Diagnosis of Autism Spectrum Disorders in Young Children Based on Resting-State Functional Magnetic Resonance Imaging Data Using Convolutional Neural Networks


Statistics show that the risk of autism spectrum disorder (ASD) is increasing in the world. Early diagnosis is most important factor in treatment of ASD. Thus far, the childhood diagnosis of ASD has been done based on clinical interviews and behavioral observations. There is a significant need to reduce the use of traditional diagnostic techniques and to diagnose this disorder in the right time and before the manifestation of behavioral symptoms. The purpose of this study is to present the intelligent model to diagnose ASD in young children based on resting-state functional magnetic resonance imaging (rs-fMRI) data using convolutional neural networks (CNNs). CNNs, which are by far one of the most powerful deep learning algorithms, are mainly trained using datasets with large numbers of samples. However, obtaining comprehensive datasets such as ImageNet and achieving acceptable results in medical imaging domain have become challenges. In order to overcome these two challenges, the two methods of “combining classifiers,” both dynamic (mixture of experts) and static (simple ‌Bayes) approaches, and “transfer learning” were used in this analysis. In addition, since diagnosis of ASD will be much more effective at an early age, samples ranging in age from 5 to 10 years from global Autism Brain Imaging Data Exchange I and II (ABIDE I and ABIDE II) datasets were used in this research. The accuracy, sensitivity, and specificity of presented model outperform the results of previous studies conducted on ABIDE I dataset (the best results obtained from Adamax optimization technique: accuracy = 0.7273, sensitivity = 0.712, specificity = 0.7348). Furthermore, acceptable classification results were obtained from ABIDE II dataset (the best results obtained from Adamax optimization technique: accuracy = 0.7, sensitivity = 0.582, specificity = 0.804) and the combination of ABIDE I and ABIDE II datasets (the best results obtained from Adam optimization technique: accuracy = 0.7045, sensitivity = 0.679, specificity = 0.7421). We can conclude that the proposed architecture can be considered as an efficient tool for diagnosis of ASD in young children. From another perspective, this proposed method can be applied to analyzing rs-fMRI data related to brain dysfunctions.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15


  1. 1.

    Crosson B, Ford A, McGregor KM, Meinzer M, Cheshkov S, Li X, Walker-Baston D, Briggs RW: Functional imaging and related techniques: An introduction for rehabilitation researchers. J Rehabil Res Dev 47(2):vii–xxxiv, 2010

    Article  Google Scholar 

  2. 2.

    Sarraf S, Sun J: Functional Brain Imaging: A Comprehensive Survey. arXiv preprint arXiv:1602.02225, 2005.

  3. 3.

    Fox MD, Snyder AZ, Vincent JL, Corbetta M, Essen DCV, Raichle ME: The human brain is intrinsically organized into dynamic, anticorrelated functional networks. Proc Natl Acad Sci USA 102(27):9673–9678, 2005. https://doi.org/10.1073/pnas.0504136102

    CAS  Article  PubMed  Google Scholar 

  4. 4.

    Buckner RL, Andrews-Hanna JR, Schacter DL: The brain’s default network. Ann NY Acad Sci 1124:1–38, 2008. https://doi.org/10.1196/annals.1440.011

    Article  PubMed  Google Scholar 

  5. 5.

    Wang J, Zuo X, He Y: Graph-based network analysis of resting-state functional MRI. Front Syst Neurosci, 2010. https://doi.org/10.3389/fnsys.2010.00016

  6. 6.

    Suk HI, Wee CY, Lee SW, Shen D: State-space model with deep learning for functional dynamics estimation in resting-state fMRI. Neuroimage 129:292–307, 2016. https://doi.org/10.1016/j.neuroimage.2016.01.005

    Article  PubMed  PubMed Central  Google Scholar 

  7. 7.

    Levy SE, Mandell DS, Schultz RT: Autism. Lancet 374(9701):1627–1638, 2009. https://doi.org/10.1016/S0140-6736(09)61376-3

    Article  PubMed  PubMed Central  Google Scholar 

  8. 8.

    Coleman M, Gillberg C: The Autisms. Oxford: Oxford University Press, 2012

    Google Scholar 

  9. 9.

    Waterhouse L: Rethinking Autism: Variation and Complexity. London: Academic Press, 2013

    Google Scholar 

  10. 10.

    Fernell E, Eriksson MA, Gillberg C: Early diagnosis of autism and impact on prognosis: a narrative review. Clin Epidemiol 5:33–43, 2013

    Article  Google Scholar 

  11. 11.

    Pennington ML, Cullinan D, Southern LB: Defining Autism: Variability in state education agency definitions of and evaluations for autism spectrum disorders. Autism Res Treat, 2014. https://doi.org/10.1155/2014/327271

    Article  Google Scholar 

  12. 12.

    Yerys BE, Pennington BF: How do we establish a biological marker for a behaviorally defined disorder? Autism as a test case. Autism Res 4(4):239–241, 2011

    Article  Google Scholar 

  13. 13.

    Plitt M, Barnes KA, Martin A: Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards. Neuroimage Clin 7:359–366, 2014. https://doi.org/10.1016/j.nicl.2014.12.013

    Article  PubMed  PubMed Central  Google Scholar 

  14. 14.

    Di Martino A, Yan CG, Li Q, Denio E, Castellanos FX, Alaerts K, Anderson JS, Assaf M, Bookheimer SY, Dapretto M, Deen B, Delmonte S, Dinstein I, Ertl-Wagner B, Fair DA, Gallagher L, Kennedy DP, Keown CL, Keysers C, Lainhart JE, Lord C, Luna B, Menon V, Minshew NJ, Monk CS, Mueller S, Müller RA, Nebel MB, Nigg JT, O’Hearn K, Pelphrey KA, Peltier SJ, Rudie JD, Sunaert S, Thioux M, Tyszka JM, Uddin LQ, Verhoeven JS, Wenderoth N, Wiggins JL, Mostofsky SH, Milham MP: The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol Psychiatry 19(6):659–667, 2014. https://doi.org/10.1038/mp.2013.78

    Article  PubMed  Google Scholar 

  15. 15.

    Nielsen JA, Zielinski BA, Fletcher PT, Alexander AL, Lange N, Bigler ED, Lainhart JE, Anderson JS: Multisite functional connectivity MRI classification of autism: ABIDE results. Front. Hum. Neurosci 7(599), 2013. https://doi.org/10.3389/fnhum.2013.00599

  16. 16.

    Anderson JS, Nielsen JA, Froehlich AL, DuBray MB, Druzgal TJ, Cariello AN, Cooperrider JR, Zielinski BA, Ravichandran C, Fletcher PT, Alexander AL, Bigler ED, Lange N, Lainhart JE: Functional connectivity magnetic resonance imaging classification of autism. Brain 134(12):3742–3754, 2011. https://doi.org/10.1093/brain/awr263

    Article  PubMed  Google Scholar 

  17. 17.

    Uddin LQ, Supekar K, Lynch CJ, Khouzam A, Phillips J, Feinstein C, Ryali S, Menon V: Salience network-based classification and prediction of symptom severity in children with autism. JAMA Psychiatry 70(8):869–879, 2013. https://doi.org/10.1001/jamapsychiatry.2013.104

    Article  PubMed  PubMed Central  Google Scholar 

  18. 18.

    Bell AJ, Sejnowski TJ: An information-maximization approach to blind separation and blind deconvolution. Neural Comput 7(6):1129–1159, 1995

    CAS  Article  Google Scholar 

  19. 19.

    McKeown MJ, Makeig S, Brown GG, Jung TP, Kindermann SS, Bell AJ, Sejnowski TJ: Analysis of fMRI data by blind separation into independent spatial components. Hum Brain Mapp 6(3):160–188, 1998

    CAS  Article  Google Scholar 

  20. 20.

    Ghiassian S, Greiner R, Jin P, Brown MRG: Using functional or structural magnetic resonance images and personal characteristic data to diagnose ADHD and autism. PLos ONE 11(12):e0166934, 2016

    Article  Google Scholar 

  21. 21.

    Sen B: Generalized Prediction Model for Detection of Psychiatric Disorders. Master Thesis, University of Alberta, 2016.

  22. 22.

    Plis SM, Hjelm D, Salakhutdinov R, Allen EA, Bockholt HJ, Long JD, Johnson HJ, Paulsen J, Turner JA, Calhoun VD: Deep learning for neuroimaging: a validation study. Front Neurosci 8, 2014. https://doi.org/10.3389/fnins.2014.00229

  23. 23.

    Olshausen BA: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583):607–609, 1996. https://doi.org/10.1038/381607a0

    CAS  Article  PubMed  Google Scholar 

  24. 24.

    Suk HI, Lee SW, Shen D: Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. Neuroimage 101:569–582, 2014. https://doi.org/10.1016/j.neuroimage.2014.06.077

    Article  PubMed  PubMed Central  Google Scholar 

  25. 25.

    Suk HI, Lee SW, Shen D: Latent feature representation with stacked auto-encoder for AD/MCI diagnosis. Brain Struct Funct 220(2):841–859, 2015. https://doi.org/10.1007/s00429-013-0687-3

    Article  PubMed  Google Scholar 

  26. 26.

    Sarraf S, Tofighi G: Classification of Alzheimer’s Disease Using fMRI Data and Deep Learning Convolutional Neural Networks. arXiv preprint arXiv:1603.08631, 2016.

  27. 27.

    Available at: http://image-net.org/challenges/LSVRC/

  28. 28.

    Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L: Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252, 2015

    Article  Google Scholar 

  29. 29.

    Available at: http://fcon_1000.projects.nitrc.org/indi/abide/

  30. 30.

    Jenkinson M, Smith SM: Pre-Processing of BOLD FMRI Data. Oxford University Centre for Functional MRI of the Brain (FMRIB), 2006.

  31. 31.

    Available at: http://www.fil.ion.ucl.ac.uk/spm/software/spm8/

  32. 32.

    Bowman FD, Guo Y, Derado G: Statistical approaches to functional neuroimaging data. Neuroimaging Clin N Am 17(4):441–458, 2007. https://doi.org/10.1016/j.nic.2007.09.002

    Article  PubMed  Google Scholar 

  33. 33.

    Hermans E: SPM8 Starters Guide, 2011. http://www.ernohermans.com.

  34. 34.

    Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS: Deep learning for visual understanding: a review. Neurocomputing 187:27–48, 2016. https://doi.org/10.1016/j.neucom.2015.09.116

    Article  Google Scholar 

  35. 35.

    Jacobs RA, Jordan MI, Steven JN, Georey EH: Adaptive mixtures of local experts. Neural Computation 3(1):79–87, 1991. https://doi.org/10.1162/neco.1991.3.1.79

    Article  PubMed  Google Scholar 

  36. 36.

    Nair V, Hinton GE: Rectified linear units improve restricted Boltzmann machines. In Proceedings of the International Conference on Machine Learning (ICML), 2010.

  37. 37.

    Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR: Improving Neural Networks by Preventing Co-adaptation of Feature Detectors. arXiv preprint arXiv: 1207.0580, 2012.

  38. 38.

    Ciresan DC, Meier U, Schmidhuber J: Transfer learning for Latin and Chinese characters with deep neural networks. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), 2012.

  39. 39.

    Ren JSJ, Xu L: On vectorization of deep convolutional neural networks for vision tasks. In: Proceedings of the Association for the Advancement of artificial intelligence (AAAI), the 29th international conference on artificial intelligence, 2015.

  40. 40.

    Ackey S, Kundegorski ME, Devereux M, Breckon TP: Transfer learning using convolutional neural networks for object classification within X-ray baggage security imagery. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), pp 1057–1061, 2016. https://doi.org/10.1109/ICIP.2016.7532519

  41. 41.

    Singh D, Garzon P: Using Convolutional Neural Networks and Transfer Learning to Perform Yelp Restaurant Photo Classification, 2016.

  42. 42.

    Tan C, Sun F, Kong T, Zhang W, Yang C, Liu C: A Survey on Deep Transfer Learning, arXiv preprint arXiv: 1808.01974, 2018.

  43. 43.

    Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35(5):1285–1298, 2016. https://doi.org/10.1109/TMI.2016.2528162

    Article  PubMed  Google Scholar 

  44. 44.

    Chollet F: Keras: Deep Learning Library for Theano and TensorFlow. 2015. https://github.com/fchollet/keras

  45. 45.

    Bastien F, Lamblin P, Pascanu R, Bergstra J, Goodfellow IJ, Bergeron A, Bouchard N, Warde-Farley D, Bengio Y: Theano: New features and speed improvements. In: Proceedings of the workshop on deep learning and unsupervised feature learning Neural Information Processing Systems (NIPS), 2012.

  46. 46.

    Theano Development Team: Theano: A Python framework for fast computation of mathematical expressions. arXiv preprint arXiv:1605.02688.

  47. 47.

    Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray DG, Steiner B, Tucker P, Vasudevan V, Warden P, Wicke M, Yu Y, Zheng X: Tensorflow: A system for large-scale machine learning. arXiv preprint arXiv:1605.08695, 2016.

  48. 48.

    Kingma DP, Ba JL: Adam: A method for stochastic optimization. In: Proceedings of the international conference on learning representations (ICLR), 2015.

Download references


We thank the Autism Brain Imaging Data Exchange (ABIDE) for generously sharing their data with scientific community.

Author information



Corresponding author

Correspondence to Arash Sharifi.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Aghdam, M.A., Sharifi, A. & Pedram, M.M. Diagnosis of Autism Spectrum Disorders in Young Children Based on Resting-State Functional Magnetic Resonance Imaging Data Using Convolutional Neural Networks. J Digit Imaging 32, 899–918 (2019). https://doi.org/10.1007/s10278-019-00196-1

Download citation


  • Autism spectrum disorder
  • Convolutional neural network
  • Transfer learning
  • Mixture of experts
  • Simple ‌Bayes