 2: Debug mode.
Default:
1- -r
Possible choices: 0, 1
Remove temporary files.
Default:
1