intensity-normalization

Normalize the intensities of magnetic resonance (MR) images — T1-w, T2-w, FLAIR, PD-w — across scanners, sites, and sessions.

MR images have no consistent intensity scale; the inconsistency is an acquisition artifact that breaks downstream processing (especially ML). This package implements the standard fixes:

Individual methods — zscore, fcm, kde, whitestripe: plain functions of one image.
Population methods — nyul, lsq, ravel: learn a transform from a set of images; save it, apply it to new scans.
Tools — tissue membership maps, histogram plotting (validation), N4 preprocessing, co-registration (ANTs).

Install

pip install intensity-normalization            # or: uv add intensity-normalization
pip install "intensity-normalization[ants]"  # ravel registration, preprocess, coregister
pip install "intensity-normalization[plot]"  # histogram plotting

The CLI also runs without installing: uvx intensity-normalize --help.

Quickstart

import intensity_normalization as inorm

normed = inorm.whitestripe(t1w_image, mask=brain_mask)  # numpy or nibabel in → same type out

tx = inorm.nyul.fit(train_images, masks=train_masks)  # population: fit once...
tx.save("nyul.npz")
normed_new = tx(new_image)  # ...apply to new scans

intensity-normalize fcm t1w.nii.gz -m brain_mask.nii.gz -p
intensity-normalize nyul images/ -m masks/ -o normalized/ --save-state nyul.npz

Documentation — quickstart, how-to guides, choosing a method, algorithms, CLI, API, migrating to v4.

Reference

If you use this package, please cite the accompanying pre-print:

@article{reinhold2019evaluating,
  title={Evaluating the impact of intensity normalization on MR image synthesis},
  author={Reinhold, Jacob C and Dewey, Blake E and Carass, Aaron and Prince, Jerry L},
  journal={Medical Imaging 2019: Image Processing},
  year={2019}
}

License

MIT

Download files

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

Source Distribution

intensity_normalization-4.0.0.tar.gz (535.1 kB view details)

Uploaded Aug 3, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

intensity_normalization-4.0.0-py3-none-any.whl (47.5 kB view details)

Uploaded Aug 3, 2026 Python 3

File details

Details for the file intensity_normalization-4.0.0.tar.gz.

File metadata

Download URL: intensity_normalization-4.0.0.tar.gz
Upload date: Aug 3, 2026
Size: 535.1 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for intensity_normalization-4.0.0.tar.gz
Algorithm	Hash digest
SHA256	`68a3b25b97f1364b074d0babac29491a8c2eab87280d3203da6f4a01023b6484`
MD5	`cf951c590f21d8b70407bf52cdd233f7`
BLAKE2b-256	`65d96f7034b2e9dbe231b10a20eeb7e9e7e698c4c8f878c4e7c705741a86941c`

See more details on using hashes here.

Provenance

The following attestation bundles were made for intensity_normalization-4.0.0.tar.gz:

Publisher: publish.yml on jcreinhold/intensity-normalization

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: intensity_normalization-4.0.0.tar.gz
- Subject digest: 68a3b25b97f1364b074d0babac29491a8c2eab87280d3203da6f4a01023b6484
- Sigstore transparency entry: 2335685407
- Sigstore integration time: Aug 3, 2026
Source repository:
- Permalink: jcreinhold/intensity-normalization@50531a3f03bfcdd63bd6d83310e63bbd58262dc8
- Branch / Tag: refs/tags/v4.0.0
- Owner: https://github.com/jcreinhold
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@50531a3f03bfcdd63bd6d83310e63bbd58262dc8
- Trigger Event: release