DeepAI AI Chat
Log In Sign Up

PRAGMA: Interactively Constructing Functional Brain Parcellations

by   Roza G. Bayrak, et al.

A prominent goal of neuroimaging studies is mapping the human brain, in order to identify and delineate functionally-meaningful regions and elucidate their roles in cognitive behaviors. These brain regions are typically represented by atlases that capture general trends over large populations. Despite being indispensable to neuroimaging experts, population-level atlases do not capture individual differences in functional organization. In this work, we present an interactive visualization method, PRAGMA, that allows domain experts to derive scan-specific parcellations from established atlases. PRAGMA features a user-driven, hierarchical clustering scheme for defining temporally correlated parcels in varying granularity. The visualization design supports the user in making decisions on how to perform clustering, namely when to expand, collapse, or merge parcels. This is accomplished through a set of linked and coordinated views for understanding the user's current hierarchy, assessing intra-cluster variation, and relating parcellations to an established atlas. We assess the effectiveness of PRAGMA through a user study with four neuroimaging domain experts, where our results show that PRAGMA shows the potential to enable exploration of individualized and state-specific brain parcellations and to offer interesting insights into functional brain networks.


page 1

page 4


Bayesian subtyping for multi-state brain functional connectome with application on adolescent brain cognition

Converging evidence indicates that the heterogeneity of cognitive profil...

Transformer-Based Hierarchical Clustering for Brain Network Analysis

Brain networks, graphical models such as those constructed from MRI, hav...

Graph-aware linear mixed effects models for brain connectivity networks

Neuroimaging data on functional connections in the brain are frequently ...

ExpertoCoder: Capturing Divergent Brain Regions Using Mixture of Regression Experts

fMRI semantic category understanding using linguistic encoding models at...

Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models

A long standing goal in neuroscience has been to elucidate the functiona...

2D histology meets 3D topology: Cytoarchitectonic brain mapping with Graph Neural Networks

Cytoarchitecture describes the spatial organization of neuronal cells in...

Constructing Compact Brain Connectomes for Individual Fingerprinting

Recent neuroimaging studies have shown that functional connectomes are u...