Data

Tools

Indexes

Applications

Experiments

Open Source Science

dl-direct

DL+DiReCT - Direct Cortical Thickness Estimation using Deep Learning-based Anatomy Segmentation and Cortex Parcellation

https://github.com/scan-nrad/dl-direct

Science Score: 39.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 14 DOI reference(s) in README
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.4%) to scientific vocabulary

Keywords

cortical-thickness deep-learning morphometry mri
Last synced: 6 months ago · JSON representation

Repository

DL+DiReCT - Direct Cortical Thickness Estimation using Deep Learning-based Anatomy Segmentation and Cortex Parcellation

Basic Info
  • Host: GitHub
  • Owner: SCAN-NRAD
  • License: bsd-3-clause
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 176 MB
Statistics
  • Stars: 26
  • Watchers: 3
  • Forks: 6
  • Open Issues: 4
  • Releases: 1
Topics
cortical-thickness deep-learning morphometry mri
Created about 5 years ago · Last pushed 10 months ago
Metadata Files
Readme License Citation

README.md

About DL+DiReCT

DL+DiReCT combines a deep learning-based neuroanatomy segmentation and cortex parcellation with a diffeomorphic registration technique to measure cortical thickness from T1w MRI.

Abstract

If you are using DL+DiReCT in your research, please cite (bibtex) the corresponding publication: Rebsamen, M, Rummel, C, Reyes, M, Wiest, R, McKinley, R. Direct cortical thickness estimation using deep learningbased anatomy segmentation and cortex parcellation. Human brain mapping. 2020; 41: 4804-4814. https://doi.org/10.1002/hbm.25159

Installation

Create virtual environment (optional)

Download and install Miniconda and create a new conda environment:

bash conda create -y -n DL_DiReCT python=3.11 source activate DL_DiReCT

Install DL+DiReCT

bash cd ${HOME} git clone https://github.com/SCAN-NRAD/DL-DiReCT.git cd DL-DiReCT pip install -e .

Usage

Run dl+direct on a T1-weighted MRI including skull-stripping (--bet) using HD-BET with: bash source activate DL_DiReCT dl+direct --subject <your_subj_id> --bet <path_to_t1_input.nii.gz> <output_dir>

Following files of interest are generated in the output directory: - T1w_norm.nii.gz Re-sampled input volume - T1w_norm_seg.nii.gz Segmentation - T1w_norm_thickmap.nii.gz Thickness map - result-vol.csv Segmentation volumes - result-thick.csv ROI-wise mean cortical thickness - result-thickstd.csv ROI-wise standard deviations of cortical thickness - label_def.csv Label definitions of the segmentation

Results may be collected into FreeSurfer alike statistics files with stats2table.

Contrast-enhanced (CE) MRI

To process images with a contrast agent (contrast-enhanced), use the option --model v6 (Rebsamen et al., 2022).

Available Models

The following models are available with the --model ... option: - v0: Default, for un-enhanced T1w MRI, cortex parcellation with Desikan-Killiany atlas (Rebsamen et al., 2020) - v6: For both contrast-enhanced and un-enhanced MRI (Rebsamen et al., 2022) - v7: Same as v6, with 74 region per hemisphere according the Destrieux atlas (Rebsamen et al., 2022)

Frequently Asked Questions

For further details, consult the corresponding publication and the FAQ or contact us

Owner

  • Name: Support Center for Advanced Neuroimaging (SCAN)
  • Login: SCAN-NRAD
  • Kind: organization
  • Location: Bern, Switzerland

University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital

GitHub Events

Total
  • Watch event: 5
  • Issue comment event: 1
  • Push event: 6
  • Pull request event: 2
  • Fork event: 3
Last Year
  • Watch event: 5
  • Issue comment event: 1
  • Push event: 6
  • Pull request event: 2
  • Fork event: 3

Dependencies

pyproject.toml pypi
  • HD_BET @ https://github.com/mrunibe/HD-BET/archive/refs/heads/master.zip
  • antspyx >=0.5.4
  • nibabel >=3.2.1
  • numpy <2.0.0
  • pandas >=0.25.3
  • pymeshlab >=2022.2.post4
  • pyradiomics @ https://github.com/AIM-Harvard/pyradiomics/archive/refs/heads/circle-ci-mac-os.zip ; python_version>='3.12'
  • pyradiomics >=3.0.1; python_version<'3.12'
  • scikit-image >=0.24.0
  • scikit-learn >=0.21.3
  • scipy >=1.3.3
  • torch >=1.3.1
  • trimesh >=3.22.3
  • vtk >=9.2.6