A low-rank multivariate general linear model for multi-subject fMRI data and a non-convex optimization algorithm for brain response comparison

Zhang, Tingting; Pham, Minh Tuan; Sun, Jianhui; Gao, Yan; Li, Huazhang; Sun, Yinge; Gonzalez, Marlen Z.; Coan, James A.

doi:10.1016/j.neuroimage.2017.12.032

Cited by 10 publications

(6 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HRF estimation with a data-driven approach or a smoothness constraint has been previously explored. The adopted methods included various constraints through, for example, Gaussian process prior (Goutte et al, 2000; Ciuciu et al, 2003), cubic smoothing splines (Zhang et al, 2007) Tikhonov regularization (Zhang et al, 2007; Casanova et al, 2008; Casanova et al 2009; Zhang et al 2012), spatial regularization (Badillo et al, 2013; Chaari et al, 2013; Zhang et al, 2018), cross validation (Zhang et al, 2013), nonlinear optimization (Pedregosa et al, 2015). Some of these methods were limited to individual-level modeling (Goutte et al, 2000; Goutte et al, 2000; Ciuciu et al, 2003; Zhang et al, 2007; Chaari et al, 2013; Pedregosa et al, 2015), and their applicability, performance, and computational feasibility of these applications at the population level remain to be explored.…”

Section: Discussionmentioning

confidence: 99%

“…Some of these methods were limited to individual-level modeling (Goutte et al, 2000;Goutte et al, 2000;Ciuciu et al, 2003;Zhang et al, 2007;Chaari et al, 2013;Pedregosa et al, 2015), and their applicability, performance, and computational feasibility of these applications at the population level remain to be explored. Other methods were confined at region level (Chaari et al, 2013;Zhang et al, 2012;Badillo et al, 2013;Zhang et al, 2013;Zhang et al, 2018) or resorted to information extraction through dimension reduction of HRF to two or three morphological features (Zhang et al, 2012;Zhang et al, 2013).…”

Section: The Importance Of Characterizing the Hrf Shapementioning

confidence: 99%

See 1 more Smart Citation

BOLD response is more than just magnitude: improving detection sensitivity through capturing hemodynamic profiles

Chen

Taylor

Reynolds

et al. 2023

Preprint

View full text Add to dashboard Cite

Typical FMRI analyses assume a canonical hemodynamic response function (HRF) with a focus on the overshoot peak height, while other morphological aspects are largely ignored. Thus, in most reported analyses, the overall effect is reduced from a curve to a single scalar. Here, we adopt a data-driven approach to HRF estimation at the whole-brain voxel level, without assuming a profile at the individual level. Then, we estimate the BOLD response in its entirety with a smoothness constraint at the population level to improve predictive accuracy and inferential efficiency. Instead of using just the scalar that represents the effect magnitude, we assess the whole HRF shape, which reveals additional information that may prove relevant for many aspects of a study, as well as for cross-study reproducibility. Through a fast event-related FMRI dataset, we demonstrate the extent of under-fitting and information loss that occurs when adopting the canonical approach. We also address the following questions: 1) How much does the HRF shape vary across regions, conditions, and clinical groups? 2) Does an agnostic approach improve sensitivity to detect an effect compared to an assumed HRF? 3) Can examining HRF shape help validate the presence of an effect complementing statistical evidence? 4) Could the HRF shape provide evidence for whole-brain BOLD response during a simple task?

show abstract

Section: Discussionmentioning

confidence: 99%

Section: The Importance Of Characterizing the Hrf Shapementioning

confidence: 99%

BOLD response is more than just magnitude: improving detection sensitivity through capturing hemodynamic profiles

Chen

Taylor

Reynolds

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The low rankness of the fMRI signal per slice has been used in image reconstruction techniques for compressed sensing applications [36] (usually in the z-axis). Moreover, low-rank constraints (in the spatial domain of fMRI) have been very recently used in a multi-way alternative of the classical General Linear Model (GLM) [37] for monitoring brain responses. Further evidence that motivates the use of low-rank constraints in the spatial domain, per slice, is provided by the Multi-Subject Dictionary Learning (MSDL) probabilistic atlas [38].…”

Section: Tensors and (Un)folding Of Fmri Datamentioning

confidence: 99%

Blind fMRI source unmixing via higher-order tensor decompositions

Chatzichristos

Kofidis

Morante

2019

Journal of Neuroscience Methods

View full text Add to dashboard Cite

Background: The growing interest in neuroimaging technologies generates a massive amount of biomedical data of high dimensionality. Tensor-based analysis of brain imaging data has been recognized as an effective analysis that exploits its inherent multi-way nature. In particular, the advantages of tensorial over matrix-based methods have previously been demonstrated in the context of functional magnetic resonance imaging (fMRI) source localization. However, such methods can also become ineffective in realistic challenging scenarios, involving, e.g., strong noise and/or significant overlap among the activated regions. Moreover, they commonly rely on the assumption of an underlying multilinear model generating the data.-New Method: This paper aims at investigating the possible gains from exploiting the 4-dimensional nature of the brain images, through a higher-order tensorization of the fMRI signal, and the use of less restrictive generative models. In this context, the higher-order Block Term Decomposition (BTD) and the PARAFAC2 tensor models are considered for the first time in fMRI blind source separation. A novel PARAFAC2-like extension of BTD (BTD2) is also proposed, aiming at combining the effectiveness of BTD in handling strong instances of noise and the potential of PARAFAC2 to cope with datasets that do not follow the strict multilinear assumption.-Comparison with Existing Methods: The methods were tested using both synthetic and real data and compared with state of the art methods.-Conclusions: The simulation results demonstrate the effectiveness of BTD and BTD2 for challenging scenarios (presence of noise, spatial overlap among activation regions and inter-subject variability in the Haemodynamic Response Function (HRF)).

show abstract

“…The data set is extracted from a time series functional magnetic resonance imaging (fMRI) data set. The predictors includes 3375 features collected from 106 subjects during a psychology experiment to study the human brain's emotion function [48]. The response variable is the scores of the subjects on his/her arousal feeling experienced during the experiment.…”

Section: Non-convex Cauchy Lossmentioning

confidence: 99%

An outer–inner linearization method for non-convex and nondifferentiable composite regularization problems

et al. 2021

Self Cite

View full text Add to dashboard Cite

We propose a new outer-inner linearization method for non-convex statistical learning problems involving non-convex structural penalties and non-convex loss. Many important statistical problems fall in this category, including the robust M-estimators, generalized linear models, and different types of structured learning problems. Our method exploits the fact that many such loss and penalty functions can be represented as compositions of smooth concave functions and nonsmooth convex functions. It linearizes the outer concave functions and solves the resulting convex, but still nonsmooth, subproblems by a special alternating linearization method. We provide proof of convergence to a stationary point of the method under mild conditions. Finally, numerical examples involving non-convex structural penalties and non-convex loss functions demonstrate the efficacy and accuracy of the method.

show abstract

A low-rank multivariate general linear model for multi-subject fMRI data and a non-convex optimization algorithm for brain response comparison

Cited by 10 publications

References 82 publications

BOLD response is more than just magnitude: improving detection sensitivity through capturing hemodynamic profiles

BOLD response is more than just magnitude: improving detection sensitivity through capturing hemodynamic profiles

Blind fMRI source unmixing via higher-order tensor decompositions

An outer–inner linearization method for non-convex and nondifferentiable composite regularization problems

Contact Info

Product

Resources

About