| | |

UNRAVEL – Utilizing tractography to uncover multi-fixel microstructure

Welcome to the UNRAVEL’s Github repository!

The documentation of the code is available on readthedocsLogin

Description

To unravel has two meanings :

  • to disentangle the fibers of
  • to resolve the intricacy, complexity, or obscurity of

With the UNRAVEL framework, we utilize tractography to unravel the microstructure of multi-fixel models.

This repository contains the code used to combine macroscopic tractography information with microscopic multi-fixel model estimates in order to improve the accuracy in the estimation of the microstructural properties of neural fibers in a specified tract.

Installing & importing

Online install

The UNRAVEL package is available through pip install under the name unravel-python. Note that the online version might not always be up to date with the latest changes.

pip install unravel-python

To upgrade the current version : pip install unravel-python --upgrade.

To install a specific version of the package, use

pip install unravel-python==1.0.0

All available versions are listed in PyPI. The package names follow the rules of semantic versioning.

To install the package with the optional dependencies, use

pip install unravel-python[viz]

Local install

If you want to download the latest version directly from GitHub, you can clone this repository

git clone https://github.com/DelinteNicolas/unravel.git

For a more frequent use of the library, you may wish to permanently add the package to your current Python environment. Navigate to the folder where this repository was cloned or downloaded (the folder containing the setup.py file) and install the package as follows

cd UNRAVEL
pip install .

If you have an existing install, and want to ensure package and dependencies are updated use –upgrade

pip install --upgrade .

Importing

At the top of your Python scripts, import the library as

import unravel

Checking current version installed

The version of the UNRAVEL package installed can be displayed by typing the following command in your python environment

unravel.__version__

or

pip show unravel-python

Uninstalling

pip uninstall unravel-python

Example data and code

An example use of the main methods and outputs of UNRAVEL is written in the example.py file. A tractogram of the middle anterior section of the corpus callosum is used as an example tractography input.

Publication & citation

Main publication DOI : 10.3389/fnins.2023.1199568

Cite article as : “Delinte N, Dricot L, Macq B, Gosse C, Van Reybroeck M and Rensonnet G (2023) Unraveling multi-fixel microstructure with tractography and angular weighting. Front. Neurosci. 17:1199568. doi: 10.3389/fnins.2023.1199568”

Thesis manuscript:

Similar Posts

  • | | |

    BIDS Managing and Analysis Tool

    > Github repository
    The BMAT software is a complete and easy-to-use local open-source neuroimaging analysis tool with a graphical user interface (GUI) that uses the BIDS format to organize and process brain MRI data for MS imaging research studies. BMAT provides the possibility to translate data from MRI scanners to the BIDS structure, create and manage BIDS datasets as well as develop and run automated processing pipelines.

    BMAT is now compatible to work with remote server using shared samba folder and a slurm scheduler to process data on remote server. It has to be noted that this feature has been implemented for users based in the Institute of NeuroSciences (IoNS) from UCLouvain. Therefore, it may not work easily with every servers, but feel free to fork the code and adapt it for your institue.

  • | | |

    Exploring Foundation Models Fine-Tuning for Cytology Tasks

    > Github repository
    In this paper, we explore the application of existing foundation models to cytological classification tasks, focusing on low-rank adaptation (LoRA), a parameter-efficient fine-tuning method well-suited to few-shot learning scenarios. We evaluate five foundation models across four cytological classification datasets. Our results demonstrate that fine-tuning the pre-trained backbones with LoRA significantly enhances model performance compared to merely fine-tuning the classifier head, achieving state-of-the-art results on both simple and complex classification tasks while requiring fewer data samples.

  • | | | | |

    Parrot

    PARROT, which stands for Platform for ARtificial intelligence guided Radiation Oncology Treatment, is a user-friendly, free, and open-source web platform. It allows users to visualize DICOM files, run AI models, display and evaluate predictions easily. The platform includes several trained state-of-the-art dose prediction and contour segmentation models. Users can also add their own models using…

  • | |

    Comunicare Analytics

    COMUNICARE Analytics est une plateforme d’analyse de données médicales et d’aide à la décision médicale développée par Comunicare Solutions. Conçue pour répondre aux besoins des professionnels de la santé, cette solution repose sur le framework de calcul distribué open-source Apache Spark, offrant des capacités d’analyse à grande échelle et des prédictions précises pour une prise…

  • | | | | | |

    MCsquare

    The use of Monte Carlo dose calculation instead of typical analytical algorithms can improve the accuracy of proton therapy treatment planning. Especially, range uncertainties are significantly reduced in heterogeneous anatomies. MCsquare, a new fast Monte Carlo code, has been developed to simulate proton PBS treatments with the accuracy and calculation speed required in the clinic….

  • |

    LiblineaR

    LiblineaR is an R package for large-scale linear modeling  supporting classification and regression of large datasets. The original software in C/C++ was developed by Prof. Chih-Jen Lin and his team at the Machine Learning Group of the Taiwan University. As most of our developments are done in the open source R language, we have developed the R library LiblineaR, making all the…

Laisser un commentaire