rest2vec: Vectorizing the resting-state functional connectome using graph embedding

rest2vec: Vectorizing the resting-state functional connectome using graph embedding

Publication date: May 11, 2020

Resting-state functional magnetic resonance imaging (rs-fMRI) is widely used in connectomics for studying the functional relationships between regions of the human brain. rs-fMRI connectomics, however, has inherent analytical challenges, such as accounting for negative correlations. In addition, functional relationships between brain regions do not necessarily correspond to their anatomical distance, making the intrinsic geometry of the functional connectome less well understood. Recent techniques in natural language processing and machine learning, such as word2vec, have used embedding methods to map high-dimensional data into meaningful vector spaces. Inspired by this approach, we have developed a graph embedding pipeline, rest2vec, for studying the intrinsic geometry of functional connectomes. We demonstrate how rest2vec uses the phase angle spatial embedding (PhASE) method with dimensionality reduction techniques to embed the functional connectome into lower dimensions. Rest2vec can also be linked to the maximum mean discrepancy (MMD) metric to assign functional modules of the connectome in a continuous manner, improving upon traditional binary classification methods. Together, this allows for studying the functional connectome such that the full range of correlative information is preserved and gives a more informed understanding of the functional organization of the brain.

PDF

Concepts Keywords
Accounting Sensory processing
Anaconda 370Previous
Binary Classification Default mode network
Bioengineering Natural7language processing
Blood Natural processing
Borel Rest2vec processing pipeline
Brain Distinct functional networks
Cartesian Space Diffusion imaging
Computer Engineering Brain
Connectome Cerebrum
Connectomes Neuroscience
Correlation Cognitive neuroscience
Correlation Matrix Gyri
Diez Neuroimaging
Dimension Connectome
Dimensionality Reduction Isomap
Euclidean Space Precuneus
FMRI Resting state fMRI
Fmri Nonlinear dimensionality reduction
Frequency Occipital lobe
Functional Connectivity Neuroscience
Functional Mri Http
Geometry Nonlinear197technique Dijkstras algorithm
Graph Magnetic resonance imaging
Graph Embedding Mri
Graph Theory
Hilbert Space
Illinois
Isometric Mapping
Kernel
Magnetic Resonance Imaging
Manifold
Manifold Learning
Matrices
Matrix
Metric
Modularity
Neuroanatomy
Neuroimaging
Nonlinear
Nonlinear Dimensionality Reduction
Oxygenation
Pearson Correlation
Phase Angle
Phase Encoding
Pipeline
Probabilistic
Probability
Probability Distributions
Python
Random Variables
Richard Bellman
Roi
Similarity Matrix
Spin
Statistical Mechanics
Sth
Swiss
Swiss Roll
Tensor
Undirected Graph
Usc
Vector
Vectors
Vertices

Semantics

Type Source Name
disease MESH community
drug DRUGBANK Aspartame
drug DRUGBANK Vildagliptin
drug DRUGBANK Pidolic Acid
drug DRUGBANK Coenzyme M
drug DRUGBANK Flunarizine
disease MESH visual
drug DRUGBANK Pentaerythritol tetranitrate
drug DRUGBANK Acetylsalicylic acid
drug DRUGBANK Ethambutol

Download Document

Leave a Comment

Your email address will not be published. Required fields are marked *