neuroim2 - Data Structures for Brain Imaging Data

A collection of data structures and methods for handling volumetric brain imaging data, with a focus on functional magnetic resonance imaging (fMRI). Provides efficient representations for three-dimensional and four-dimensional neuroimaging data through sparse and dense array implementations, memory-mapped file access for large datasets, and spatial transformation capabilities. Implements methods for image resampling, spatial filtering, region of interest analysis, and connected component labeling. General introduction to fMRI analysis can be found in Poldrack et al. (2024, "Handbook of functional MRI data analysis", <ISBN:9781108795760>).

Last updated

fmrineuroimagingcppopenmp

9.42 score 3 stars 8 dependents 258 scripts 516 downloads

fmrihrf - Hemodynamic Response Functions for fMRI Data Analysis

Creates, manipulates, and evaluates hemodynamic response functions and event-related regressors for functional magnetic resonance imaging data analysis. Supports multiple basis sets including Canonical, Gamma, Gaussian, B-spline, and Fourier bases. Features decorators for time-shifting and blocking, and efficient convolution algorithms for regressor construction. Methods are based on standard fMRI analysis techniques as described in Jezzard et al. (2001, ISBN:9780192630711).

Last updated

openblascppopenmp

7.71 score 5 dependents 95 scripts 521 downloads

bidser - Work with 'BIDS' (Brain Imaging Data Structure) Projects

Tools for working with 'BIDS' (Brain Imaging Data Structure) formatted neuroimaging datasets. The package provides functionality for reading and querying 'BIDS'-compliant projects, creating mock 'BIDS' datasets for testing, and extracting preprocessed data from 'fMRIPrep' derivatives. It supports searching and filtering 'BIDS' files by various entities such as subject, session, task, and run to streamline neuroimaging data workflows. See Gorgolewski et al. (2016) <doi:10.1038/sdata.2016.44> for the 'BIDS' specification.

Last updated

7.02 score 6 stars 58 scripts 183 downloads

fmridesign - Design Matrix Construction for fMRI Analysis

Constructs and inspects design matrices for functional magnetic resonance imaging (fMRI) analyses. Provides a formula interface for specifying event-related designs with flexible hemodynamic response function (HRF) bases, parametric modulators, and trialwise models. Includes facilities for baseline/nuisance regressors, contrast specification, and utilities for naming, validation, and visualization. Intended to support the model-building stage prior to statistical fitting. Implements methods described in Friston et al. (1995) <doi:10.1006/nimg.1995.1007> and Lindquist (2008) <doi:10.1214/09-STS282>.

Last updated

6.36 score 2 dependents 105 scripts

fmrilss - Least Squares Separate (LSS) Analysis for fMRI Data

Implements efficient least squares separate (LSS) analysis for functional magnetic resonance imaging (fMRI) data. LSS is used to estimate trial-by-trial activation patterns in event-related fMRI designs. The package provides both R and C++ implementations for computational efficiency.

Last updated

openblascppopenmp

5.83 score 1 stars 2 dependents 29 scripts

fmrireg - Regression Analysis of Functional Magnetic Resonance Imaging Data

Provides tools for the analysis of functional magnetic resonance imaging (fMRI) data. Facilities are included to construct flexible hemodynamic response functions, experimental regressors, and conduct univariate fMRI regression analyses.

Last updated

openblascppopenmp

5.71 score 8 stars 1 dependents 81 scripts

neuroatlas - Neuroimaging Atlases and Parcellations

Provides a unified interface to access and work with various neuroimaging atlases and parcellations including Schaefer, Brainnetome, Glasser, FreeSurfer ASEG, and Olsen MTL atlases. Integrates with TemplateFlow for standardized template access and supports interactive brain surface visualisation via triangle-mesh rendering with 'ggplot2' and 'ggiraph'.

Last updated

atlasneuroimagingparcellation

5.57 score 3 stars 16 scripts

neurosurf - Data Structures and Visualization for Surface-Based Neuroimaging Data

A comprehensive toolkit for working with surface-based neuroimaging data represented as triangle meshes. The package provides classes and methods for creating, manipulating, and visualizing 3D surface geometries (e.g., cortical surfaces), with support for various file formats including FreeSurfer and GIFTI. Key features include: surface smoothing, curvature computation, neighborhood graph construction, geodesic distance calculations, searchlight analysis for surface-based machine learning, and interactive 3D visualization via HTMLWidgets. The package facilitates advanced surface-based analyses through specialized data structures for representing surface geometry and associated functional data.

Last updated

cpp

5.41 score 1 stars 1 dependents 36 scripts

fmriAR - Fast AR and ARMA Noise Whitening for Functional MRI (fMRI) Design and Data

Lightweight utilities to estimate autoregressive (AR) and autoregressive moving average (ARMA) noise models from residuals and apply matched generalized least squares to whiten functional magnetic resonance imaging (fMRI) design and data matrices. The ARMA estimator follows a classic 1982 approach <doi:10.1093/biomet/69.1.81>, and a restricted AR family mirrors workflows described by Cox (2012) <doi:10.1016/j.neuroimage.2011.08.056>.

Last updated

openblascpp

5.13 score 3 dependents 6 scripts 528 downloads

fmrilatent - Latent Space Representations of fMRI Data

Provides S4 classes and methods for representing neuroimaging data in latent spaces. The LatentNeuroVec class offers a memory-efficient representation using matrix factorization (basis x loadings plus a per-voxel offset), enabling compact storage and efficient computation for PCA, temporal bases, graph and wavelet dictionaries, Slepian bases, HRBF atoms, and related fMRI decompositions. Integrates with the neuroim2 package for standard neuroimaging data structures.

Last updated

cppopenmp

5.06 score 1 dependents 3 scripts

shard - Deterministic, Zero-Copy Parallel Execution for R

Provides a parallel execution runtime for R that emphasizes deterministic memory behavior and efficient handling of large shared inputs. 'shard' enables zero-copy parallel reads via shared/memory-mapped segments, encourages explicit output buffers to avoid large result aggregation, and supervises worker processes to mitigate memory drift via controlled recycling. Diagnostics report peak memory usage, end-of-run memory return, and hidden copy/materialization events to support reproducible performance benchmarking.

Last updated

openblas

5.02 score 3 stars 3 scripts 491 downloads

fmristore - Efficient Storage of fMRI Data

Provides efficient storage and retrieval of functional magnetic resonance imaging (fMRI) data using HDF5 format. The package offers S4 classes and methods for working with dense and sparse representations of 4D neuroimaging data, latent space decompositions, and spatially clustered voxel time series. It includes memory-efficient access patterns for large datasets and integrates with the neuroim2 package for standard neuroimaging data structures.

Last updated

4.90 score 35 scripts

delarr - Lazy Delayed Arrays with Fused Execution

Provides a lightweight delayed array abstraction with tidy-friendly verbs, expression fusion, and pluggable storage backends.

Last updated

4.80 score 3 dependents 10 scripts

fmridataset - Unified Container for fMRI Datasets

Provides a unified S3 class 'fmri_dataset' for representing functional magnetic resonance imaging (fMRI) data from various sources including raw NIfTI files, BIDS projects, pre-loaded NeuroVec objects, and in-memory matrices. Features lazy loading, flexible data access patterns, and integration with neuroimaging analysis workflows.

Last updated

4.33 score 2 dependents 48 scripts

xnatR - Interface with XNAT Systems

An R package for interacting with XNAT systems via the REST API. Provides functions to authenticate, list projects/subjects/experiments/scans, search, and download data from XNAT neuroimaging archives.

Last updated

3.78 score 5 scripts

neurotransform - Geometric Transforms for Neuroimaging Data

A self-contained, dependency-light library for geometric transforms in neuroimaging. Provides affine and nonlinear (warp) mappings between coordinate systems, plus volume-to-surface mapping primitives. Emphasizes correctness, elegance, and composability with a category-theoretic flavor.

Last updated

cpp

3.54 score 7 scripts

fmrigds - Lazy, Format-Agnostic Group Analysis for fMRI

Provides a Group Data Set (GDS) abstraction and lazy analysis pipeline for first-level fMRI statistical outputs. Unifies tabular, NIfTI, HDF5, and fmristore inputs under a common sample x subject x contrast representation; supports space-aware transformations, group and meta-analytic reducers, provenance tracking, and reproducible export.

Last updated

openblascppopenmp

3.36 score 2 dependents 11 scripts

templateflow - Client for the 'TemplateFlow' Archive

R client for querying and fetching resources from the TemplateFlow archive using a local cache backed by the public TemplateFlow S3 bucket. Provides functions to list template assets, download missing files, read template metadata, and retrieve citations.

Last updated

3.48 score 1 dependents

fmrireport - PDF Reporting for fMRI GLM Fits

Generates publication-oriented PDF reports for fitted fMRI GLM models from 'fmrireg'. Reports include model/design summaries, HRF plots, coefficient summaries, contrast brain maps, and peak coordinate tables.

Last updated

3.30 score

dipca - Dynamic Inner Principal Component Analysis

Implements Dynamic Inner Principal Component Analysis (DiPCA), Dynamic Inner Canonical Correlation Analysis (DiCCA), and Dynamic Inner Partial Least Squares (DiPLS) for multivariate time series analysis. These methods extract latent components that follow autoregressive models, enabling temporal prediction and reconstruction. Based on the methods of Dong and Qin (2018) <doi:10.1016/j.jprocont.2017.05.002> for DiPCA, Dong and Qin (2018) <doi:10.1016/j.ifacol.2018.09.379> for DiCCA, and Dong and Qin (2018) <doi:10.1016/j.jprocont.2018.04.006> for DiPLS. Integrates with the 'multivarious' package framework for consistent preprocessing and projection interfaces.

Last updated

cpp

3.30 score

niflowr - Spec-Driven Neuroimaging Command-Line Tool Wrappers

A lightweight, declarative framework for wrapping neuroimaging command-line tools (FSL, AFNI, ANTs, FreeSurfer) in R. Tool interfaces are defined as JSON specifications that describe inputs, outputs, CLI rendering rules, and validation constraints. The package builds safe argument vectors (never shell strings), executes via 'processx', captures provenance, and integrates with 'targets' for pipeline orchestration.

Last updated

2.90 score

ciftier - Read and Write CIFTI-2 Neuroimaging Files

Pure R implementation of CIFTI-2 format I/O for grayordinate neuroimaging data. Reads and writes dense timeseries (.dtseries.nii), dense scalars (.dscalar.nii), and dense labels (.dlabel.nii) files without requiring external tools such as Connectome Workbench. Provides S4 classes mirroring the CIFTI-2 XML schema, user-friendly axis abstractions, and optional integration with 'neuroim2' and 'neurosurf' for spatially-aware brain imaging objects.

Last updated

2.00 score

phynd - Fast Design-Free Physiological Denoising

Fast, design-free physiological denoising inspired by PHYCAA+ using low-rank dynamic component extraction with optional DiCCA/DiPCA integration.

Last updated

cpp

2.00 score