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.
Available on many operating systems
All Algorithms available via CLI
Create your Own
K-Fold cross validation
Single Shell: DTI, CSA, SFM, SDT, Q-Ball, CSD, ...
Multi-Shell: GQI, DTI, DKI, SHORE, MAPMRI, MSMT-CSD, ...
Diffeomorphic 2D/3D Registration
Streamlines based Registration
High resolution DWI
LPCA - MPPCA
Non Local Means
interactive tractogram visualization
Advanced UI and Shaders
DIPY 1.5.0 released March 11, 2022.
DIPY 1.4.1 released May 6, 2021.
DIPY 1.4.0 released March 13, 2021.
See some of our Past Announcements
DIPY 1.5.0 is now available. New features include:
New reconstruction model added: Q-space Trajectory Imaging (QTI).
New reconstruction model added: Robust and Unbiased Model-BAsed Spherical Deconvolution (RUMBA-SD).
New reconstruction model added: Residual block Deep Neural Network (ResDNN).
Masking management in Affine Registration added.
Multiple Workflows updated (DTIFlow, DKIFlow, ImageRegistrationFlow) and added (MotionCorrectionFlow).
Compatibility with Python 3.10 added.
Migrations from Azure Pipeline to Github Actions.
Large codebase cleaning.
New parallelisation module added.
dipy.io.bvectxt module deprecated.
New DIPY Horizon features (ROI Visualizer, random colors flag).
Large documentation update.
Closed 129 issues and merged 72 pull requests.
See Older Highlights.
Tue Aug 02
RT @BramshQ: First in-person conference after God knows how long! #AAIC2022. Come by my poster (P3-220) if you are at #AAIC22 to chat about…
Mon Aug 01
RT @krsitek: Loved flipping the page on my BRAIN Initiative calendar and seeing @BramshQ’s beautiful #sciart! Makes it a little less painfu…
Fri Jul 15
@njahanshad Thank you for taking interest in the challenge! We'll soon send you an email about the details.
Fri Jul 15
Great work 🤩 FiberNeat: Unsupervised White Matter Tract Filtering. No training or atlas required!! 🧠 https://t.co/xWsiooG0wh
Fri Jul 15
RT @PTenigma: If you're at #EMBC22 come see us @ 10:45am in the Forth Room (SEC Armadillo) to talk about manifold embedding (t-SNE, UMAP) t…
Garyfallidis E, Brett M, Amirbekian B, Rokem A, van der Walt S, Descoteaux M, Nimmo-Smith I and Dipy Contributors (2014). DIPY, a library for the analysis of diffusion MRI data. Frontiers in Neuroinformatics, vol.8, no.8.