Accurate Predictions of Individual Differences in Task-evoked Brain Activity from Resting-state FMRI Using a Sparse Ensemble Learner

Overview

Journal Neuroimage

Specialty Radiology

Date 2022 Jul 1

PMID 35777635

Authors

Ying-Qiu Zheng

Seyedeh-Rezvan Farahibozorg

Weikang Gong

Hossein Rafipoor

Saad Jbabdi

Stephen Smith

Affiliations

Soon will be listed here.

Abstract

Modelling and predicting individual differences in task-fMRI activity can have a wide range of applications from basic to clinical neuroscience. It has been shown that models based on resting-state activity can have high predictive accuracy. Here we propose several improvements to such models. Using a sparse ensemble learner, we show that (i) features extracted using Stochastic Probabilistic Functional Modes (sPROFUMO) outperform the previously proposed dual-regression approach, (ii) that the shape and overall intensity of individualised task activations can be modelled separately and explicitly, (iii) training the model on predicting residual differences in brain activity further boosts individualised predictions. These results hold for both surface-based analyses of the Human Connectome Project data as well as volumetric analyses of UK-biobank data. Overall, our model achieves state of the art prediction accuracy on par with the test-retest reliability of task-fMRI scans, suggesting that it has potential to supplement traditional task localisers.

Citing Articles

Individualised prediction of longitudinal change in multimodal brain imaging.

Gong W, Beckmann C, Smith S Imaging Neurosci (Camb). 2025; 2:1-19.

PMID: 40046980 PMC: 11877422. DOI: 10.1162/imag_a_00215.

Exploring the neural basis of non-invasive prehabilitation in brain tumour patients: An fMRI-based case report of language network plasticity.

Boccuni L, Roca-Ventura A, Buloz-Osorio E, Leno-Colorado D, Martin-Fernandez J, Cabello-Toscano M Front Oncol. 2024; 14:1390542.

PMID: 38826790 PMC: 11140081. DOI: 10.3389/fonc.2024.1390542.

An atlas of trait associations with resting-state and task-evoked human brain functional organizations in the UK Biobank.

Zhao B, Li T, Li Y, Fan Z, Xiong D, Wang X Imaging Neurosci (Camb). 2024; 1:1-23.

PMID: 38770197 PMC: 11105703. DOI: 10.1162/imag_a_00015.

Predicting high-level visual areas in the absence of task fMRI.

Molloy M, Saygin Z, Osher D Sci Rep. 2024; 14(1):11376.

PMID: 38762549 PMC: 11102456. DOI: 10.1038/s41598-024-62098-9.

Dynamic effective connectivity among large-scale brain networks mediates risk of anxiety.

Tian T, Liu D, Zhang G, Wang J, Wan C, Fang J Hum Brain Mapp. 2023; 44(9):3730-3743.

PMID: 37042391 PMC: 10203788. DOI: 10.1002/hbm.26308.

References

van den Heuvel M, Mandl R, Hulshoff Pol H . Normalized cut group clustering of resting-state FMRI data. PLoS One. 2008; 3(4):e2001. PMC: 2291558. DOI: 10.1371/journal.pone.0002001. View

Lage-Castellanos A, Valente G, Formisano E, De Martino F . Methods for computing the maximum performance of computational models of fMRI responses. PLoS Comput Biol. 2019; 15(3):e1006397. PMC: 6426260. DOI: 10.1371/journal.pcbi.1006397. View

Farahibozorg S, Bijsterbosch J, Gong W, Jbabdi S, Smith S, Harrison S . Hierarchical modelling of functional brain networks in population and individuals from big fMRI data. Neuroimage. 2021; 243:118513. PMC: 8526871. DOI: 10.1016/j.neuroimage.2021.118513. View

Coalson T, Van Essen D, Glasser M . The impact of traditional neuroimaging methods on the spatial localization of cortical areas. Proc Natl Acad Sci U S A. 2018; 115(27):E6356-E6365. PMC: 6142239. DOI: 10.1073/pnas.1801582115. View

Parker Jones O, Voets N, Adcock J, Stacey R, Jbabdi S . Resting connectivity predicts task activation in pre-surgical populations. Neuroimage Clin. 2017; 13:378-385. PMC: 5222953. DOI: 10.1016/j.nicl.2016.12.028. View

Alfaro-Almagro F, Jenkinson M, Bangerter N, Andersson J, Griffanti L, Douaud G . Image processing and Quality Control for the first 10,000 brain imaging datasets from UK Biobank. Neuroimage. 2017; 166:400-424. PMC: 5770339. DOI: 10.1016/j.neuroimage.2017.10.034. View

Beckmann C, Smith S . Probabilistic independent component analysis for functional magnetic resonance imaging. IEEE Trans Med Imaging. 2004; 23(2):137-52. DOI: 10.1109/TMI.2003.822821. View

Dohmatob E, Richard H, Pinho A, Thirion B . Brain topography beyond parcellations: Local gradients of functional maps. Neuroimage. 2021; 229:117706. DOI: 10.1016/j.neuroimage.2020.117706. View

Smith S, Fox P, Miller K, Glahn D, Fox P, Mackay C . Correspondence of the brain's functional architecture during activation and rest. Proc Natl Acad Sci U S A. 2009; 106(31):13040-5. PMC: 2722273. DOI: 10.1073/pnas.0905267106. View

10.

Smith S, Hyvarinen A, Varoquaux G, Miller K, Beckmann C . Group-PCA for very large fMRI datasets. Neuroimage. 2014; 101:738-49. PMC: 4289914. DOI: 10.1016/j.neuroimage.2014.07.051. View

11.

Harrison S, Bijsterbosch J, Segerdahl A, Fitzgibbon S, Farahibozorg S, Duff E . Modelling subject variability in the spatial and temporal characteristics of functional modes. Neuroimage. 2020; 222:117226. PMC: 7779373. DOI: 10.1016/j.neuroimage.2020.117226. View

12.

Ellis D, Aizenberg M . Structural Brain Imaging Predicts Individual-Level Task Activation Maps Using Deep Learning. Front Neuroimaging. 2023; 1:834883. PMC: 10406267. DOI: 10.3389/fnimg.2022.834883. View

13.

Filippini N, MacIntosh B, Hough M, Goodwin G, Frisoni G, Smith S . Distinct patterns of brain activity in young carriers of the APOE-epsilon4 allele. Proc Natl Acad Sci U S A. 2009; 106(17):7209-14. PMC: 2678478. DOI: 10.1073/pnas.0811879106. View

14.

Salimi-Khorshidi G, Douaud G, Beckmann C, Glasser M, Griffanti L, Smith S . Automatic denoising of functional MRI data: combining independent component analysis and hierarchical fusion of classifiers. Neuroimage. 2014; 90:449-68. PMC: 4019210. DOI: 10.1016/j.neuroimage.2013.11.046. View

15.

Cole M, Bassett D, Power J, Braver T, Petersen S . Intrinsic and task-evoked network architectures of the human brain. Neuron. 2014; 83(1):238-51. PMC: 4082806. DOI: 10.1016/j.neuron.2014.05.014. View

16.

Yeo B, Krienen F, Sepulcre J, Sabuncu M, Lashkari D, Hollinshead M . The organization of the human cerebral cortex estimated by intrinsic functional connectivity. J Neurophysiol. 2011; 106(3):1125-65. PMC: 3174820. DOI: 10.1152/jn.00338.2011. View

17.

Bijsterbosch J, Beckmann C, Woolrich M, Smith S, Harrison S . The relationship between spatial configuration and functional connectivity of brain regions revisited. Elife. 2019; 8. PMC: 6541435. DOI: 10.7554/eLife.44890. View

18.

Ngo G, Khosla M, Jamison K, Kuceyeski A, Sabuncu M . Predicting individual task contrasts from resting-state functional connectivity using a surface-based convolutional network. Neuroimage. 2021; 248:118849. PMC: 10155599. DOI: 10.1016/j.neuroimage.2021.118849. View

19.

Miller K, Alfaro-Almagro F, Bangerter N, Thomas D, Yacoub E, Xu J . Multimodal population brain imaging in the UK Biobank prospective epidemiological study. Nat Neurosci. 2016; 19(11):1523-1536. PMC: 5086094. DOI: 10.1038/nn.4393. View

20.

Nickerson L, Smith S, Ongur D, Beckmann C . Using Dual Regression to Investigate Network Shape and Amplitude in Functional Connectivity Analyses. Front Neurosci. 2017; 11:115. PMC: 5346569. DOI: 10.3389/fnins.2017.00115. View