3D Convolutional Neural Networks for Classification of Functional Connectomes

  • Meenakshi Khosla
  • Keith Jamison
  • Amy Kuceyeski
  • Mert R. SabuncuEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11045)


Resting-state functional MRI (rs-fMRI) scans hold the potential to serve as a diagnostic or prognostic tool for a wide variety of conditions, such as autism, Alzheimer’s disease, and stroke. While a growing number of studies have demonstrated the promise of machine learning algorithms for rs-fMRI based clinical or behavioral prediction, most prior models have been limited in their capacity to exploit the richness of the data. For example, classification techniques applied to rs-fMRI often rely on region-based summary statistics and/or linear models. In this work, we propose a novel volumetric Convolutional Neural Network (CNN) framework that takes advantage of the full-resolution 3D spatial structure of rs-fMRI data and fits non-linear predictive models. We showcase our approach on a challenging large-scale dataset (ABIDE, with \(N>2,000\)) and report state-of-the-art accuracy results on rs-fMRI-based discrimination of autism patients and healthy controls.


Functional connectivity fMRI Convolutional neural networks Autism ABIDE 



This work was supported by NIH grants R01LM012719 & R01AG053949 (MS), R21NS10463401 & R01NS10264601A1 (AK), NSF NeuroNex grant 1707312 (MS) & Anna-Maria & Stephen Kellen Foundation Junior Faculty Fellowship (AK).


  1. 1.
    Abraham, A., et al.: Deriving reproducible biomarkers from multi-site resting-state data: an autism-based example. NeuroImage 147, 736–745 (2017)CrossRefGoogle Scholar
  2. 2.
    Brown, C.J., Hamarneh, G.: Machine learning on human connectome data from MRI. CoRR, 1611.08699 (2016)Google Scholar
  3. 3.
    Cameron, C.R., et al.: A whole brain fMRI atlas generated via spatially constrained spectral clustering. Hum. Brain Mapp. 33(8), 1914–1928 (2012)CrossRefGoogle Scholar
  4. 4.
    Craddock, C., et al.: The neuro bureau preprocessing initiative: open sharing of preprocessed neuroimaging data and derivatives. Front. Neuroinformatics (2013)Google Scholar
  5. 5.
    Desikan, R.S., et al.: An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. NeuroImage 31(3), 968–980 (2006)CrossRefGoogle Scholar
  6. 6.
    Di Martino, A., et al.: Enhancing studies of the connectome in autism using the autism brain imaging data exchange II. Sci. Data 4, 170010 (2017)CrossRefGoogle Scholar
  7. 7.
    Dosenbach, N.U.F., Nardos, B., Cohen, A.L., et al.: Prediction of individual brain maturity using fMRI. Science 329(5997), 1358–1361 (2010)CrossRefGoogle Scholar
  8. 8.
    Eickhoff, S.B., et al.: A new spm toolbox for combining probabilistic cytoarchitectonic maps and functional imaging data. NeuroImage 25(4), 1325–1335 (2005)CrossRefGoogle Scholar
  9. 9.
    Heinsfeld, A.S., et al.: Identification of autism spectrum disorder using deep learning and the abide dataset. NeuroImage Clin. 17, 16–23 (2018)CrossRefGoogle Scholar
  10. 10.
    Kaiser, M.: A Tutorial in Connectome Analysis: Topological and Spatial Features of Brain Networks. ArXiv e-prints, May 2011Google Scholar
  11. 11.
    Kawahara, J., et al.: BrainNetCNN: convolutional neural networks for brain networks; towards predicting neurodevelopment. NeuroImage 146, 1038–1049 (2017)CrossRefGoogle Scholar
  12. 12.
    Kong, R., et al.: Spatial topography of individual-specific cortical networks predicts human cognition, personality, and emotion. Cereb. Cortex (2018)Google Scholar
  13. 13.
    Lancaster, J.L., Woldorff, M.G., et al.: Automated talairach atlas labels for functional brain mapping. Hum. Brain Mapp. 10(3), 120–131 (2000)CrossRefGoogle Scholar
  14. 14.
    Mennes, M., et al.: Resting state functional connectivity correlates of inhibitory control in children with ADHD. Front Psychiatry (2012)Google Scholar
  15. 15.
    Muschelli, J., Nebel, M.B., et al.: Reduction of motion-related artifacts in resting state fMRI using aCompCor. NeuroImage 96, 22–35 (2014)CrossRefGoogle Scholar
  16. 16.
    Niepert, M., et al.: Learning convolutional neural networks for graphs. In: Proceedings of Machine Learning Research, New York, USA, June 2016Google Scholar
  17. 17.
    Padmanabhan, A., et al.: The default mode network in autism. Biol. Psychiatry Cogn. Neurosci. Neuroimaging 2(6), 476–486 (2017)CrossRefGoogle Scholar
  18. 18.
    Plitt, M., et al.: Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards. NeuroImage Clin. 7, 359–366 (2015)CrossRefGoogle Scholar
  19. 19.
    Power, J.D., Mitra, A., et al.: Methods to detect, characterize, and remove motion artifact in resting state fMRI. NeuroImage 84, 320–341 (2014)CrossRefGoogle Scholar
  20. 20.
    Simonyan, K., et al.: Deep inside convolutional networks: visualising image classification models and saliency maps. CoRR, 1312.6034 (2013)Google Scholar
  21. 21.
    Tzourio-Mazoyer, N., et al.: Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. NeuroImage 15(1), 273–289 (2002)CrossRefGoogle Scholar
  22. 22.
    Varoquaux, G., Baronnet, F., Kleinschmidt, A., Fillard, P., Thirion, B.: Detection of brain functional-connectivity difference in post-stroke patients using group-level covariance modeling. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 200–208. Springer, Heidelberg (2010). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Meenakshi Khosla
    • 1
  • Keith Jamison
    • 2
    • 3
  • Amy Kuceyeski
    • 2
    • 3
  • Mert R. Sabuncu
    • 1
    • 4
    Email author
  1. 1.School of Electrical and Computer EngineeringCornell UniversityIthacaUSA
  2. 2.RadiologyWeill Cornell Medical CollegeNew York CityUSA
  3. 3.Brain and Mind Research InstituteWeill Cornell Medical CollegeNew York CityUSA
  4. 4.Nancy E. and Peter C. Meinig School of Biomedical EngineeringCornell UniversityIthacaUSA

Personalised recommendations