Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example

被引:473
作者
Abraham, Alexandre [1 ,2 ]
Milham, Michael P. [5 ,6 ]
Di Martino, Adriana [7 ]
Craddock, R. Cameron [5 ,6 ]
Samaras, Dimitris [3 ,4 ]
Thirion, Bertrand [1 ,2 ]
Varoquaux, Gael [1 ,2 ]
机构
[1] Saclay INRIA le de France, Saclay, France
[2] CEA, Neurospin Bat 145, F-91191 Gif Sur Yvette, France
[3] SUNY Stony Brook, Stony Brook, NY 11794 USA
[4] Ecole Cent Arts & Mfg, F-92290 Chatenay Malabry, France
[5] Child Mind Inst, Ctr Dev Brain, New York, NY USA
[6] Nathan S Kline Inst Psychiat Res, Ctr Biomed Imaging & Neuromodulat, Orangeburg, NY 10962 USA
[7] NYU, Langone Med Ctr, Ctr Child Study, New York, NY USA
关键词
Data heterogeneity; Resting-state fMRI; Data pipelines; Biomarkers; Connectome; Autism spectrum disorders; HUMAN CEREBRAL-CORTEX; FUNCTIONAL CONNECTIVITY; SPECTRUM DISORDERS; BRAIN CONNECTIVITY; SAMPLE-SIZE; FMRI; NETWORK; CONNECTOMES; PREDICTION; SUBJECT;
D O I
10.1016/j.neuroimage.2016.10.045
中图分类号
Q189 [神经科学];
学科分类号
071006 [神经生物学];
摘要
Resting-state functional Magnetic Resonance Imaging (R-fMRI) holds the promise to reveal functional biomarkers of neuropsychiatric disorders. However, extracting such biomarkers is challenging for complex multi-faceted neuropathologies, such as autism spectrum disorders. Large multi-site datasets increase sample sizes to compensate for this complexity, at the cost of uncontrolled heterogeneity. This heterogeneity raises new challenges, akin to those face in realistic diagnostic applications. Here, we demonstrate the feasibility of inter-site classification of neuropsychiatric status, with an application to the Autism Brain Imaging Data Exchange (ABIDE) database, a large (N=871) multi-site autism dataset. For this purpose, we investigate pipelines that extract the most predictive biomarkers from the data. These R-fMRI pipelines build participant-specific connectomes from functionally-defined brain areas. Connectomes are then compared across participants to learn patterns of connectivity that differentiate typical controls from individuals with autism. We predict this neuropsychiatric status for participants from the same acquisition sites or different, unseen, ones. Good choices of methods for the various steps of the pipeline lead to 67% prediction accuracy on the full ABIDE data, which is significantly better than previously reported results. We perform extensive validation on multiple subsets of the data defined by different inclusion criteria. These enables detailed analysis of the factors contributing to successful connectome-based prediction. First, prediction accuracy improves as we include more subjects, up to the maximum amount of subjects available. Second, the definition of functional brain areas is of paramount importance for biomarker discovery: brain areas extracted from large R-fMRI datasets outperform reference atlases in the classification tasks.
引用
收藏
页码:736 / 745
页数:10
相关论文
共 76 条
[1]
Abraham A, 2013, LECT NOTES COMPUT SC, V8150, P607, DOI 10.1007/978-3-642-40763-5_75
[2]
Anderson J.S., 2013, NEUROIMAGE CLIN
[3]
Anderson J.S., 2010, Cerebral Cortex
[4]
Functional connectivity magnetic resonance imaging classification of autism [J].
Anderson, Jeffrey S. ;
Nielsen, Jared A. ;
Froehlich, Alyson L. ;
DuBray, Molly B. ;
Druzgal, T. Jason ;
Cariello, Annahir N. ;
Cooperrider, Jason R. ;
Zielinski, Brandon A. ;
Ravichandran, Caitlin ;
Fletcher, P. Thomas ;
Alexander, Andrew L. ;
Bigler, Erin D. ;
Lange, Nicholas ;
Lainhart, Janet E. .
BRAIN, 2011, 134 :3739-3751
[5]
Avants BB, 2009, INSIGHT J, V2, P1, DOI 10.54294/uvnhin
[6]
Probabilistic independent component analysis for functional magnetic resonance imaging [J].
Beckmann, CF ;
Smith, SA .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2004, 23 (02) :137-152
[7]
A component based noise correction method (CompCor) for BOLD and perfusion based fMRI [J].
Behzadi, Yashar ;
Restom, Khaled ;
Liau, Joy ;
Liu, Thomas T. .
NEUROIMAGE, 2007, 37 (01) :90-101
[8]
Power failure: why small sample size undermines the reliability of neuroscience [J].
Button, Katherine S. ;
Ioannidis, John P. A. ;
Mokrysz, Claire ;
Nosek, Brian A. ;
Flint, Jonathan ;
Robinson, Emma S. J. ;
Munafo, Marcus R. .
NATURE REVIEWS NEUROSCIENCE, 2013, 14 (05) :365-376
[9]
Calhoun V.D., 2011, FRONTIERS PSYCHIAT, V2
[10]
A method for making group inferences from functional MRI data using independent component analysis [J].
Calhoun, VD ;
Adali, T ;
Pearlson, GD ;
Pekar, JJ .
HUMAN BRAIN MAPPING, 2001, 14 (03) :140-151