Abstract
Joint decomposition of functional magnetic resonance imaging (fMRI) time series into time courses of neural activity events and hemodynamic response functions (HRF) can enable new insights into functional connectivity, task activation, and neurovascular coupling in health and disease. Current methods for this problem handle time series of either temporally isolated events or extended blocks of continuous events but not both; and they constrain the HRF to one specific functional form. We propose to use an autoencoder and a convolutional neural network (CNN) to overcome these challenges. The autoencoder uses convolutional neural networks to reconstruct the fMRI time series while estimating the neural event time series. The CNN estimates the HRF as the convolutional filter that, when applied to a binarized version of the neural event time series, best reconstructs the fMRI time series. When applied to synthetic data and data simulated by the STANCE fMRI simulator, the method estimates ground-truth neural events and HRFs more robustly than competing methods. When applied to real-world fMRI data, the method identifies temporally isolated, continuous, or mixed neural events that correspond to experimental conditions more closely than competing methods. The flexibility and computational power of machine learning techniques enable the accurate capture of diverse HRFs and neural event time series from fMRI data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Buxton, R.B.: Dynamic models of BOLD contrast. Neuroimage 62(2), 953–961 (2012)
Buxton, R.B., et al.: Modeling the hemodynamic response to brain activation. Neuroimage 23, S220–S233 (2004)
Buxton, R.B., Wong, E.C., Frank, L.R.: Dynamics of blood flow and oxygenation changes during brain activation: the balloon model. Magn. Reson. Med. 39(6), 855–864 (1998)
Friston, K.J., Jezzard, P., Turner, R.: Analysis of functional MRI time-series. Hum. Brain Mapp. 1(2), 153–171 (1994)
Friston, K.J., et al.: Nonlinear responses in fMRI: the Balloon model, Volterra kernels, and other hemodynamics. Neuroimage 12(4), 466–477 (2000)
Handwerker, D.A., Ollinger, J.M., D’Esposito, M.: Variation of BOLD hemodynamic responses across subjects and brain regions and their effects on statistical analyses. Neuroimage 21(4), 1639–1651 (2004)
Huettel, S.A., Singerman, J.D., McCarthy, G.: The effects of aging upon the hemodynamic response measured by functional MRI. Neuroimage 13(1), 161–175 (2001)
Rangaprakash, D., et al.: Hemodynamic response function (HRF) variability confounds resting-state fMRI functional connectivity. Magn. Reson. Med. 80(4), 1697–1713 (2018)
West, K.L., et al.: BOLD hemodynamic response function changes significantly with healthy aging. Neuroimage 188, 198–207 (2019)
Buckner, R.L., et al.: Functional brain imaging of young, nondemented, and demented older adults. J. Cogn. Neurosci. 12(Supplement 2), 24–34 (2000)
Cherkaoui, H., et al.: Multivariate semi-blind deconvolution of fMRI time series. Neuroimage 241, 118418 (2021)
Rangaprakash, D., et al.: Hemodynamic variability in soldiers with trauma: implications for functional MRI connectivity studies. NeuroImage: Clin. 16, 409–417 (2017)
Rangaprakash, D., et al.: FMRI hemodynamic response function (HRF) as a novel marker of brain function: applications for understanding obsessive-compulsive disorder pathology and treatment response. Brain Imaging Behav. 15(3), 1622–1640 (2021)
Amaro Jr, E., Barker, G.J.: Study design in fMRI: basic principles. Brain Cogn. 60(3), 220–232 (2006)
Buckner, R.L.: Event-related fMRI and the hemodynamic response. Hum. Brain Mapp. 6(5–6), 373–377 (1998)
Fan, J., et al.: The activation of attentional networks. Neuroimage 26(2), 471–479 (2005)
Sheu, L.K., Jennings, J.R., Gianaros, P.J.: Test–retest reliability of an fMRI paradigm for studies of cardiovascular reactivity. Psychophysiology 49(7), 873–884 (2012)
Chuang, K.-C., et al.: Nonlinear conditional time-varying granger causality of task fMRI via deep stacking networks and adaptive convolutional kernels. In: Wang, L., Qi Dou, P., Fletcher, T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part I, pp. 271–281. Springer Nature Switzerland, Cham (2022). https://doi.org/10.1007/978-3-031-16431-6_26
Chuang, K.-C., et al.: Deep stacking networks for conditional nonlinear granger causal modeling of fMRI data. In: Abdulkadir, A.., et al. (eds.) Machine Learning in Clinical Neuroimaging: 4th International Workshop, MLCN 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings, pp. 113–124. Springer International Publishing, Cham (2021). https://doi.org/10.1007/978-3-030-87586-2_12
Friston, K., Harrison, L., Penny, W.: Dynamic causal modelling. Neuroimage 19(4), 1273–1302 (2003)
Friston, K., Moran, R., Seth, A.K.: Analysing connectivity with Granger causality and dynamic causal modelling. Curr. Opin. Neurobiol. 23(2), 172–178 (2013)
Chuang, K.-C., et al.: Brain effective connectivity and functional connectivity as markers of lifespan vascular exposures in middle-aged adults: the Bogalusa Heart Study. Front. Aging Neurosci. 15, 1110434 (2023)
Friston, K.: Functional and effective connectivity: a review. Brain Connect. 1(1), 13–36 (2011)
Wen, X., Rangarajan, G., Ding, M.: Is Granger causality a viable technique for analyzing fMRI data? PLoS ONE 8(7), e67428 (2013)
Wu, G.-R., et al.: A blind deconvolution approach to recover effective connectivity brain networks from resting state fMRI data. Med. Image Anal. 17(3), 365–374 (2013)
Seth, A.K., Chorley, P., Barnett, L.C.: Granger causality analysis of fMRI BOLD signals is invariant to hemodynamic convolution but not downsampling. Neuroimage 65, 540–555 (2013)
Aggarwal, P., Gupta, A., Garg, A.: Joint estimation of activity signal and HRF in fMRI using fused LASSO. In: 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE (2015)
Cherkaoui, H., et al.: Sparsity-based blind deconvolution of neural activation signal in fMRI. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2019)
Bühler, M., et al:, Does erotic stimulus presentation design affect brain activation patterns? Event-related vs. blocked fMRI designs. Behav. Brain Funct. 4(1), 1–12 (2008)
Donaldson, D.I.: Parsing brain activity with fMRI and mixed designs: what kind of a state is neuroimaging in? Trends Neurosci. 27(8), 442–444 (2004)
Asemani, D., Morsheddost, H., Shalchy, M.A.: Effects of ageing and Alzheimer disease on haemodynamic response function: a challenge for event-related fMRI. Healthcare Technol. Let. 4(3), 109–114 (2017)
Glover, G.H.: Deconvolution of impulse response in event-related BOLD fMRI1. Neuroimage 9(4), 416–429 (1999)
Arthur, D., Vassilvitskii, S.: K-means++ the advantages of careful seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms (2007)
Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16) (2016)
Chollet, F.: keras (2015)
Hill, J.E., et al.: A task-related and resting state realistic fMRI simulator for fMRI data validation. In: Medical Imaging 2017: Image Processing. International Society for Optics and Photonics (2017)
Penny, W.D., et al.: Statistical Parametric Mapping: The Analysis of Functional Brain Images. Elsevier (20110
Carmichael, O., et al.: High-normal adolescent fasting plasma glucose is associated with poorer midlife brain health: Bogalusa Heart Study. J. Clin. Endocrinol. Metab. 104(10), 4492–4500 (2019)
Glover, G.H., Li, T.Q., Ress, D.: Image-based method for retrospective correction of physiological motion effects in fMRI: RETROICOR. Magn. Reson. Medi. Offic. J. Int. Soc. Magn. Reson. Med. 44(1), 162–167 (2000)
Harvey, J.-L., et al.: A short, robust brain activation control task optimised for pharmacological fMRI studies. PeerJ 6, e5540 (2018)
Kirby, K.M., et al.: Neuroimaging, behavioral, and gait correlates of fall profile in older adults. Front. Aging Neurosci. 13, 630049 (2021)
Martindale, J., et al.: The hemodynamic impulse response to a single neural event. J. Cereb. Blood Flow Metab. 23(5), 546–555 (2003)
Yeşilyurt, B., Uğurbil, K., Uludağ, K.: Dynamics and nonlinearities of the BOLD response at very short stimulus durations. Magn. Reson. Imaging 26(7), 853–862 (2008)
Acknowledgments
Funding for this work was provided by NIH grants R01AG041200 and R01AG062309 as well as the Pennington Biomedical Research Foundation.
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
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chuang, KC., Ramakrishnapillai, S., Kirby, K., Van Gemmert, A.W.A., Bazzano, L., Carmichael, O.T. (2023). Joint Estimation of Neural Events and Hemodynamic Response Functions from Task fMRI via Convolutional Neural Networks. In: Abdulkadir, A., et al. Machine Learning in Clinical Neuroimaging. MLCN 2023. Lecture Notes in Computer Science, vol 14312. Springer, Cham. https://doi.org/10.1007/978-3-031-44858-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-44858-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44857-7
Online ISBN: 978-3-031-44858-4
eBook Packages: Computer ScienceComputer Science (R0)