Multimedia Tools and Applications

, Volume 77, Issue 17, pp 22809–22820 | Cite as

SAE-based classification of school-aged children with autism spectrum disorders using functional magnetic resonance imaging

  • Zhiyong Xiao
  • Canhua Wang
  • Nan Jia
  • Jianhua WuEmail author


This paper employs a novel-deep learning method and brain frequencies to discriminate school-aged children with autism spectrum disorders (ASD) from typically developing (TD) school-aged children with functional magnetic resonance imaging (fMRI) data of 84 subjects from the ABIDE (Autism Brain Imaging Data Exchange) database. Firstly, the fMRI data were preprocessed, and then each subject’s dataset was decomposed into 30 independent components (IC). Secondly, some key ICs were selected and inputted into a stacked autoencoder (SAE). The SAE was adopted for features subtraction and dimensionality reduction. Finally, a softmax classifier was used to discriminate the school-aged children with ASD from TD school-aged children. The average accuracy of the work was as high as 87.21% (average sensitivity = 92.86%, average specificity = 84.32%). The results of classification demonstrated that the proposed method may have the potential to automatically discriminate school-aged children with ASD from TD school-aged children. Attempts to use deep learning-based algorithms and brain frequencies to discriminate school-aged children with ASD from TD school-aged children should likely be a key step forward in auxiliary clinical utility.


Stacked autoencoder Classification School-aged children Autism spectrum disorder Brain frequency 



This study was supported by the Natural Science Foundation of China (Grant nos. 61662047). The authors would like to thank researchers and funding agencies that have contributed to ABIDE.

Compliance with ethical standards

Competing financial interests

The authors declare no competing financial interests.


  1. 1.
    Anderson JS, Nielsen JA, Froehlich AL, DuBray MB, Druzgal TJ, Cariello AN et al (2011d) Functional connectivity magnetic resonance imaging classification of autism. Brain 134:3742–3754CrossRefGoogle Scholar
  2. 2.
    Assaf M, Jagannathan K, Calhoun VD et al (2010) Abnormal functional connectivity of default mode sub-networks in autism spectrum disorder patients. NeuroImage 53(1):247–256CrossRefGoogle Scholar
  3. 3.
    Bajaj S, Adhikari BM, Dhamala M (2013) Higher frequency network activity flow predicts lower frequency node activity in intrinsic low-frequency BOLD fluctuations. PLoS One 8(5):e64466CrossRefGoogle Scholar
  4. 4.
    Baron-Cohen S (2009) Autism the empathizing-systemizing theory. Ann N Y Acad Sci 1156:68–80CrossRefGoogle Scholar
  5. 5.
    Barttfeld P, Wicker B, Cukier S et al (2012) State-dependent changes of connectivity patterns and functional brain network topology in autism spectrum disorder. Neuropsychologia 50(14):3653–3662CrossRefGoogle Scholar
  6. 6.
    Belmonte MK, Allen G, Beckelmitchener A et al (2004) Autism and abnormal development of brain connectivity. Journal of neuroscience the official journal of the society for. Neuroscience 24(42):9228–9231CrossRefGoogle Scholar
  7. 7.
    Buzsaki G, Draguhn A (2004) Neuronal oscillations in cortical networks. Science 304:1926–1929CrossRefGoogle Scholar
  8. 8.
    Chen H, Duan X, Liu F et al (2016) Multivariate classification of autism spectrum disorder using frequency-specific resting-state functional connectivity—a multi-center study. Prog Neuro-Psychopharmacol Biol Psychiatry 64:1–9CrossRefGoogle Scholar
  9. 9.
    Chen Y, He F, Wu Y et al (2017) A local start search algorithm to compute exact Hausdorff distance for arbitrary point sets. Pattern Recogn 67:139–148CrossRefGoogle Scholar
  10. 10.
    Courchesne E, Mouton PR, Calhoun ME et al (2011) Neuron number and size in prefrontal cortex of children with autism. JAMA 306(18):2001–2010CrossRefGoogle Scholar
  11. 11.
    Di MA, Kelly C, Grzadzinski R et al (2011) Aberrant striatal functional connectivity in children with autism[J]. Biol Psychiatry 69(9):847–856CrossRefGoogle Scholar
  12. 12.
    Dosreis S, Weiner CL, Johnson L et al (2006) Autism spectrum disorder screening and management practices among general pediatric providers. J Dev Behav Pediatr 27(2 Suppl):88–94CrossRefGoogle Scholar
  13. 13.
    Goh S, Dong Z, Zhang Y, DiMauro S, Peterson BS (2014) Mitochondrial dysfunction as a neurobiological subtype of autism Spectrum DisorderEvidence from brain imaging. JAMA Psychiatry 71:665–671CrossRefGoogle Scholar
  14. 14.
    Han Y, Wang J, Zhao Z et al (2011) Frequency-dependent changes in the amplitude of low-frequency fluctuations in amnestic mild cognitive impairment: a resting-state fMRI study. NeuroImage 55(1):287–295CrossRefGoogle Scholar
  15. 15.
    Hill EL, Frith U (2003) Understanding autism: insights from mind and brain. Philos Trans R Soc Lond B Biol Sci 358:281–289CrossRefGoogle Scholar
  16. 16.
    Hoptman MJ, Xi ZPDB, Javitt DC et al (2010) Amplitude of low-frequency oscillations in schizophrenia: a resting state fMRI study. Schizophr Res 117(1):13–20CrossRefGoogle Scholar
  17. 17.
    Huys QJ, Maia TV, Frank MJ (2016) Computational psychiatry as a bridge from neuroscience to clinical applications. Nat Neurosci 19(3):404–413CrossRefGoogle Scholar
  18. 18.
    Iidaka T (2015) Resting state functional magnetic resonance imaging and neural network classified autism and control. Cortex 63:55–67CrossRefGoogle Scholar
  19. 19.
    Levy F (2007) Theories of autism. Aust N Z J Psychiatr 41(11):859–868CrossRefGoogle Scholar
  20. 20.
    Li K, He F, Yu H et al (2017) A correlative classifiers approach based on particle filter and sample set for tracking occluded target. Appl Math J Chinese Univ 32(3):294–312MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Lord C, Rutter M, Le Couteur A (1994) Autism diagnostic interview-revised: a revised version of a diagnostic interview for caregivers of individuals with possible pervasive developmental disorders. J Autism Dev Disord 24:659–685CrossRefGoogle Scholar
  22. 22.
    Lord C, Rutter M, DiLavore PC, Risi S (1999) Autism diagnostic observation schedule. Los Angeles, Western Psychological ServiceGoogle Scholar
  23. 23.
    Luca MD, Beckmann CF, Stefano ND et al (2006) fMRI resting state networks define distinct modes of long-distance interactions in the human brain. NeuroImage 29(4):1359–1367CrossRefGoogle Scholar
  24. 24.
    Lynch CJ, Uddin LQ, Supekar K et al (2013) Default mode network in childhood autism: posteromedial cortex heterogeneity and relationship with social deficits. Biol Psychiatry 74(3):212–219CrossRefGoogle Scholar
  25. 25.
    Martino AD, Ghaffari M, Curchack J et al (2008) Decomposing intra-subject variability in children with attention-deficit/hyperactivity disorder. Biol Psychiatry 64(7):607–614CrossRefGoogle Scholar
  26. 26.
    McKeown MS, Sejnowski TJ (1998) Independent component analysis of fMRI data: Examining the assumptions. Hum Brain Mapp 6(5–6):368–372CrossRefGoogle Scholar
  27. 27.
    Murdaugh DL, Shinkareva SV, Deshpande HR et al (2012) Differential deactivation during Mentalizing and classification of autism based on default mode network connectivity. PLoS One 7(11):e50064CrossRefGoogle Scholar
  28. 28.
    Murillo L, Shih A, Rosanoff M et al (2016) The role of multi-stakeholder collaboration and community consensus building in improving identification and early diagnosis of autism in low-resource settings. Aust Psychol 51(4):280–286CrossRefGoogle Scholar
  29. 29.
    Association AP (2013) Diagnostic and statistical manual of mental disorders, 5th edn (DSM-5). American Psychiatric Association, Arlington, pp 4189–4189Google Scholar
  30. 30.
    Orrù G, Petterssonyeo W, Marquand AF et al (2012) Using support vector machine to identify imaging biomarkers of neurological and psychiatric disease: a critical review. Neurosci Biobehav Rev 36(4):1140–1152CrossRefGoogle Scholar
  31. 31.
    Penttonen M (2003) Natural logarithmic relationship between brain oscillators. Thalamus Relat Syst 2(2):145–152CrossRefGoogle Scholar
  32. 32.
    Perez Velazquez JL, Barcelo F, Hung Y et al (2009) Decreased brain coordinated activity in autism spectrum disorders during executive tasks: reduced long-range synchronization in the fronto-parietal networks. Int J Psychophysiol 73(3):341–349CrossRefGoogle Scholar
  33. 33.
    Autism and D. D. M. N. S. Y. P. Investigators (2014) Prevalence of autism spectrum disorder among children aged 8 years—autism and developmental disabilities monitoring network, 11 sites, United States, 2010. Morbidity and Mortality Weekly Report: Surveillance Summaries 63(2):1–21Google Scholar
  34. 34.
    Ruparelia K, Abubakar A, Badoe E et al (2016) Autism Spectrum Disorders in Africa: Current Challenges in Identification, Assessment, and Treatment: a report on the international child neurology association meeting on ASD in africa. J Child Neurol 31(8):1018–1026CrossRefGoogle Scholar
  35. 35.
    Salvador R, Martínez A, Pomarol-Clotet E et al (2008) A simple view of the brain through a frequency-specific functional connectivity measure. NeuroImage 39(1):279–289CrossRefGoogle Scholar
  36. 36.
    Siegel M, Donner TH, Engel AK (2012) Spectral fingerprints of large-scale neuronal interactions. Nat Rev Neurosci 13(2):121–134CrossRefGoogle Scholar
  37. 37.
    Syed MA, Yang Z, Hu XP et al (2017) Investigating brain Connectomic alterations in autism using the reproducibility of independent components derived from resting state functional MRI data. Front Neurosci 11:459CrossRefGoogle Scholar
  38. 38.
    Uddin LQ, Menon V, Young CB et al (2011) Multivariate searchlight classification of structural magnetic resonance imaging in children and adolescents with autism. Biol Psychiatry 70(9):833–841CrossRefGoogle Scholar
  39. 39.
    Uddin LQ, Supekar K, Lynch CJ et al (2013) Salience network–based classification and prediction of symptom severity in children with autism. Jama Psychiatry 70(8):869–879CrossRefGoogle Scholar
  40. 40.
    Wu Y, He F, Zhang D et al Service-oriented feature-based data exchange for cloud-based design and manufacturing. IEEE Trans Serv Comput.
  41. 41.
    Yan X, He F, Chen Y (2017) A novel hardware/software partitioning method based on position disturbed particle swarm optimization with invasive weed optimization. J Comput Sci Technol 32(2):340–355MathSciNetCrossRefGoogle Scholar
  42. 42.
    Zhang D, He F, Han S et al (2017) An efficient approach to directly compute the exact Hausdorff distance for 3D point sets. Integrated Computer-Aided Engineering 24(3):261–277CrossRefGoogle Scholar
  43. 43.
    Zhang YD, Hou XX, Lv YD et al (2017) Sparse autoencoder based deep neural network for Voxelwise detection of cerebral microbleed. IEEE, international conference on parallel and distributed systems. IEEE: 1229–32Google Scholar
  44. 44.
    Zhou Y, He F, Qiu Y (2017) Dynamic strategy based parallel ant Colony optimization on GPUs for TSPs. SCIENCE CHINA Inf Sci 60(6):068102CrossRefGoogle Scholar
  45. 45.
    Zuo XN, Di MA (2010) The oscillating brain: complex and reliable. NeuroImage 49(2):1432–1445CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Zhiyong Xiao
    • 1
    • 2
  • Canhua Wang
    • 1
    • 3
  • Nan Jia
    • 4
  • Jianhua Wu
    • 4
    Email author
  1. 1.School of Mechatronic EngineeringNanchang UniversityNanchangChina
  2. 2.School of SoftwareJiangxi Agricultural UniversityNanchangChina
  3. 3.School of ComputerJiangxi University of Traditional Chinese MedicineNanchangChina
  4. 4.School of Information EngineeringNanchang UniversityNanchangChina

Personalised recommendations