Wavelet coherence-based classifier: A resting-state functional MRI study on neurodynamics in adolescents with high-functioning autism

Bernas, Antoine; Aldenkamp, Albert P.; Zinger, Svitlana

doi:10.1016/j.cmpb.2017.11.017

Cited by 64 publications

(47 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A growing number of prior studies have indicated the need for characterizing FC using alternative measures. The advantages of harnessing both temporal and spectral information has been illustrated with the use of wavelet coherence to capture non-stationarity in BOLD signals in resting-state functional MRI 20,21 and for population-based classification 22 . Mutual information, which could be interpreted as the amount of information flowing between the given regions, has been shown to perform better in the context of task functional MRI 23 as well as resting-state functional MRI 24,25 .…”

Section: Discussionmentioning

confidence: 99%

Rethinking Measures of Functional Connectivity via Feature Extraction

Mohanty

Sethares

Nair

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Functional magnetic resonance imaging (fMRI)-based functional connectivity (FC) commonly characterizes the functional connections in the brain. Conventional quantification of FC by Pearson's correlation captures linear, time-domain dependencies among blood-oxygen-level-dependent (BOLD) signals. We examined measures to quantify FC by investigating: (i) Is Pearson's correlation sufficient to characterize FC? (ii) Can alternative measures better quantify FC? (iii) What are the implications of using alternative FC measures? FMRI analysis in healthy adult population suggested that: (i) Pearson's correlation cannot comprehensively capture BOLD inter-dependencies. (ii) Eight alternative FC measures were similarly consistent between task and resting-state fMRI, improved age-based classification and provided better association with behavioral outcomes. (iii) Formulated hypotheses were: first, in lieu of Pearson's correlation, an augmented, composite and multi-metric definition of FC is more appropriate; second, canonical large-scale brain networks may depend on the chosen FC measure. A thorough notion of FC promises better understanding of variations within a given population.open Scientific RepoRtS | (2020) 10:1298 | https://doi.org/10.1038/s41598-020-57915-wwww.nature.com/scientificreports www.nature.com/scientificreports/ dependencies). These different measures were compared and contrasted with three experiments which assessed the consistency of information provided by the FC measures, utility of the FC measures in population-based discrimination and the biological plausibility of using these FC measures.Experiment 1 (E1). The goal of the first experiment was to understand the relative consistency of the different FC measures when evaluated in young and healthy individuals. Within-individual consistency was first established by comparing the overlap (Sørensen-Dice similarity coefficient) of the FC pattern observed in task (motor and verbal) and resting-state functional MRI and then averaging across individuals for each FC measure. Findings from E1: Consistency of functional connectivity. Consistency of all of the identified FCmeasures was evaluated by comparing task functional MRI and resting-state functional MRI in young healthy adults (demographics in Table 1). Since the connectivity pattern may be different for each FC measure, the task functional MRI data offer a form of ground truth as they activate specific regions in the brain which can bear correspondence with those in resting condition. Thresholded FC maps (threshold = one standard deviation above grand mean) between task and resting-state conditions are illustrated for Pearson's correlation in Fig. 2 (subfigure A) and remaining FC measures in Supplementary Fig. 1.Consistency of resting-state FC, quantified by Sørensen-Dice similarity coefficient, is tabulated in Table 2 for the motor and language networks. While mostly comparable across many FC measures, the overlap coefficients for Pearson's correlation are not necessarily the best in any of these tested net...

show abstract

Section: Discussionmentioning

confidence: 99%

Rethinking Measures of Functional Connectivity via Feature Extraction

Mohanty

Sethares

Nair

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…A variation of Fourier Transform (FT) called Graph Fourier Transform (GFT) was applied on 172 subjects and control data where the author first computed the statistical measures from the healthy time series of a subject then projected that to a structural graph which was computed from the healthy connectome graph that resulted in better classification. In another study [ 28 ] using ICA (Independent Component Analysis) and their associated time series, wavelet-based coherence maps were built which when given to classifier for training, resulted in 86.7% and 80% testing accuracies on two different datasets containing 12 ASD, 18 controls and 12 ASD and 12 controls respectively. In [ 29 ] authors proposed a spatial filter approach that projected the covariance matrix of the BOLD signal of the ASD and control subjects to the orthogonal directions to make the two type of subjects highly separable.…”

Section: Related Research Workmentioning

confidence: 99%

A Three-Stage Teacher, Student Neural Networks and Sequential Feed Forward Selection-Based Feature Selection Approach for the Classification of Autism Spectrum Disorder

et al. 2020

View full text Add to dashboard Cite

Autism disorder, generally known as Autism Spectrum Disorder (ASD) is a brain disorder characterized by lack of communication skills, social aloofness and repetitions in the actions in the patients, which is affecting millions of the people across the globe. Accurate identification of autistic patients is considered a challenging task in the domain of brain disorder science. To address this problem, we have proposed a three-stage feature selection approach for the classification of ASD on the preprocessed Autism Brain Imaging Data Exchange (ABIDE) rs-fMRI Dataset. In the first stage, a large neural network which we call a “Teacher ” was trained on the correlation-based connectivity matrix to learn the latent representation of the input. In the second stage an autoencoder which we call a “Student” autoencoder was given the task to learn those trained “Teacher” embeddings using the connectivity matrix input. Lastly, an SFFS-based algorithm was employed to select the subset of most discriminating features between the autistic and healthy controls. On the combined site data across 17 sites, we achieved the maximum 10-fold accuracy of 82% and for the individual site-wise data, based on 5-fold accuracy, our results outperformed other state of the art methods in 13 out of the total 17 site-wise comparisons.

show abstract

“…On the one hand, wavelet coherence is a powerful mathematical tool of X t (in our study, X t is the oil return risks and other variables series (Other variables include OPEC oil production, non-OPEC oil production, world total petroleum consumption and oil supply or demand in countries)) with the non-stationary and continuous volatility. Recently, this approach has received great attention in crude oil markets [35][36][37][38][39][40]. On the other hand, numerous studies have attempted to examine the correlation between oil supply or demand and fluctuation in the crude oil price based on Granger tests [41].…”

Section: Data and Wavelet Approachmentioning

confidence: 99%

The Heterogeneous Interconnections between Supply or Demand Side and Oil Risks

Liao

et al. 2019

Energies

View full text Add to dashboard Cite

Due to the crucial implication of oil risks for economic growth and policy making, the aim of this paper is to explore the heterogeneous interconnections of supply or demand in oil risks over time horizons and different countries. Specifically, we first examine the correlation of supply or demand in oil return risks and show the relationships in different countries based on wavelet coherence. Furthermore, we explore the time-varying interconnections between supply- or demand-side and oil return risks, as well as oil producers and demand countries. The empirical results show that the correlation between supply and oil return risks is relatively stable, whereas the linkage between demand and oil return risks shows greater volatility due to the impact of specific events. Further study indicates that there are heterogeneous interconnections between supply- or demand-side and oil return risks over sample periods. Specifically, the sign of response could be divided into four phases, i.e., 1997–2002, 2002–2010, 2010–2013 and 2014–2018. In addition, the interconnections of the demand side could be divided into three phases due to the sign of it. What is more, the dynamic interconnections of oil producers’ or countries’ demands behave quite heterogeneously in different countries. Thus policymakers should focus on the coordination level and space capacity in the global crude oil market.

show abstract

Wavelet coherence-based classifier: A resting-state functional MRI study on neurodynamics in adolescents with high-functioning autism

Cited by 64 publications

References 33 publications

Rethinking Measures of Functional Connectivity via Feature Extraction

Rethinking Measures of Functional Connectivity via Feature Extraction

A Three-Stage Teacher, Student Neural Networks and Sequential Feed Forward Selection-Based Feature Selection Approach for the Classification of Autism Spectrum Disorder

The Heterogeneous Interconnections between Supply or Demand Side and Oil Risks

Contact Info

Product

Resources

About