Format

Send to

Choose Destination
Neuroimage. 2015 May 1;111:431-41. doi: 10.1016/j.neuroimage.2015.02.048. Epub 2015 Feb 28.

Robust regression for large-scale neuroimaging studies.

Author information

1
Parietal Team, INRIA Saclay-Île-de-France, Saclay, France; CEA, DSV, I2BM, Neurospin bât 145, 91191 Gif-Sur-Yvette, France; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany. Electronic address: virgile.fritsch@inria.fr.
2
Parietal Team, INRIA Saclay-Île-de-France, Saclay, France; CEA, DSV, I2BM, Neurospin bât 145, 91191 Gif-Sur-Yvette, France; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
3
Department of Forensic and Neurodevelopmental Sciences, Institute of Psychiatry, King's College London, London, United Kingdom; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
4
Department of Child and Adolescent Psychiatry, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
5
MRC Social, Genetic and Developmental Psychiatry (SGDP) Centre, London, United Kingdom; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
6
Trinity College Institute of Neuroscience and Discipline of Psychiatry, School of Medicine, Trinity College Dublin, Dublin, Ireland; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
7
Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; Physikalisch-Technische Bundesanstalt (PTB), Braunschweig, Berlin, Germany; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
8
Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; Department of Psychiatry and Psychotherapy, Campus Charité Mitte, Charité Universitätsmedizin Berlin, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
9
MRC Social, Genetic and Developmental Psychiatry (SGDP) Centre, London, United Kingdom; Department of Psychiatry, Universite de Montreal, CHU Ste Justine Hospital, Canada; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
10
Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; Central Institute of Mental Health, Mannheim, Germany; Medical Faculty Mannheim, University of Heidelberg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
11
Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; Institute of Neuroscience, Trinity College Dublin, Dublin, Ireland; Department of Psychiatry, University of VT, USA; Department of Psychology, University of VT, USA; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
12
Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; Institut National de la Santé et de la Recherche Médicale, INSERM CEA Unit 1000 "Imaging & Psychiatry", University Paris Sud, Orsay, France; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
13
Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Department of Addictive Behaviour and Addiction Medicine, Germany; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
14
Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; Rotman Research Institute, University of Toronto, Toronto, Canada; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; School of Psychology, University of Nottingham, United Kingdom; Montreal Neurological Institute, McGill University, Canada; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
15
CEA, DSV, I2BM, Neurospin bât 145, 91191 Gif-Sur-Yvette, France; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.
16
Helen Wills Neuroscience Institute, Henry H. Wheeler Jr. Brain Imaging Center, University of California at Berkeley, USA; Universitaetsklinikum Hamburg Eppendorf, Hamburg, Germany; School of Physics and Astronomy, University of Nottingham, United Kingdom; AP-HP Department of Adolescent Psychopathology and Medicine, Maison de Solenn, University Paris Descartes, Paris, France; The Hospital for Sick Children, University of Toronto, Toronto, Canada; Behavioural and Clinical Neurosciences Institute, Department of Experimental Psychology, University of Cambridge, United Kingdom; Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Germany; Neuroimaging Center, Technische Universität Dresden, Germany.

Abstract

Multi-subject datasets used in neuroimaging group studies have a complex structure, as they exhibit non-stationary statistical properties across regions and display various artifacts. While studies with small sample sizes can rarely be shown to deviate from standard hypotheses (such as the normality of the residuals) due to the poor sensitivity of normality tests with low degrees of freedom, large-scale studies (e.g. >100 subjects) exhibit more obvious deviations from these hypotheses and call for more refined models for statistical inference. Here, we demonstrate the benefits of robust regression as a tool for analyzing large neuroimaging cohorts. First, we use an analytic test based on robust parameter estimates; based on simulations, this procedure is shown to provide an accurate statistical control without resorting to permutations. Second, we show that robust regression yields more detections than standard algorithms using as an example an imaging genetics study with 392 subjects. Third, we show that robust regression can avoid false positives in a large-scale analysis of brain-behavior relationships with over 1500 subjects. Finally we embed robust regression in the Randomized Parcellation Based Inference (RPBI) method and demonstrate that this combination further improves the sensitivity of tests carried out across the whole brain. Altogether, our results show that robust procedures provide important advantages in large-scale neuroimaging group studies.

KEYWORDS:

Large cohorts; Neuroimaging genetics; Outliers; Robust regression; fMRI

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center