Predicting behavior through dynamic modes in resting-state fMRI data

Ikeda, Shigeyuki; Kawano, Koki; Watanabe, Soichi; Yamashita, Okito; Kawahara, Yoshinobu

doi:10.1016/j.neuroimage.2021.118801

Cited by 11 publications

(7 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown that RSFC could predict cognition and task performance measures better than self-reported measures ( Dubois et al, 2018a ; Li et al, 2019a ; Kong et al, 2021a ). Dynamic functional connectivity is also more strongly associated with task performance measures than self-reported measures ( Vidaurre et al, 2017 ; Liégeois et al, 2019 ; Ikeda et al, 2022 ). Furthermore, utilizing functional connectivity from task fMRI rather resting-state fMRI has been shown to improve the prediction of cognition more than personality and mental health ( Chen et al, 2022 ).…”

Section: Discussionmentioning

confidence: 98%

Comparison between gradients and parcellations for functional connectivity prediction of behavior

et al. 2023

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 98%

Comparison between gradients and parcellations for functional connectivity prediction of behavior

et al. 2023

View full text Add to dashboard Cite

“…It has been shown that RSFC could predict cognition and task performance measures better than selfreported measures (Dubois et al, 2018a;Li et al, 2019a;Kong et al, 2021a). Dynamic functional connectivity is also more strongly associated with task performance measures than self-reported measures (Vidaurre et al, 2017;Liégeois et al, 2019;Ikeda et al, 2022). Furthermore, utilizing functional connectivity from task fMRI rather resting-state fMRI has been shown to improve the prediction of cognition more than personality and mental health .…”

Section: Prediction Of Task Performance Measures Is Better Than Self-...mentioning

confidence: 99%

Section: Prediction Of Task Performance Measures Is Better Than Self-...mentioning

confidence: 99%

Comparison Between Gradients and Parcellations for Functional Connectivity Prediction of Behavior

Kong

Tan

Wulan

et al. 2022

Preprint

View full text Add to dashboard Cite

Resting-state functional connectivity (RSFC) has been widely used to predict behavioral measures. To predict behavioral measures, there are different approaches for representing RSFC with parcellations and gradients being the two most popular approaches. There is limited comparison between parcellation and gradient approaches in the literature. Here, we compared different parcellation and gradient approaches for RSFC-based prediction of a broad range of behavioral measures in the Human Connectome Project (HCP) and Adolescent Brain Cognitive Development (ABCD) datasets. Among the parcellation approaches, we considered group-average “hard” parcellations (Schaefer et al., 2018), individual-specific “hard” parcellations (Kong et al., 2021a), and an individual-specific “soft” parcellation (spatial independent component analysis with dual regression; Beckmann et al., 2009). For gradient approaches, we considered the well-known principal gradients derived from diffusion embedding (Margulies et al., 2016), and the local gradient approach that detects local changes in RSFC across the cortex (Laumann et al., 2015). Across two regression algorithms (linear ridge regression and kernel ridge regression), we found that individual-specific hard-parcellation performed the best in the HCP dataset, while the principal gradients, spatial independent component analysis and group-average “hard” parcellations exhibited similar performance. On the other hand, principal gradients and all parcellation approaches performed similarly in the ABCD dataset. Across both datasets, local gradients performed the worst. Finally, we found that the principal gradient approach required at least 40 to 60 gradients in order to perform as well as parcellation approaches. While most principal gradient studies utilize a single gradient, our results suggest that incorporating higher order gradients could provide significant behaviorally relevant information.

show abstract

“…Time-delay coordinates DMD (tdcDMD) is a method used for decomposing standing waves into spatiotemporal patterns with high accuracy ( 21 ); tdcDMD was performed using the dmd.py function in the DMD toolbox ( https://github.com/erichson/DMDpack ). As described in a previous study ( 26 ), the BOLD signals of each subject were converted into DMs. As shown in Equation 1 , the BOLD signal matrix X was composed of rows representing the number of ROI,

and columns representing the number of measurements,

.…”

Section: Methodsmentioning

confidence: 99%

“…Moreover, DMs representing brain states describe intricate curved surfaces in a multidimensional space. In a previous study ( 26 ), the modified K-means clustering algorithm was applied to DMs and treated DMs with identical amplitudes and antiphases. However, this approach failed to disentangle intricate curved surfaces in a multidimensional space.…”

Section: Methodsmentioning

confidence: 99%

Manifold alteration between major depressive disorder and healthy control subjects using dynamic mode decomposition in resting-state fMRI data

Endo,

Ikeda,

Harada

et al. 2024

Front. Psychiatry

Self Cite

View full text Add to dashboard Cite

BackgroundThe World Health Organization has reported that approximately 300 million individuals suffer from the mood disorder known as MDD. Non-invasive measurement techniques have been utilized to reveal the mechanism of MDD, with rsfMRI being the predominant method. The previous functional connectivity and energy landscape studies have shown the difference in the coactivation patterns between MDD and HCs. However, these studies did not consider oscillatory temporal dynamics.MethodsIn this study, the dynamic mode decomposition, a method to compute a set of coherent spatial patterns associated with the oscillation frequency and temporal decay rate, was employed to investigate the alteration of the occurrence of dynamic modes between MDD and HCs. Specifically, The BOLD signals of each subject were transformed into dynamic modes representing coherent spatial patterns and discrete-time eigenvalues to capture temporal variations using dynamic mode decomposition. All the dynamic modes were disentangled into a two-dimensional manifold using t-SNE. Density estimation and density ratio estimation were applied to the two-dimensional manifolds after the two-dimensional manifold was split based on HCs and MDD.ResultsThe dynamic modes that uniquely emerged in the MDD were not observed. Instead, we have found some dynamic modes that have shown increased or reduced occurrence in MDD compared with HCs. The reduced dynamic modes were associated with the visual and saliency networks while the increased dynamic modes were associated with the default mode and sensory-motor networks.ConclusionTo the best of our knowledge, this study showed initial evidence of the alteration of occurrence of the dynamic modes between MDD and HCs. To deepen understanding of how the alteration of the dynamic modes emerges from the structure, it is vital to investigate the relationship between the dynamic modes, cortical thickness, and surface areas.

show abstract

Predicting behavior through dynamic modes in resting-state fMRI data

Cited by 11 publications

References 69 publications

Comparison between gradients and parcellations for functional connectivity prediction of behavior

Comparison between gradients and parcellations for functional connectivity prediction of behavior

Comparison Between Gradients and Parcellations for Functional Connectivity Prediction of Behavior

Manifold alteration between major depressive disorder and healthy control subjects using dynamic mode decomposition in resting-state fMRI data

Contact Info

Product

Resources

About