Abstract
Computational models often overfit on neuroimaging datasets (which are high-dimensional and consist of small sample sizes), resulting in poor inferences such as ungeneralisable biomarkers. One solution is to pool datasets (of similar disorders) from other sites to augment the small dataset, but such efforts have to handle variations introduced by site effects and inconsistent labelling. To overcome these issues, we propose an encoder-decoder-classifier architecture that combines semi-supervised learning with harmonisation of data across sites. The architecture is trained end-to-end via a novel multi-objective loss function. Using the architecture on multi-site fMRI datasets such as ADHD-200 and ABIDE, we obtained significant improvement on classification performance and showed how site-invariant biomarkers were disambiguated from site-specific ones. Our findings demonstrate the importance of accounting for both site effects and labelling inconsistencies when combining datasets from multiple sites to overcome the paucity of data. With the proliferation of neuroimaging research conducted on retrospectively aggregated datasets, our architecture offers a solution to handle site differences and labelling inconsistencies in such datasets. Code is available at https://github.com/SCSE-Biomedical-Computing-Group/SHRED.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Sites with too few data (site CMU in ABIDE) or extreme class imbalance (sites KKI, SBL, SDSU in ABIDE; KKI, PITT, WUSTL in ADHD-200) were excluded.
- 2.
In ABIDE I [9], 13 sites used clinical judgement along with the gold standard, while others used gold standards or clinical judgement only. There could be differences in clinical judgement, warranting the need to deal with label inconsistency.
References
Akiba, T., Sano, S., Yanase, T., Ohta, T., Koyama, M.: Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2623–2631 (2019)
Almuqhim, F., Saeed, F.: ASD-SAENet: a sparse autoencoder, and deep-neural network model for detecting autism spectrum disorder (ASD) using fMRI data. Front. Comput. Neurosci. 15, 27 (2021)
Bartels, A., Blaschko, M., Shelton, J.: Augmenting feature-driven fMRI analyses: Semi-supervised learning and resting state activity. In: Advances in Neural Information Processing Systems, vol. 22 (2009)
Bellec, P., Chu, C., Chouinard-Decorte, F., Benhajali, Y., Margulies, D.S., Craddock, R.C.: The neuro bureau ADHD-200 preprocessed repository. Neuroimage 144, 275–286 (2017)
Chen, C.P., et al.: Diagnostic classification of intrinsic functional connectivity highlights somatosensory, default mode, and visual regions in autism. NeuroImage Clin. 8, 238–245 (2015)
Chen, Y., Li, G., Ide, J.S., Luo, X., Li, C.S.R.: Sex differences in attention deficit hyperactivity symptom severity and functional connectivity of the dorsal striatum in young adults. Neuroimage Rep. 1(2), 100025 (2021)
Craddock, C., et al.: The neuro bureau preprocessing initiative: open sharing of preprocessed neuroimaging data and derivatives. Front. Neuroinform. 7, 27 (2013)
Di Martino, A., et al.: Enhancing studies of the connectome in autism using the autism brain imaging data exchange II. Sci. Data 4(1), 1–15 (2017)
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)
Gupta, S., Chan, Y.H., Rajapakse, J.C., Initiative, A.D.N., et al.: Obtaining leaner deep neural networks for decoding brain functional connectome in a single shot. Neurocomputing 453, 326–336 (2021)
Ingalhalikar, M., Shinde, S., Karmarkar, A., Rajan, A., Rangaprakash, D., Deshpande, G.: Functional connectivity-based prediction of autism on site harmonized abide dataset. IEEE Trans. Biomed. Eng. 68(12), 3628–3637 (2021)
Johnson, W.E., Li, C., Rabinovic, A.: Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics 8(1), 118–127 (2007)
Li, X., Gu, Y., Dvornek, N., Staib, L.H., Ventola, P., Duncan, J.S.: Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results. Med. Image Anal. 65, 101765 (2020)
Milham, M.P., Fair, D., Mennes, M., Mostofsky, S.H., et al.: The ADHD-200 consortium: a model to advance the translational potential of neuroimaging in clinical neuroscience. Front. Syst. Neurosci. 6, 62 (2012)
Noman, F., et al.: Graph autoencoders for embedding learning in brain networks and major depressive disorder identification. arXiv preprint arXiv:2107.12838 (2021)
Odaibo, S.: Tutorial: Deriving the standard variational autoencoder (VAE) loss function. arXiv preprint arXiv:1907.08956 (2019)
Parisot, S., et al.: Spectral graph convolutions for population-based disease prediction. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 177–185. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_21
Parkes, L., Satterthwaite, T.D., Bassett, D.S.: Towards precise resting-state fMRI biomarkers in psychiatry: synthesizing developments in transdiagnostic research, dimensional models of psychopathology, and normative neurodevelopment. Curr. Opin. Neurobiol. 65, 120–128 (2020)
Power, J.D., et al.: Functional network organization of the human brain. Neuron 72(4), 665–678 (2011)
Rakić, M., Cabezas, M., Kushibar, K., Oliver, A., Llado, X.: Improving the detection of autism spectrum disorder by combining structural and functional MRI information. NeuroImage Clin. 25, 102181 (2020)
Ramos, T.C., Balardin, J.B., Sato, J.R., Fujita, A.: Abnormal cortico-cerebellar functional connectivity in autism spectrum disorder. Front. Syst. Neurosci. 12, 74 (2019)
Schnack, H.G., Kahn, R.S.: Detecting neuroimaging biomarkers for psychiatric disorders: sample size matters. Front. Psych. 7, 50 (2016)
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: International Conference on Machine Learning, pp. 3145–3153. PMLR (2017)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319–3328. PMLR (2017)
van Engelen, J.E., Hoos, H.H.: A survey on semi-supervised learning. Mach. Learn. 109(2), 373–440 (2019). https://doi.org/10.1007/s10994-019-05855-6
Varoquaux, G.: Cross-validation failure: small sample sizes lead to large error bars. Neuroimage 180, 68–77 (2018)
Vogt, B.A.: Cingulate impairments in ADHD: comorbidities, connections, and treatment. Handb. Clin. Neurol. 166, 297–314 (2019)
Wang, M., Zhang, D., Huang, J., Yap, P.T., Shen, D., Liu, M.: Identifying autism spectrum disorder with multi-site fMRI via low-rank domain adaptation. IEEE Trans. Med. Imaging 39(3), 644–655 (2019)
Yu-Feng, Z., et al.: Altered baseline brain activity in children with ADHD revealed by resting-state functional MRI. Brain Develop. 29(2), 83–91 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chan, Y.H., Yew, W.C., Rajapakse, J.C. (2022). Semi-supervised Learning with Data Harmonisation for Biomarker Discovery from Resting State fMRI. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science, vol 13431. Springer, Cham. https://doi.org/10.1007/978-3-031-16431-6_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-16431-6_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16430-9
Online ISBN: 978-3-031-16431-6
eBook Packages: Computer ScienceComputer Science (R0)