Lecture

Multivariate Methods II: ICA for Functional Brain Imaging

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In course

MICRO-513: Signal processing for functional brain imaging

Computational methods for the analysis of human brain imaging data ...

Description

This lecture covers the application of Independent Component Analysis (ICA) in functional brain imaging, focusing on the transition from Principal Component Analysis (PCA) to ICA. Topics include the importance of non-Gaussianity, cleaning artefacts in fMRI, spatial versus temporal ICA, and the challenges in determining the number of components. The instructor explains the definition of ICA, its assumptions, and the difficulties in variance estimation and component ordering. Various ICA algorithms and their properties are discussed, along with the use of ICA for denoising and group studies. The lecture concludes with a critical note on ICA's properties and its role in exploring resting-state fMRI data.

Instructor

Dimitri Nestor Alice Van De Ville

Expertise Brain and spinal cord imaging, signal and image processing, network science, dynamic systems Teaching & PhD PhD Students Alexandre Cionca, Chun Hei Michael Chan, Flavia Petruso, Bassam El Rawas, Nikolaos Molochidis, Christophe Pascal Jérémie Chênes, Fabrice Jean Guibert, Alessio Siviglia, Ekansh Sareen, Beatrice Lugli Past EPFL PhD Students Djano Kandaswamy, Fikret Isik Karahanoglu, Nora Leonardi, Zafer Dogan, Jeffrey Adam Kasten, Naghmeh Ghazaleh, Rotem Roza Kopel, Daniela Maria Zöller, Thomas

Official source

Related concepts (32)

Independent component analysis

In signal processing, independent component analysis (ICA) is a computational method for separating a multivariate signal into additive subcomponents. This is done by assuming that at most one subcomponent is Gaussian and that the subcomponents are statistically independent from each other. ICA is a special case of blind source separation. A common example application is the "cocktail party problem" of listening in on one person's speech in a noisy room.

Functional magnetic resonance imaging

Functional magnetic resonance imaging or functional MRI (fMRI) measures brain activity by detecting changes associated with blood flow. This technique relies on the fact that cerebral blood flow and neuronal activation are coupled. When an area of the brain is in use, blood flow to that region also increases. The primary form of fMRI uses the blood-oxygen-level dependent (BOLD) contrast, discovered by Seiji Ogawa in 1990.

Principal component analysis

Principal component analysis (PCA) is a popular technique for analyzing large datasets containing a high number of dimensions/features per observation, increasing the interpretability of data while preserving the maximum amount of information, and enabling the visualization of multidimensional data. Formally, PCA is a statistical technique for reducing the dimensionality of a dataset. This is accomplished by linearly transforming the data into a new coordinate system where (most of) the variation in the data can be described with fewer dimensions than the initial data.

Functional neuroimaging

Functional neuroimaging is the use of neuroimaging technology to measure an aspect of brain function, often with a view to understanding the relationship between activity in certain brain areas and specific mental functions. It is primarily used as a research tool in cognitive neuroscience, cognitive psychology, neuropsychology, and social neuroscience.

Neuroimaging

Neuroimaging is the use of quantitative (computational) techniques to study the structure and function of the central nervous system, developed as an objective way of scientifically studying the healthy human brain in a non-invasive manner. Increasingly it is also being used for quantitative research studies of brain disease and psychiatric illness. Neuroimaging is highly multidisciplinary involving neuroscience, computer science, psychology and statistics, and is not a medical specialty.

Related lectures (64)

Statistical Signal Processing

Covers Gaussian Mixture Models, Denoising, Data Classification, and Spike Sorting using Principal Component Analysis.

Principal Component Analysis: Dimensionality Reduction

Covers Principal Component Analysis for dimensionality reduction, exploring its applications, limitations, and importance of choosing the right components.

Kernel PCA: Nonlinear Dimensionality Reduction

Explores Kernel Principal Component Analysis, a nonlinear method using kernels for linear problem solving and dimensionality reduction.

Principal Component Analysis: Dimension Reduction

Covers Principal Component Analysis for dimension reduction in biological data, focusing on visualization and pattern identification.

Clustering & Density Estimation