Discovering common change-point patterns in functional connectivity across subjects

Dai, Mengyu; Zhang, Zhengwu; Srivastava, Anuj

doi:10.1016/j.media.2019.101532

Cited by 13 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used resting state EPI scans of the first 200 participants from the Human Connectome Project S1200 (HCP, Smith et al., 2013b ; Van Essen et al., 2013 ), an open-access dataset of MRI data. Time-varying FC has previously been demonstrated in this dataset using a wide array of different approaches ( Battaglia et al., 2020 ; Casorso et al., 2019 ; Choe et al., 2017 ; Dai et al., 2019 ; Liegeois et al., 2019 ; Riccelli et al., 2017 ; Sporns et al., 2021 ; Vidaurre et al., 2017 ; Zalesky et al., 2014 ; Zamani Esfahlani et al., 2020 ), making it a suitable example to evaluate model stasis. The dataset consists of structural and functional MRI data of 1200 healthy, young adults (age 22–35).…”

Section: Methodsmentioning

confidence: 85%

Data and model considerations for estimating time-varying functional connectivity in fMRI

et al. 2022

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 85%

Data and model considerations for estimating time-varying functional connectivity in fMRI

et al. 2022

View full text Add to dashboard Cite

“…We used resting state EPI scans of the first 200 participants from the Human Connectome Project S1200 (HCP, (Smith et al, 2013b;Van Essen et al, 2013)), an open-access dataset of MRI data. Time-varying FC has previously been demonstrated in this dataset using a wide array of different approaches (Battaglia et al, 2020;Casorso et al, 2019;Choe et al, 2017;Dai et al, 2019;Liegeois et al, 2019;Riccelli et al, 2017;Sporns et al, 2021;Vidaurre et al, 2017;Zalesky et al, 2014;Zamani Esfahlani et al, 2020), making it a suitable example to evaluate model stasis. The dataset consists of structural and functional MRI data of 1200 healthy, young adults (age 22-35).…”

Section: Hcp Dataset and Preprocessingmentioning

confidence: 96%

Data and model considerations for estimating time-varying functional connectivity in fMRI

Ahrends¹,

Stevner

Pervaiz

et al. 2021

Preprint

View full text Add to dashboard Cite

Functional connectivity (FC) in the brain has been shown to exhibit subtle but reliable modulations within a session. One way of estimating time-varying FC is by using state-based models that describe fMRI time series as temporal sequences of states, each with an associated, characteristic pattern of FC. However, the estimation of these models from data sometimes fails to capture changes in a meaningful way, such that the model estimation assigns entire sessions (or the largest part of them) to a single state, therefore failing to capture within-session state modulations effectively; we refer to this phenomenon as the model becoming static, or model stasis. Here, we aim to quantify how the nature of the data and the choice of model parameters affect the model's ability to detect temporal changes in FC using both simulated fMRI time courses and resting state fMRI data. We show that large between-subject FC differences can overwhelm subtler within-session modulations, causing the model to become static. Further, the choice of parcellation can also affect the model's ability to detect temporal changes. We finally show that the model often becomes static when the number of free parameters that need to be estimated is high and the number of observations available for this estimation is low in comparison. Based on these findings, we derive a set of practical recommendations for time-varying FC studies, in terms of preprocessing, parcellation and complexity of the model.

show abstract

“…To facilitate the learning and explanation, the FC matrix needs to be mapped from the Riemannian space to the Euclidean space by projecting it onto a tangent plane of the Riemannian manifold and vice versa. In existing work, ( Dai et al, 2019 ) proposed to align the FC matric from different subjects within Riemannian manifold, which removes the differences between multiple sessions of a single subject (Yair et al, 2019 ). Since all the algebraic operations on functional brain networks are performed on the Riemannian manifold of SPD matrices, the network topology is well maintained during network inference.…”

Section: Introductionmentioning

confidence: 99%

Uncovering shape signatures of resting‐state functional connectivity by geometric deep learning on Riemannian manifold

Dan

Huang

Cai

et al. 2022

Human Brain Mapping

View full text Add to dashboard Cite

Functional neural activities manifest geometric patterns, as evidenced by the evolving network topology of functional connectivities (FC) even in the resting state. In this work, we propose a novel manifold‐based geometric neural network for functional brain networks (called “Geo‐Net4Net” for short) to learn the intrinsic low‐dimensional feature representations of resting‐state brain networks on the Riemannian manifold. This tool allows us to answer the scientific question of how the spontaneous fluctuation of FC supports behavior and cognition. We deploy a set of positive maps and rectified linear unit (ReLU) layers to uncover the intrinsic low‐dimensional feature representations of functional brain networks on the Riemannian manifold taking advantage of the symmetric positive‐definite (SPD) form of the correlation matrices. Due to the lack of well‐defined ground truth in the resting state, existing learning‐based methods are limited to unsupervised methodologies. To go beyond this boundary, we propose to self‐supervise the feature representation learning of resting‐state functional networks by leveraging the task‐based counterparts occurring before and after the underlying resting state. With this extra heuristic, our Geo‐Net4Net allows us to establish a more reasonable understanding of resting‐state FCs by capturing the geometric patterns (aka. spectral/shape signature) associated with resting states on the Riemannian manifold. We have conducted extensive experiments on both simulated data and task‐based functional resonance magnetic imaging (fMRI) data from the Human Connectome Project (HCP) database, where our Geo‐Net4Net not only achieves more accurate change detection results than other state‐of‐the‐art counterpart methods but also yields ubiquitous geometric patterns that manifest putative insights into brain function.

show abstract

Discovering common change-point patterns in functional connectivity across subjects

Cited by 13 publications

References 30 publications

Data and model considerations for estimating time-varying functional connectivity in fMRI

Data and model considerations for estimating time-varying functional connectivity in fMRI

Data and model considerations for estimating time-varying functional connectivity in fMRI

Uncovering shape signatures of resting‐state functional connectivity by geometric deep learning on Riemannian manifold

Contact Info

Product

Resources

About