Adaptive Smoothing in fMRI Data Processing Neural Networks

Albert Vilamala, Kristoffer Hougaard Madsen, Lars Kai Hansen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Functional Magnetic Resonance Imaging (fMRI) relies on multi-step data processing pipelines to accurately determine brain activity; among them, the crucial step of spatial smoothing. These pipelines are commonly suboptimal, given the local optimisation strategy they use, treating each step in isolation. With the advent of new tools for deep learning, recent work has proposed to turn these pipelines into end-to-end learning networks. This change of paradigm offers new avenues to improvement as it allows for a global optimisation. The current work aims at benefitting from this paradigm shift by defining a smoothing step as a layer in these networks able to adaptively modulate the degree of smoothing required by each brain volume to better accomplish a given data analysis task. The viability is evaluated on real fMRI data where subjects did alternate between left and right finger tapping tasks.
Original languageEnglish
Title of host publicationProceedings of the 2017 International Workshop on Pattern Recognition in Neuroimaging
Number of pages4
PublisherIEEE
Publication date2017
DOIs
Publication statusPublished - 2017
Event2017 International Workshop on Pattern Recognition in Neuroimaging - University of Toronto, Toronto, Canada
Duration: 21 Jun 201723 Jun 2017

Conference

Conference2017 International Workshop on Pattern Recognition in Neuroimaging
LocationUniversity of Toronto
CountryCanada
CityToronto
Period21/06/201723/06/2017

Fingerprint Dive into the research topics of 'Adaptive Smoothing in fMRI Data Processing Neural Networks'. Together they form a unique fingerprint.

Cite this