Skip to main content

Harmonizing neuroimaging data across sites. Implementation of neurocombat using sklearn format

Project description

NeuroCombat-sklearn

License: MIT Version PythonVersion

Implementation of Combat harmonization method in scikit-learn compatible format.

The Combat harmonization/normalization method uses an parametric empirical Bayes framework to robustly adjust data for site/batch effects. The scikit-learn compatible format was used to facilitates the use of this harmonization method in machine learning projects.

This repository is developed by Walter Hugo Lopez Pinaya at King's College London and community contributors.

Installation

Requirements

User installation

If you already have a working installation of numpy and scipy, the easiest way to install neurocombat-sklearn is using pip :

pip install neurocombat-sklearn

Citation

If you find this code useful for your research, please cite:

@article{fortin2018harmonization,
  title={Harmonization of cortical thickness measurements across scanners and sites},
  author={Fortin, Jean-Philippe and Cullen, Nicholas and Sheline, Yvette I and Taylor, Warren D and Aselcioglu, Irem and Cook, Philip A and Adams, Phil and Cooper, Crystal and Fava, Maurizio and McGrath, Patrick J and others},
  journal={Neuroimage},
  volume={167},
  pages={104--120},
  year={2018},
  publisher={Elsevier}
}

@article{johnson2007adjusting,
  title={Adjusting batch effects in microarray expression data using empirical Bayes methods},
  author={Johnson, W Evan and Li, Cheng and Rabinovic, Ariel},
  journal={Biostatistics},
  volume={8},
  number={1},
  pages={118--127},
  year={2007},
  publisher={Oxford University Press}
}

Disclaimer

Based on:

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

neurocombat-sklearn-0.1.3.tar.gz (5.9 kB view hashes)

Uploaded Source

Built Distribution

neurocombat_sklearn-0.1.3-py3-none-any.whl (7.9 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page