DWIPrep is a robust and easy-to-use pipeline for preprocessing of diverse dMRI data. The transparent workflow dispenses of manual intervention, thereby ensuring the reproducibility of the results.
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.
We should integrate tensor estimation and its derivatives into the pipeline.
enhancementWe need to build interfaces for tools that will be useful for the preprocessing pipeline. This list will probably change, but it's a good place to start:
Fixes #17 . This merge includes both the addition of gradients' rotation due to transformations applied to the DWI series and the storage of the transformed series and their associated files in BIDS-compatible format.
It must be certain that all linear and non-linear transformation performed on the DWI data is also reflected in the corresponding B vector and values. I saw that a similar issue was already referred to here, so it should be easy to manage.
Basically what we need to do is convert FSL or ANTs' transformation matrices into mrtirx3's format and than apply it to the DWI data in .mif format, since the above-mention thread declares that mrtrix deals with such transformations so it should be safe as long as we keep it in mrtrix's playground (.mif files).
enhancementFixes #5, #13 and sort-of fixes #12. Derivatives handling in a BIDS-compatible manner now takes places under a dedicated workflow rather than as scattered nodes. I also did my best to try to fit this pipeline's outputs to nipreps' format, but didn't manage to do so perfectly. The main issue I've encountered in this regards is tensor-derived metrics' naming. There doesn't seems to be an appropriate entity/label/datatype combination for these outputs. Had to make one of my own.
All things considered, I've done some major refactoring and the code is much more readable now. I'll make some efforts in the upcoming days to fully document it.
We should follow nipreps' standard and define an outputnode that stores all workflow's outputs and inserts them as inputs to a workflow that defines their names.
enhancementAll output paths definitions should be carried out via nipreps' DerivativesDataSink instead of a custom made solution.
enhancementAfter a few trials (and errors), I came to the conclusion that it's better (in terms of time and quality) to use FSL's epi_reg functionality rather than freesurfer's bbreg. Anyway, it fixes #10
While in earlier projects I used other tools for cross-modalities, within-subject coregistration, I think it would be wise to implement a coregistration pipeline that used freesrufer's BBReg. It seems to me the gold standard in other projects, mainly nipy's, and I would like to conform to it.
It includes applying the calculated transform to all relevant outputs of the preprocessing pipeline.
After several iteration, I've found the most convenient way (for me) to generate the pipeline.
It's very messy at the moment, but the logic is solid:
It was stupid of me not to investigate nipype`s workflow engines before going into building one of my own. Anyway, dwiprep should really be based on this mechanism.
I was already building a mechanism that started to look like what is already there.
Would be nice to generate a subject-specific report (as done in projects like FMRIPrep.
Got a recommendation for jinja
enhancementPHASER: A Robust and Correspondence-Free Global Pointcloud Registration Ubuntu 18.04+ROS Melodic: Overview Pointcloud registration using correspondenc
Models Playground ??️ Upload a Preprocessed Dataset ?? Choose whether to perform Classification or Regression ?? Enter the Dependent Variable ?
NVIDIA Merlin NVIDIA Merlin is an open source library designed to accelerate recommender systems on NVIDIA’s GPUs. It enables data scientists, machine
NeurIPS 2021 Title: Distilling Robust and Non-Robust Features in Adversarial Exa
Medical image preprocessing and augmentation toolkit for deep learning. Part of the PyTorch Ecosystem.
Aiming at the common training datsets split, spectrum preprocessing, wavelength select and calibration models algorithm involved in the spectral analysis process, a complete algorithm library is established, which is named opensa (openspectrum analysis).
Torch-RecHub A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend. 安装 pip install torch-rechub 主要特性 scikit-learn风格易用
actions-includes Allows including an action inside another action (by preprocessing the Yaml file). Instead of using uses or run in your action step,
GD-VCR Code for Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning (EMNLP 2021). Research Questions and Aims: How well can a model perform o
GP-VAE This repository provides datasets and code for preprocessing, training and testing models for the paper: Diverse Text Generation via Variationa
Demo BERT ONNX pipeline written in rust This demo showcase the use of onnxruntime-rs with a GPU on CUDA 11 to run Bert in a data pipeline with Rust. R
[CVPR 2022] Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes Dongkwon Jin, Wonhui Park, Seong-Gyun Jeong, Heeyeon Kwon, and Cha
virtual_Keyboard this is a lite easy to use virtual keyboard project for anyone to use motivation I made this for this year's recruitment for RobEn AA
Interesting and reproducible research works should be conserved. This repository wraps a collection of deep neural network models into a simple and un
CCPD (Chinese City Parking Dataset, ECCV) UPdate on 10/03/2019. CCPD Dataset is now updated. We are confident that images in subsets of CCPD is much m
Note: This is an alpha (preview) version which is still under refining. nn-Meter is a novel and efficient system to accurately predict the inference l
Diverse Image Inpainting with Bidirectional and Autoregressive Transformers Installation pip install -r requirements.txt Dataset Preparation Given the
Diverse Structure Inpainting ArXiv | Papar | Supplementary Material | BibTex This repository is for the CVPR 2021 paper, "Generating Diverse Structure
Diverse Image Captioning with Context-Object Split Latent Spaces This repository is the PyTorch implementation of the paper: Diverse Image Captioning
101 Dec 1, 2022
19 Dec 10, 2022
419 Jan 3, 2023
35 Dec 26, 2022
1.6k Jan 6, 2023
50 Jan 7, 2023
67 Jan 4, 2023
70 Nov 4, 2022
24 Oct 13, 2022
18 Dec 29, 2022
14 Dec 17, 2022
106 Dec 29, 2022
3 Oct 23, 2021
16 Jun 16, 2022
1.8k Dec 30, 2022
244 Jan 6, 2023
25 Nov 9, 2022
152 Nov 4, 2022
34 Nov 21, 2022