A regularization algorithm for decoding perceptual temporal profiles from fMRI data

In several biomedical fields, researchers are faced with regression problems that can be stated as Statistical Learning problems. One example is given by decoding brain states from functional magnetic resonance imaging (fMRI) data. Recently, it has been shown that the general Statistical Learning pr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:NeuroImage (Orlando, Fla.) Jg. 56; H. 1; S. 258 - 267
Hauptverfasser: Prato, Marco, Favilla, Stefania, Zanni, Luca, Porro, Carlo A., Baraldi, Patrizia
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Elsevier Inc 01.05.2011
Elsevier Limited
Schlagworte:
Adult
Algorithms
Applied mathematics
Artificial Intelligence
Brain - physiology
Brain Mapping - methods
Competition
Female
Functional magnetic resonance imaging
Humans
Hypotheses
Image Interpretation, Computer-Assisted - methods
Inverse problems
Machine learning methods
Magnetic Resonance Imaging
Male
Middle Aged
Pain
Pain - physiopathology
Pain Measurement
Pain perception
Standard deviation
Studies
Support vector machines
Young Adult
United States > US
Pittsburgh Pennsylvania
Support vector machines
Functional magnetic resonance imaging
Pain perception
Inverse problems
Machine learning methods
ISSN:1053-8119, 1095-9572, 1095-9572
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In several biomedical fields, researchers are faced with regression problems that can be stated as Statistical Learning problems. One example is given by decoding brain states from functional magnetic resonance imaging (fMRI) data. Recently, it has been shown that the general Statistical Learning problem can be restated as a linear inverse problem. Hence, new algorithms were proposed to solve this inverse problem in the context of Reproducing Kernel Hilbert Spaces. In this paper, we detail one iterative learning algorithm belonging to this class, called ν-method, and test its effectiveness in a between-subjects regression framework. Specifically, our goal was to predict the perceived pain intensity based on fMRI signals, during an experimental model of acute prolonged noxious stimulation. We found that, using a linear kernel, the psychophysical time profile was well reconstructed, while pain intensity was in some cases significantly over/underestimated. No substantial differences in terms of accuracy were found between the proposed approach and one of the state-of-the-art learning methods, the Support Vector Machines. Nonetheless, adopting the ν-method yielded a significant reduction in computational time, an advantage that became more evident when a relevant feature selection procedure was implemented. The ν-method can be easily extended and included in typical approaches for binary or multiple classification problems, and therefore it seems well-suited to build effective brain activity estimators. ► A fast learning algorithm for decoding perceptual profiles from fMRI data. ► Between-subjects prediction of pain intensity in healthy volunteers. ► Individual psychophysical pain profiles were well reconstructed. ► No significant difference in accuracy between our approach and SVR.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1053-8119
1095-9572
1095-9572
DOI:10.1016/j.neuroimage.2011.01.074