Diffusion Imaging In Python - Documentation#

DIPY is the paragon 3D/4D+ imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.

DIPY is part of the NiPy ecosystem.

Highlights#

DIPY 1.10.0 is now available. New features include:

  • NF: Patch2Self3 - Large improvements of self-supervised denoising method added.

  • NF: Fiber density and spread from ODF using Bingham distributions method added.

  • NF: Iteratively reweighted least squares for robust fitting of diffusion models added.

  • NF: NDC - Neighboring DWI Correlation quality metric added.

  • NF: DAM - tissue classification method added.

  • NF: New Parallel Backends (Ray, joblib, Dask) for fitting reconstruction methods added.

  • RF: Deprecation of Tensorflow support. PyTorch support is now the default.

  • Transition to Keyword-only arguments (PEP 3102).

  • Zero-warnings policy (CIs, Compilation, doc generation) adopted.

  • Adoption of ruff for automatic style enforcement.

  • Transition to using f-strings.

  • Citation system updated. It is more uniform and robust.

  • Multiple Workflows updated.

  • Multiple DIPY Horizon features updated.

  • Large documentation update.

  • Closed 250 issues and merged 185 pull requests.

See Older Highlights.

Announcements#

See some of our Past Announcements

On this page