Metadata-Version: 2.4
Name: pyfix
Version: 0.10.0
Summary: Python implementation of FSL's FIX tool for denoising
Author-email: Sean Fitzgibbon <sean.fitzgibbon@ndcn.ox.ac.uk>
License: Apache License Version 2.0
Project-URL: Repository, https://git.fmrib.ox.ac.uk/fsl/pyfix.git
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: cachetools
Requires-Dist: file-tree
Requires-Dist: fslpy>=3.21.1
Requires-Dist: jinja2
Requires-Dist: joblib
Requires-Dist: matplotlib
Requires-Dist: nibabel
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-learn>=1.3
Requires-Dist: seaborn
Requires-Dist: scipy
Requires-Dist: spectrum
Provides-Extra: extra
Requires-Dist: xgboost; extra == "extra"
Requires-Dist: optuna; extra == "extra"

# pyFIX

This package contains a python port of [FMRIB's ICA-based Xnoiseifier](https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/FIX) (`FIX`).

FIX attempts to auto-classify ICA components into "good" vs "bad" components, so that the bad components can be removed from the 4D FMRI data. FIX is intended to be run on single-session [MELODIC](https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/MELODIC) ICA output.


> This python port attempts to emulate `FIX` as closely as possible but is *not* a like-for-like replacement.  The primary difference is that the ensemble classifier that was used in `FIX`, and was implemented in `R`, is *not* used by `pyFIX`.  Instead we use the [XGBoost](https://xgboost.readthedocs.io/en/stable/) classifier by default, and also allow the user to use any classifier that conforms to the [scikit-learn](https://scikit-learn.org/stable/) classifier API.


## Usage

There is a drop-in command line replacement for `legacy FIX` for fMRI.  Simply call `fix` on the command line for usage instructions.


## Citation

> G. Salimi-Khorshidi, G. Douaud, C.F. Beckmann, M.F. Glasser, L. Griffanti S.M. Smith. Automatic denoising of functional MRI data: Combining independent component analysis and hierarchical fusion of classifiers. NeuroImage, 90:449-68, 2014

> L. Griffanti, G. Salimi-Khorshidi, C.F. Beckmann, E.J. Auerbach, G. Douaud, C.E. Sexton, E. Zsoldos, K. Ebmeier, N. Filippini, C.E. Mackay, S. Moeller, J.G. Xu, E. Yacoub, G. Baselli, K. Ugurbil, K.L. Miller, and S.M. Smith. ICA-based artefact removal and accelerated fMRI acquisition for improved resting state network imaging. NeuroImage, 95:232-47, 2014
