Abstract
Resting-state functional magnetic resonance imaging (rs-fMRI) has been a promising technique for computer-aided diagnosis of neurodevelopmental brain diseases, e.g., autism spectrum disorder (ASD), due to its sensitivity to the progressive variations of brain functional connectivity. To overcome the challenge of overfitting resulting from small sample size, recent studies began to fuse multi-site datasets for improving model generalization. However, these existing methods generally simply combine multiple sites into single dataset, ignoring the heterogeneity (i.e., data distribution discrepancy) among diverse sources. Actually, distribution alignment, alleviating the inter-site distribution shift, is the fundamental step for multi-site data analysis. In this paper, we propose a novel Transport-based Multi-site Joint Distribution Adaptation (TMJDA) framework to reduce multi-site heterogeneity for ASD diagnosis by aligning joint feature and label distribution using optimal transport (OT). Specifically, with the given target domain and multi-source domains, our TMJDA method concurrently performs joint distribution alignment in each pair of source and target domains, upon which, multiple domain-specific classifiers are further aligned by penalizing decision inconsistency among diverse classifiers for reducing inter-site distribution discrepancy. We evaluated our TMJDA model on the public Autism Brain Imaging Data Exchange (ABIDE) database. Experimental results demonstrate the effectiveness of our method in ASD diagnosis based on multi-site rs-fMRI datasets.
J. Zhang and P. Wan—These authors contributed equally to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amaral, D.G., et al.: Autism BrainNet: a network of postmortem brain banks established to facilitate autism research. Handb. Clin. Neurol. 150, 31–39 (2018)
Kana, R.K., et al.: Disrupted cortical connectivity theory as an explanatory model for autism spectrum disorders. Phys. Life Rev. 8(4), 410–437 (2011)
Maximo, J.O., et al.: The implications of brain connectivity in the neuropsychology of autism. Neuropsychol. Rev. 24(1), 16–31 (2014)
Anderson, J.S., et al.: Functional connectivity magnetic resonance imaging classification of autism. Brain 134(12), 3742–3754 (2011)
Wang, M., et al.: Multi-task exclusive relationship learning for Alzheimer’s disease progression prediction with longitudinal data. Med. Image Anal. 53, 111–122 (2019)
Heinsfeld, A.S., et al.: Identification of autism spectrum disorder using deep learning and the ABIDE dataset. NeuroImage Clin. 17, 16–23 (2018)
Button, K.S., et al.: Power failure: why small sample size undermines the reliability of neuroscience. Nat. Rev. Neurosci. 14(5), 365–376 (2013)
Abraham, A., et al.: Deriving reproducible biomarkers from multi-site resting-state data: an autism-based example. NeuroImage 147, 736–745 (2017)
Wang, M., Zhang, D., Huang, J., Shen, D., Liu, M.: Low-rank representation for multi-center autism spectrum disorder identification. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 647–654. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_73
Wachinger, C., et al.: Domain adaptation for Alzheimer’s disease diagnostics. NeuroImage 139, 470–479 (2016)
Itani, S., et al.: A multi-level classification framework for multi-site medical data: application to the ADHD-200 collection. Expert Syst. Appl. 91, 36–45 (2018)
Pan, S., et al.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2009)
Si, S., et al.: Bregman divergence-based regularization for transfer subspace learning. IEEE Trans. Knowl. Data Eng. 22(7), 929–942 (2009)
Long, M., et al.: Transfer feature learning with joint distribution adaptation. In: ICCV, pp. 2200–2207. IEEE, Piscataway (2013)
Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_35
Xu, R., et al.: Deep cocktail network: Multi-source unsupervised domain adaptation with category shift. In: CVPR, pp. 3964–3973. IEEE, Piscataway (2018)
Courty, N., Flamary, R., Tuia, D.: Domain adaptation with regularized optimal transport. In: Calders, T., Esposito, F., Hüllermeier, E., Meo, R. (eds.) ECML PKDD 2014. LNCS (LNAI), vol. 8724, pp. 274–289. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-44848-9_18
Courty, N., et al.: Optimal transport for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1853–1865 (2016)
Chambon, S., et al.: Domain adaptation with optimal transport improves EEG sleep stage classifiers. In: PRNI, pp. 1–4. IEEE, Piscataway (2018)
Di Martino, A., et al.: 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)
Craddock, C., et al.: Towards automated analysis of connectomes: the configurable pipeline for the analysis of connectomes (C-PAC). Front Neuroinform. 42 (2013)
Kantorovich, L.V.: On the translocation of masses. J. Math. Sci. 133(4), 1381–1382 (2006)
Courty, N., et al.: Joint distribution optimal transportation for domain adaptation. In: NeurIPS, pp. 3730–3739. MIT Press, Cambridge (2017)
Zhu, Y., et al.: Aligning domain-specific distribution and classifier for cross-domain classification from multiple sources. In: AAAI, pp. 5989–5996. AAAI, Palo Alto (2019)
Li, Z., et al.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2017)
Damodaran, B.B., Kellenberger, B., Flamary, R., Tuia, D., Courty, N.: DeepJDOT: deep joint distribution optimal transport for unsupervised domain adaptation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 467–483. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_28
Ganin, Y., et al.: Unsupervised domain adaptation by backpropagation. In: ICML, pp. 1180–1189. ACM, New York (2015)
Acknowledgement
This work was supported by the National Natural Science Foundation of China (Nos. 61876082, 61732006, 61861130366), the National Key R&D Program of China (Grant Nos. 2018YFC2001600, 2018YFC2001602, 2018ZX10201002) and the Royal Society-Academy of Medical Sciences Newton Advanced Fellowship (No. NAF\(\backslash \)R1\(\backslash \)180371).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, J., Wan, P., Zhang, D. (2020). Transport-Based Joint Distribution Alignment for Multi-site Autism Spectrum Disorder Diagnosis Using Resting-State fMRI. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12262. Springer, Cham. https://doi.org/10.1007/978-3-030-59713-9_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-59713-9_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59712-2
Online ISBN: 978-3-030-59713-9
eBook Packages: Computer ScienceComputer Science (R0)
