|
Overview
|
|
|
Yu Zhang, Wei Wu, Russell T. Toll, Sharon Naparstek, Adi Maron-Katz, Mallissa Watts, Joseph Gordon, Jisoo Jeong, Laura Astolfi, Emmanuel Shpigel, Parker Longwell, Kamron Sarhadi, Dawlat EI-Said, Yuanqing Li, Crystal Cooper, Cherise Chin-Fatt, Martjn Arns, Madhukar H. Trivedi, Charles R. Marmar, Amit Etkin
Nature Biomedical Engineering, 2021 Motivation: The understanding and treatment of psychiatric disorders are known to be neurobiologically and clinically heterogeneous but could benefit from the data-driven identification of disease subtypes. Solution: We developed a data-driven subtyping framework based on unsupervised sparse clustering to accomplished simultaneous feature selection and sample clustering on the power-envelope-based connectivity of signals reconstructed from high-density resting-state EEG. Extensive validation and replication were performed on four independent datasets involving two different psychiatric disorders, including PTSD and MDD. Results: We identified the disease subtypes and showed that the subtypes are transferable across independent datasets recorded under different conditions. The subtype whose functional connectivity differed most from those of healthy controls was less responsive to psychotherapy treatment for PTSD and failed to respond to antidepressant medication for MDD. By contrast, both subtypes responded equally well to two different forms of repetitive transcranial magnetic stimulation therapy for MDD. Our data-driven approach may constitute a generalizable solution for connectome-based diagnosis. |
|
|
|
|
Wei Wu, Yu Zhang, Jing Jiang, Molly Lucas, Gregory Fonzon, Camarin Rolle, Crystal Cooper, Cherise Chin-Fatt, Noralie Krepel, Carena Cornelssen, Rachael Wright, Russel Toll, Hersh Trivedi, Karen Monuszko, Trevor Caudle, Kamron Sarhadi, Manish Jha, Joseph Trombello, Thilo Deckersbach, Phil Adams, Patrick McGrath, Myrna Weissman, Maurizio Fava, Diego Pizzagalli, Martjin Arns, Madhukar Trivedi, Amit Etkin
Nature Biotechnology, 2020 Problem: Antidepressants are widely prescribed, but their efficacy relative to placebo is modest, in part because the clinical diagnosis of major depression encompasses biologically heterogeneous conditions. Solution: We designed a latent-space machine-learning algorithm tailored for resting-state EEG and applied it to data from the largest imaging-coupled, placebocontrolled antidepressant study. Results: Our computational model robustly predicted treatment outcome with the antidepressant sertraline and distinguishing between response to sertraline versus placebo at the individual patient level and which may furthermore support treatment selection between medication and rTMS. Together, these findings ground in individual-level neurobiology a treatment-responsive phenotype obscured within the broader clinical diagnosis of depression and its associated biological heterogeneity and lay a path toward machine-learning-driven personalized approaches to treatment in depression. |
|
|
Gregory Fonzon#, Amit Etkin#, Yu Zhang#, Wei Wu, Crystal Cooper, Cherise Chin-Fatt, Manish Jha, Joseph Trombello, Thilo Deckersbach, Phil Adams, Melvin Mclnnis, Patrick McGrath, Myrna Weissman, Maurizio Fava, Maduhkar Trivedi
Nature Human Behaviour, 2019 (#Co-first authors) Problem: The efficacy of antidepressant treatment for depression is controversial due to the only modest superiority demonstrated over placebo. However, neurobiological heterogeneity within depression may limit overall antidepressant efficacy. Solution: We propose to identify a neurobiological phenotype responsive to antidepressant treatment by testing pretreatment brain activation during response to, and regulation of, emotional conflict as a moderator of the clinical benefit of the antidepressant sertraline versus placebo. Results: Using neuroimaging data from a large randomized controlled trial, we found widespread moderation of clinical benefits by brain activity during regulation of emotional conflict, in which greater downregulation of conflict-responsive regions predicted better sertraline outcomes. Treatment-predictive machine learning using brain metrics outperformed a model trained on clinical and demographic variables. |
|
|
|
|
Yu Zhang, Han Zhang, Xiaobo Chen, Mingxia Liu, Xiaofeng Zhu, Seong-Whan Lee, Dinggang Shen
Pattern Recognition, 2019 Problem: Conventional brain network modeling often results in large inter-subject variability in the network structure. This could reduce the statistical power in group comparison, or even deteriorate the generalization capability of the individualized diagnosis of brain diseases. Solution: We propose to integrate individual functional connectivity information into the GSR-based network construction framework to achieve higher between-group separability while maintaining the merit of within-group consistency. Results: Outstanding performance of individualized mild cognitive impairment identification demonstrates that our method provides a promising and generalized solution for the future connectome-based personalized diagnosis of brain disease. |
|
|
|
Temporally constrained sparse group spatial patterns for motor imagery BCI
IEEE Transactions on Cybernetics, 2018
Yu Zhang, Chang S. Nam, Guoxu Zhou, Jing Jin, Xingyu Wang, Andrzej Cichocki
Problem: The effectiveness of CSP is highly affected by the frequency band and time window of EEG segments. Although numerous algorithms have been designed to optimize the spectral bands of CSP, most of them selected the time window in a heuristic way. This is likely to result in a suboptimal feature extraction since the time period when the brain responses to the mental tasks occurs may not be accurately detected.
Solution: we propose a novel algorithm, namely temporally constrained sparse group spatial pattern, for the simultaneous optimization of filter bands and time window within CSP to further boost classification accuracy of MI EEG.
Results: Superiority classification performance on three BCI competition datasets demonstrates that our proposed algorithm is a promising candidate for developing improved motor-imagery BCI systems.
IEEE Transactions on Cybernetics, 2018
Yu Zhang, Chang S. Nam, Guoxu Zhou, Jing Jin, Xingyu Wang, Andrzej Cichocki
Problem: The effectiveness of CSP is highly affected by the frequency band and time window of EEG segments. Although numerous algorithms have been designed to optimize the spectral bands of CSP, most of them selected the time window in a heuristic way. This is likely to result in a suboptimal feature extraction since the time period when the brain responses to the mental tasks occurs may not be accurately detected.
Solution: we propose a novel algorithm, namely temporally constrained sparse group spatial pattern, for the simultaneous optimization of filter bands and time window within CSP to further boost classification accuracy of MI EEG.
Results: Superiority classification performance on three BCI competition datasets demonstrates that our proposed algorithm is a promising candidate for developing improved motor-imagery BCI systems.
|
|
Sparse Bayesian classification of EEG for brain-computer interface
IEEE Transactions on Neural Networks and Learning Systems, 2016
Yu Zhang, Guoxu Zhou, Jing Jin, Qibin Zhao, Xingyu Wang, Andrzej Cichocki
Problem: The effectiveness of regularization is often highly dependent on the selection of regularization parameters that are typically determined by crossvalidation (CV). However, the CV imposes two main limitations on BCIs: 1) a large amount of training data is required from the user and 2) it takes a relatively long time to calibrate the classifier. These limitations substantially deteriorate the system’s practicability and may cause a user to be reluctant to use BCIs.
Solution: We introduce a sparse Bayesian method by exploiting Laplace priors, namely, SBLaplace, for EEG classification. A sparse discriminant vector is learned with a Laplace prior in a hierarchical fashion under a Bayesian evidence framework.
Results: The experimental results demonstrate that the SBLaplace algorithm achieves better overall performance than the state-of-the-art algorithms for EEG classification.
IEEE Transactions on Neural Networks and Learning Systems, 2016
Yu Zhang, Guoxu Zhou, Jing Jin, Qibin Zhao, Xingyu Wang, Andrzej Cichocki
Problem: The effectiveness of regularization is often highly dependent on the selection of regularization parameters that are typically determined by crossvalidation (CV). However, the CV imposes two main limitations on BCIs: 1) a large amount of training data is required from the user and 2) it takes a relatively long time to calibrate the classifier. These limitations substantially deteriorate the system’s practicability and may cause a user to be reluctant to use BCIs.
Solution: We introduce a sparse Bayesian method by exploiting Laplace priors, namely, SBLaplace, for EEG classification. A sparse discriminant vector is learned with a Laplace prior in a hierarchical fashion under a Bayesian evidence framework.
Results: The experimental results demonstrate that the SBLaplace algorithm achieves better overall performance than the state-of-the-art algorithms for EEG classification.
|
|
Frequency Recognition in SSVEP-based BCI using Multiset Canonical Correlation Analysis
International Journal of Neural Systems, 2014
Yu Zhang, Guoxu Zhou, Jing Jin, Xingyu Wang, Andrzej Cichocki
Problem: Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognitionin steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Despite its efficiency, a potential problem is that using pre-constructed sine-cosine waves as the required reference signals in the CCA method often does not result in the optimal recognition accuracy due to their lack of features from the real EEG data.
Solution: We proposes a novel method based on multiset canonical correlation analysis (MsetCCA) to optimize the reference signals used in the CCA method for SSVEP frequency recognition. The MsetCCA method learns multiple linear transforms that implement joint spatial filtering to maximize the overall correlation among canonical variates, and hence extracts SSVEP common features from multiple sets of EEG data recorded at the same stimulus frequency. The optimized reference signals are formed by combination of the common features and completely based on training data.
Results: Experimental study with EEG data from ten healthy subjects demonstrates that the MsetCCA method improves the recognition accuracy of SSVEP frequency in comparison with the CCA method and other two competing methods (multiway CCA (MwayCCA) and phase constrained CCA (PCCA)), especially for a small number of channels and a short time window length. The superiority indicates that the proposed MsetCCA method is a new promising candidate for frequency recognition in SSVEP-based BCIs.
International Journal of Neural Systems, 2014
Yu Zhang, Guoxu Zhou, Jing Jin, Xingyu Wang, Andrzej Cichocki
Problem: Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognitionin steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Despite its efficiency, a potential problem is that using pre-constructed sine-cosine waves as the required reference signals in the CCA method often does not result in the optimal recognition accuracy due to their lack of features from the real EEG data.
Solution: We proposes a novel method based on multiset canonical correlation analysis (MsetCCA) to optimize the reference signals used in the CCA method for SSVEP frequency recognition. The MsetCCA method learns multiple linear transforms that implement joint spatial filtering to maximize the overall correlation among canonical variates, and hence extracts SSVEP common features from multiple sets of EEG data recorded at the same stimulus frequency. The optimized reference signals are formed by combination of the common features and completely based on training data.
Results: Experimental study with EEG data from ten healthy subjects demonstrates that the MsetCCA method improves the recognition accuracy of SSVEP frequency in comparison with the CCA method and other two competing methods (multiway CCA (MwayCCA) and phase constrained CCA (PCCA)), especially for a small number of channels and a short time window length. The superiority indicates that the proposed MsetCCA method is a new promising candidate for frequency recognition in SSVEP-based BCIs.
|
|
Aggregation of Sparse Linear Discriminant Analysis for Event-Related Potential Classification in Brain-Computer Interface
International Journal of Neural Systems, 2014
Yu Zhang, Guoxu Zhou, Jing Jin, Qibin Zhao , Xingyu Wang, Andrzej Cichocki
Problem: Two main issues for event-related potential (ERP) classification in brain-computer interface applicationare curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classification performance, especially with insufficient training samples resulted from limited calibration time.
Solution: This study introduces an aggregation of sparse linear discriminant analyses (ASLDA) to overcome these problems. In the ASLDA, multiple sparse discriminant vectors are learned from differently L1-regularized least-squares regressions by exploiting the equivalence between LDA and least-squares regression, and are subsequently aggregated to form an ensemble classifier, which could not only implement automatic feature selection for dimensionality reduction to alleviate curse-of-dimensionality, but also decrease the variance to improve generalization capacity for new test samples.
Results: Extensive investigation and comparison are carried out among the ASLDA, the ordinary LDA and other competing ERP classification algorithms, based on different three ERP datasets. Experimental results indicate that the ASLDA yields better overall performance for single-trial ERP classification when insufficient training samples are available. This suggests the proposed ASLDA is promising for ERP classification in small sample size scenario to improve the practicability of brain-computer interface.
International Journal of Neural Systems, 2014
Yu Zhang, Guoxu Zhou, Jing Jin, Qibin Zhao , Xingyu Wang, Andrzej Cichocki
Problem: Two main issues for event-related potential (ERP) classification in brain-computer interface applicationare curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classification performance, especially with insufficient training samples resulted from limited calibration time.
Solution: This study introduces an aggregation of sparse linear discriminant analyses (ASLDA) to overcome these problems. In the ASLDA, multiple sparse discriminant vectors are learned from differently L1-regularized least-squares regressions by exploiting the equivalence between LDA and least-squares regression, and are subsequently aggregated to form an ensemble classifier, which could not only implement automatic feature selection for dimensionality reduction to alleviate curse-of-dimensionality, but also decrease the variance to improve generalization capacity for new test samples.
Results: Extensive investigation and comparison are carried out among the ASLDA, the ordinary LDA and other competing ERP classification algorithms, based on different three ERP datasets. Experimental results indicate that the ASLDA yields better overall performance for single-trial ERP classification when insufficient training samples are available. This suggests the proposed ASLDA is promising for ERP classification in small sample size scenario to improve the practicability of brain-computer interface.
|
|
L1-Regularized Multiway Canonical Correlation Analysis for SSVEP-based BCI
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013
Yu Zhang, Guoxu Zhou, Jing Jin, Xingyu Wang, Andrzej Cichocki
This study introduces an L1-regularized multiway canonical correlation analysis (L1-MCCA) for reference signal optimization to improve the SSVEP recognition performance further. A multiway extension of the CCA, called MCCA, is first presented, in which collaborative CCAs are exploited to optimize the reference signals in correlation analysis for SSVEP recognition alternatingly from the channel-way and trial-way arrays of constructed EEG tensor. L1-regularization is subsequently imposed on the trialway array optimization in the MCCA, and hence results in the more powerful L1-MCCA with function of effective trial selection.
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013
Yu Zhang, Guoxu Zhou, Jing Jin, Xingyu Wang, Andrzej Cichocki
This study introduces an L1-regularized multiway canonical correlation analysis (L1-MCCA) for reference signal optimization to improve the SSVEP recognition performance further. A multiway extension of the CCA, called MCCA, is first presented, in which collaborative CCAs are exploited to optimize the reference signals in correlation analysis for SSVEP recognition alternatingly from the channel-way and trial-way arrays of constructed EEG tensor. L1-regularization is subsequently imposed on the trialway array optimization in the MCCA, and hence results in the more powerful L1-MCCA with function of effective trial selection.
L1-MCCA model
L1-MCCA for SSVEP recognition
|
Classification coefficient comparision
Learning results of reference signals
|
Spatial-Temporal Discriminant Analysis for ERP-based Brain-Computer Interface
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013
Yu Zhang, Guoxu Zhou, Qibin Zhao, Jing Jin, Xingyu Wang, Andrzej Cichocki
This study introduces a spatial-temporal discriminant analysis (STDA) to ERP classification. As a multiway extension of the LDA, the STDA method tries tomaximize the discriminant information between target and nontarget classes through finding two projection matrices from spatial and temporal dimensions collaboratively, which reduces effectively the feature dimensionality in the discriminant analysis, and hence decreases significantly the number of required training samples. The proposed STDA method was validated with dataset II of the BCI Competition III and dataset recorded from our own experiments, and compared to the state-of-the-art algorithms for ERP classification. The superior classification performance in using few training samples shows that the STDA is effective to reduce the system calibration time and improve the classification accuracy, thereby enhancing the practicability of ERP-based BCI.
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013
Yu Zhang, Guoxu Zhou, Qibin Zhao, Jing Jin, Xingyu Wang, Andrzej Cichocki
This study introduces a spatial-temporal discriminant analysis (STDA) to ERP classification. As a multiway extension of the LDA, the STDA method tries tomaximize the discriminant information between target and nontarget classes through finding two projection matrices from spatial and temporal dimensions collaboratively, which reduces effectively the feature dimensionality in the discriminant analysis, and hence decreases significantly the number of required training samples. The proposed STDA method was validated with dataset II of the BCI Competition III and dataset recorded from our own experiments, and compared to the state-of-the-art algorithms for ERP classification. The superior classification performance in using few training samples shows that the STDA is effective to reduce the system calibration time and improve the classification accuracy, thereby enhancing the practicability of ERP-based BCI.
Spatial-temporal discriminant analysis model
|
Feature distribution
|
A Novel BCI Based on ERP Sensitive to Configural Processing of Human Faces
Journal of Neural Engineering, 2012
Yu Zhang, Qibin Zhao, Jing Jin, Xingyu Wang, Andrzej Cichocki
This study introduces a novel brain–computer interface (BCI) based on an oddball paradigm using stimuli of facial images with loss of configural face information (e.g., inversion of face). Our experiments confirm that the face-sensitive event-related potential (ERP) components N170 and vertex positive potential (VPP) have reflected early structural encoding of faces and can be modulated by the configural processing of faces. With the proposed novel paradigm, we investigate the effects of ERP components N170, VPP and P300 on target detection for BCI. An eight-class BCI platform is developed to analyze ERPs and evaluate the target detection performance. The online classification accuracy of 88.7% and information transfer rate of 38.7 bits/min with only single trial suggest that the proposed paradigm is very promising for visual stimuli-driven BCI applications.
Journal of Neural Engineering, 2012
Yu Zhang, Qibin Zhao, Jing Jin, Xingyu Wang, Andrzej Cichocki
This study introduces a novel brain–computer interface (BCI) based on an oddball paradigm using stimuli of facial images with loss of configural face information (e.g., inversion of face). Our experiments confirm that the face-sensitive event-related potential (ERP) components N170 and vertex positive potential (VPP) have reflected early structural encoding of faces and can be modulated by the configural processing of faces. With the proposed novel paradigm, we investigate the effects of ERP components N170, VPP and P300 on target detection for BCI. An eight-class BCI platform is developed to analyze ERPs and evaluate the target detection performance. The online classification accuracy of 88.7% and information transfer rate of 38.7 bits/min with only single trial suggest that the proposed paradigm is very promising for visual stimuli-driven BCI applications.
Grand average ERP waveforms
|
Scalp topographies of the grand averaged ERPs
|
