Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning

被引:23
作者
Spera, Giovanna [1 ]
Retico, Alessandra [1 ]
Bosco, Paolo [2 ]
Ferrari, Elisa [1 ,3 ]
Palumbo, Letizia [1 ]
Oliva, Piernicola [4 ,5 ]
Muratori, Filippo [2 ,6 ]
Calderoni, Sara [2 ,6 ]
机构
[1] Natl Inst Nucl Phys INFN, Pisa Div, Pisa, Italy
[2] IRCCS Stella Maris Fdn, Pisa, Italy
[3] Scuola Normale Super Pisa, Fac Sci, Pisa, Italy
[4] Univ Sassari, Dept Chem & Pharm, Sassari, Italy
[5] Natl Inst Nucl Phys INFN, Cagliari Div, Cagliari, Italy
[6] Univ Pisa, Dept Clin & Expt Med, Pisa, Italy
来源
FRONTIERS IN PSYCHIATRY | 2019年 / 10卷
关键词
autism spectrum disorders; children; resting-state fMRI; functional connectivity; machine learning; ABIDE; SYMPTOM SEVERITY; BRAIN; NETWORK; MRI; CLASSIFICATION; ORGANIZATION; INDIVIDUALS; PATTERNS; FUSIFORM; CORTEX;
D O I
10.3389/fpsyt.2019.00620
中图分类号
R749 [精神病学];
学科分类号
100205 ;
摘要
No univocal and reliable brain-based biomarkers have been detected to date in Autism Spectrum Disorders (ASD). Neuroimaging studies have consistently revealed alterations in brain structure and function of individuals with ASD; however, it remains difficult to ascertain the extent and localization of affected brain networks. In this context, the application of Machine Learning (ML) classification methods to neuroimaging data has the potential to contribute to a better distinction between subjects with ASD and typical development controls (TD). This study is focused on the analysis of resting-state fMRI data of individuals with ASD and matched TD, available within the ABIDE collection. To reduce the multiple sources of heterogeneity that impact on understanding the neural underpinnings of autistic condition, we selected a subgroup of 190 subjects (102 with ASD and 88 TD) according to the following criteria: male children (age range: 6.5-13 years); rs-fMRI data acquired with open eyes; data from the University sites that provided the largest number of scans (KKI, NYU, UCLA, UM). Connectivity values were evaluated as the linear correlation between pairs of time series of brain areas; then, a Linear kernel Support Vector Machine (L-SVM) classification, with an inter-site cross-validation scheme, was carried out. A permutation test was conducted to identify over-connectivity and under-connectivity alterations in the ASD group. The mean L-SVM classification performance, in terms of the area under the ROC curve (AUC), was 0.75 +/- 0.05. The highest performance was obtained using data from KKI, NYU and UCLA sites in training and data from UM as testing set (AUC = 0.83). Specifically, stronger functional connectivity (FC) in ASD with respect to TD involve (p < 0.001) the angular gyrus with the precuneus in the right (R) hemisphere, and the R frontal operculum cortex with the pars opercularis of the left (L) inferior frontal gyrus. Weaker connections in ASD group with respect to TD are the intra-hemispheric R temporal fusiform cortex with the R hippocampus, and the L supramarginal gyrus with L planum polare. The results indicate that both under-and over-FC occurred in a selected cohort of ASD children relative to TD controls, and that these functional alterations are spread in different brain networks.
引用
收藏
页数:14
相关论文
共 71 条
  • [41] Metz Charles E, 2006, J Am Coll Radiol, V3, P413, DOI 10.1016/j.jacr.2006.02.021
  • [42] Abnormalities of intrinsic functional connectivity in autism spectrum disorders
    Monk, Christopher S.
    Peltier, Scott J.
    Wiggins, Jillian Lee
    Weng, Shih-Jen
    Carrasco, Melisa
    Risi, Susan
    Lord, Catherine
    [J]. NEUROIMAGE, 2009, 47 (02) : 764 - 772
  • [43] Enhanced perceptual functioning in autism:: An update, and eight principles of autistic perception
    Mottron, L
    Dawson, M
    Soulières, I
    Hubert, B
    Burack, J
    [J]. JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS, 2006, 36 (01) : 27 - 43
  • [44] Classifying brain states and determining the discriminating activation patterns: Support Vector Machine on functional MRI data
    Mourao-Miranda, J
    Bokde, ALW
    Born, C
    Hampel, H
    Stetter, M
    [J]. NEUROIMAGE, 2005, 28 (04) : 980 - 995
  • [45] Towards a consensus regarding global signal regression for resting state functional connectivity MRI
    Murphy, Kevin
    Fox, Michael D.
    [J]. NEUROIMAGE, 2017, 154 : 169 - 173
  • [46] Local resting state functional connectivity in autism: site and cohort variability and the effect of eye status
    Nair, Sangeeta
    Keehn, R. Joanne Jao
    Berkebile, Michael M.
    Maximo, Jose Omar
    Witkowska, Natalia
    Mueller, Ralph-Axel
    [J]. BRAIN IMAGING AND BEHAVIOR, 2018, 12 (01) : 168 - 179
  • [47] Multisite functional connectivity MRI classification of autism: ABIDE results
    Nielsen, Jared A.
    Zielinski, Brandon A.
    Fletcher, P. Thomas
    Alexander, Andrew L.
    Lange, Nicholas
    Bigler, Erin D.
    Lainhart, Janet E.
    Anderson, Jeffrey S.
    [J]. FRONTIERS IN HUMAN NEUROSCIENCE, 2013, 7
  • [48] Developmental changes in large-scale network connectivity in autism
    Nomi, Jason S.
    Uddin, Lucina Q.
    [J]. NEUROIMAGE-CLINICAL, 2015, 7 : 732 - 741
  • [49] Altered Connectivity Between Cerebellum, Visual, and Sensory-Motor Networks in Autism Spectrum Disorder: Results from the EU-AIMS Longitudinal European Autism Project
    Oldehinkel, Marianne
    Mennes, Maarten
    Marquand, Andre
    Charman, Tony
    Tillmann, Julian
    Ecker, Christine
    Dell'Acqua, Flavio
    Brandeis, Daniel
    Banaschewski, Tobias
    Baumeister, Sarah
    Moessnang, Carolin
    Baron-Cohen, Simon
    Holt, Rosemary
    Bolte, Sven
    Durston, Sarah
    Kundu, Prantik
    Lombardo, Michael, V
    Spooren, Will
    Loth, Eva
    Murphy, Declan G. M.
    Beckmann, Christian F.
    Buitelaar, Jan K.
    Ahmad, Jumana
    Ambrosino, Sara
    Auyeung, Bonnie
    Bourgeron, Thomas
    Bours, Carsten
    Brammer, Michael
    Brogna, Claudia
    de Bruijn, Yvette
    Chakrabarti, Bhismadev
    Cornelissen, Ineke
    Crawley, Daisy
    DellAcqua, Flavio
    Dumas, Guillaume
    Faulkner, Jessica
    Frouin, Vincent
    Garces, Pilar
    Goyard, David
    Ham, Lindsay
    Hayward, Hannah
    Hipp, Joerg
    Johnson, Mark H.
    Jones, Emily J. H.
    Lai, Meng-Chuan
    D'ardhuy, Xavier Liogier
    Lythgoe, David J.
    Mandl, Rene
    Mason, Luke
    Meyer-Lindenberg, Andreas
    [J]. BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING, 2019, 4 (03) : 260 - 270