Advertisement

Graph Neural Network for Interpreting Task-fMRI Biomarkers

  • Xiaoxiao LiEmail author
  • Nicha C. Dvornek
  • Yuan Zhou
  • Juntang Zhuang
  • Pamela Ventola
  • James S. Duncan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11768)

Abstract

Finding the biomarkers associated with ASD is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. A promising approach to identify biomarkers is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, i.e. brain networks constructed by fMRI. One way to interpret important features is through looking at how the classification probability changes if the features are occluded or replaced. The major limitation of this approach is that replacing values may change the distribution of the data and lead to serious errors. Therefore, we develop a 2-stage pipeline to eliminate the need to replace features for reliable biomarker interpretation. Specifically, we propose an inductive GNN to embed the graphs containing different properties of task-fMRI for identifying ASD and then discover the brain regions/sub-graphs used as evidence for the GNN classifier. We first show GNN can achieve high accuracy in identifying ASD. Next, we calculate the feature importance scores using GNN and compare the interpretation ability with Random Forest. Finally, we run with different atlases and parameters, proving the robustness of the proposed method. The detected biomarkers reveal their association with social behaviors and are consistent with those reported in the literature. We also show the potential of discovering new informative biomarkers. Our pipeline can be generalized to other graph feature importance interpretation problems.

Keywords

Graph Neural Network Task-fMRI ASD biomarker 

Notes

Acknowledgment

This work was supported by NIH Grant R01 NS035193.

References

  1. 1.
    Adebayo, J., et al.: Sanity checks for saliency maps. In: Advances in Neural Information Processing Systems, pp. 9505–9515 (2018)Google Scholar
  2. 2.
    Cangea, C., et al.: Towards sparse hierarchical graph classifiers. arXiv preprint arXiv:1811.01287 (2018)
  3. 3.
    Carroll, J.D., Chang, J.J.: Analysis of individual differences in multidimensional scaling via an N-way generalization of “Eckart-Young” decomposition. Psychometrika 35(3), 283–319 (1970)CrossRefGoogle Scholar
  4. 4.
    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
  5. 5.
    Destrieux, C., et al.: Automatic parcellation of human cortical gyri and sulci using standard anatomical nomenclature. NeuroImage 53(1), 1–15 (2010)CrossRefGoogle Scholar
  6. 6.
    Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch geometric. CoRR abs/1903.02428 (2019)Google Scholar
  7. 7.
    Gilmer, J., et al.: Neural message passing for quantum chemistry. In: ICML 2017, pp. 1263–1272. JMLR.org (2017)
  8. 8.
    Goldani, A.A., et al.: Biomarkers in autism. Front. Psychiatry 5, 100 (2014)CrossRefGoogle Scholar
  9. 9.
    Kaiser, M.D., et al.: Neural signatures of autism. Proc. Nat. Acad. Sci. 107(49), 21223–21228 (2010)CrossRefGoogle Scholar
  10. 10.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
  11. 11.
    Ktena, S.I., et al.: Distance metric learning using graph convolutional networks: application to functional brain networks. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 469–477. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66182-7_54CrossRefGoogle Scholar
  12. 12.
    Loe, C.W., Jensen, H.J.: Comparison of communities detection algorithms for multiplex. Physica A: Stat. Mech. Appl. 431, 29–45 (2015)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Nishii, R.: Box-Cox Transformation. Encyclopedia of Mathematics. Springer, New York (2001)zbMATHGoogle Scholar
  14. 14.
    Yang, D., et al.: Brain responses to biological motion predict treatment outcome in young children with autism. Transl. Psychiatry 6(11), e948 (2016)CrossRefGoogle Scholar
  15. 15.
    Yarkoni, T., et al.: Large-scale automated synthesis of human functional neuroimaging data. Nat. Methods 8(8), 665 (2011)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Xiaoxiao Li
    • 1
    Email author
  • Nicha C. Dvornek
    • 5
  • Yuan Zhou
    • 5
  • Juntang Zhuang
    • 1
  • Pamela Ventola
    • 4
  • James S. Duncan
    • 1
    • 2
    • 3
    • 5
  1. 1.Biomedical EngineeringYale UniversityNew HavenUSA
  2. 2.Electrical EngineeringYale UniversityNew HavenUSA
  3. 3.Statistics and Data ScienceYale UniversityNew HavenUSA
  4. 4.Child Study CenterYale School of MedicineNew HavenUSA
  5. 5.Radiology and Biomedical ImagingYale School of MedicineNew HavenUSA

Personalised recommendations