Reproducibility of importance extraction methods in neural network based fMRI classification

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Standard

Harvard

APA

Vancouver

Author

Bibtex - Lataa

@article{9443f10011604bf9b73594b652ce0849,
title = "Reproducibility of importance extraction methods in neural network based fMRI classification",
abstract = "Recent advances in machine learning allow faster training, improved performance and increased interpretability of classification techniques. Consequently, their application in neuroscience is rapidly increasing. While classification approaches have proved useful in functional magnetic resonance imaging (fMRI) studies, there are concerns regarding extraction, reproducibility and visualization of brain regions that contribute most significantly to the classification. We addressed these issues using an fMRI classification scheme based on neural networks and compared a set of methods for extraction of category-related voxel importances in three simulated and two empirical datasets. The simulation data revealed that the proposed scheme successfully detects spatially distributed and overlapping activation patterns upon successful classification. Application of the proposed classification scheme to two previously published empirical fMRI datasets revealed robust importance maps that extensively overlap with univariate maps but also provide complementary information. Our results demonstrate increased statistical power of importance maps compared to univariate approaches for both detection of overlapping patterns and patterns with weak univariate information.",
keywords = "Classification, fMRI, Importance maps, MVPA, Neural networks, Pattern reproducibility",
author = "Athanasios Gotsopoulos and Heini Saarim{\"a}ki and Enrico Glerean and J{\"a}{\"a}skel{\"a}inen, {Iiro P.} and Mikko Sams and Lauri Nummenmaa and Jouko Lampinen",
year = "2018",
month = "11",
day = "1",
doi = "10.1016/j.neuroimage.2018.06.076",
language = "English",
volume = "181",
pages = "44--54",
journal = "NeuroImage",
issn = "1053-8119",

}

RIS - Lataa

TY - JOUR

T1 - Reproducibility of importance extraction methods in neural network based fMRI classification

AU - Gotsopoulos, Athanasios

AU - Saarimäki, Heini

AU - Glerean, Enrico

AU - Jääskeläinen, Iiro P.

AU - Sams, Mikko

AU - Nummenmaa, Lauri

AU - Lampinen, Jouko

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Recent advances in machine learning allow faster training, improved performance and increased interpretability of classification techniques. Consequently, their application in neuroscience is rapidly increasing. While classification approaches have proved useful in functional magnetic resonance imaging (fMRI) studies, there are concerns regarding extraction, reproducibility and visualization of brain regions that contribute most significantly to the classification. We addressed these issues using an fMRI classification scheme based on neural networks and compared a set of methods for extraction of category-related voxel importances in three simulated and two empirical datasets. The simulation data revealed that the proposed scheme successfully detects spatially distributed and overlapping activation patterns upon successful classification. Application of the proposed classification scheme to two previously published empirical fMRI datasets revealed robust importance maps that extensively overlap with univariate maps but also provide complementary information. Our results demonstrate increased statistical power of importance maps compared to univariate approaches for both detection of overlapping patterns and patterns with weak univariate information.

AB - Recent advances in machine learning allow faster training, improved performance and increased interpretability of classification techniques. Consequently, their application in neuroscience is rapidly increasing. While classification approaches have proved useful in functional magnetic resonance imaging (fMRI) studies, there are concerns regarding extraction, reproducibility and visualization of brain regions that contribute most significantly to the classification. We addressed these issues using an fMRI classification scheme based on neural networks and compared a set of methods for extraction of category-related voxel importances in three simulated and two empirical datasets. The simulation data revealed that the proposed scheme successfully detects spatially distributed and overlapping activation patterns upon successful classification. Application of the proposed classification scheme to two previously published empirical fMRI datasets revealed robust importance maps that extensively overlap with univariate maps but also provide complementary information. Our results demonstrate increased statistical power of importance maps compared to univariate approaches for both detection of overlapping patterns and patterns with weak univariate information.

KW - Classification

KW - fMRI

KW - Importance maps

KW - MVPA

KW - Neural networks

KW - Pattern reproducibility

UR - http://www.scopus.com/inward/record.url?scp=85049558363&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2018.06.076

DO - 10.1016/j.neuroimage.2018.06.076

M3 - Article

VL - 181

SP - 44

EP - 54

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -

ID: 26595745