Continuous tracking using deep learning-based decoding for noninvasive brain-computer interface.

Brain-computer interfaces (BCI) using electroencephalography provide a noninvasive method for users to interact with external devices without the need for muscle activation. While noninvasive BCIs have the potential to improve the quality of lives of healthy and motor-impaired individuals, they currently have limited applications due to inconsistent performance and low degrees of freedom. In this study, we use deep learning (DL)-based decoders for online continuous pursuit (CP), a complex BCI task requiring the user to track an object in 2D space. We developed a labeling system to use CP data for supervised learning, trained DL-based decoders based on two architectures, including a newly proposed adaptation of the PointNet architecture, and evaluated the performance over several online sessions. We rigorously evaluated the DL-based decoders in a total of 28 human participants, and found that the DL-based models improved throughout the sessions as more training data became available and significantly outperformed a traditional BCI decoder by the last session. We also performed additional experiments to test an implementation of transfer learning by pretraining models on data from other subjects, and midsession training to reduce intersession variability. The results from these experiments showed that pretraining did not significantly improve performance, but updating the models' midsession may have some benefit. Overall, these findings support the use of DL-based decoders for improving BCI performance in complex tasks like CP, which can expand the potential applications of BCI devices and help to improve the quality of lives of healthy and motor-impaired individuals.

Integrating Simultaneous Motor Imagery and Spatial Attention for EEG-BCI Control.

OBJECTIVE: EEG-based brain-computer interfaces (BCI) are non-invasive approaches for replacing or restoring motor functions in impaired patients, and direct brain-to-device communication in the general population. Motor imagery (MI) is one of the most used BCI paradigms, but its performance varies across individuals and certain users require substantial training to develop control. In this study, we propose to integrate a MI paradigm simultaneously with a recently proposed Overt Spatial Attention (OSA) paradigm, to accomplish BCI control. METHODS: We evaluated a cohort of 25 human subjects' ability to control a virtual cursor in one- and two-dimensions over 5 BCI sessions. The subjects used 5 different BCI paradigms: MI alone, OSA alone, MI, and OSA simultaneously towards the same target (MI+OSA), and MI for one axis while OSA controls the other (MI/OSA and OSA/MI). RESULTS: Our results show that MI+OSA reached the highest average online performance in 2D tasks at 49% Percent Valid Correct (PVC), and statistically outperforms both MI alone (42%) and OSA alone (45%). MI+OSA had a similar performance to each subject's best individual method between MI alone and OSA alone (50%) and 9 subjects reached their highest average BCI performance using MI+OSA. CONCLUSION: Integrating MI and OSA leads to improved performance over both individual methods at the group level and is the best BCI paradigm option for some subjects. SIGNIFICANCE: This work proposes a new BCI control paradigm that integrates two existing paradigms and demonstrates its value by showing that it can improve users' BCI performance.

Continuous Tracking using Deep Learning-based Decoding for Non-invasive Brain-Computer Interface.

Brain-computer interfaces (BCI) using electroencephalography (EEG) provide a non-invasive method for users to interact with external devices without the need for muscle activation. While noninvasive BCIs have the potential to improve the lives of both healthy and motor impaired individuals, they currently have limited applications due to inconsistent performance and low degrees of freedom. In this study, we use deep-learning (DL)-based decoders for online Continuous Pursuit (CP), a complex BCI task requiring the user to track an object in 2D space. We developed a new labelling system to use CP data for supervised learning, trained DL-based decoders based on two architectures, including a newly proposed adaptation of the PointNet architecture, and evaluated the performance over several online sessions. We rigorously evaluated the DL-based decoders in a total of 28 human subjects, and found that the DL-based models improved throughout the sessions as more training data became available and significantly outperformed a traditional BCI decoder by the last session. We also performed additional experiments to test an implementation of transfer learning by pre-training models on data from other subjects, and mid-session training to reduce inter-session variability. The results from these experiments show that pre-training did not significantly improve performance, but updating the models mid-session may have some benefit. Overall, these findings support the use of DL-based decoders for improving BCI performance in complex tasks like CP, which can expand the potential applications of BCI devices and help improve the lives of both healthy individuals and motor-impaired patients.

Integrating simultaneous motor imagery and spatial attention for EEG-BCI control.

OBJECTIVE: EEG-based brain-computer interfaces (BCI) are non-invasive approaches for replacing or restoring motor functions in impaired patients, and direct brain-to-device communication in the general population. Motor imagery (MI) is one of the most used BCI paradigms, but its performance varies across individuals and certain users require substantial training to develop control. In this study, we propose to integrate a MI paradigm simultaneously with a recently proposed Overt Spatial Attention (OSA) paradigm, to accomplish BCI control. METHODS: We evaluated a cohort of 25 human subjects' ability to control a virtual cursor in one- and two-dimensions over 5 BCI sessions. The subjects used 5 different BCI paradigms: MI alone, OSA alone, MI and OSA simultaneously towards the same target (MI+OSA), and MI for one axis while OSA controls the other (MI/OSA and OSA/MI). RESULTS: Our results show that MI+OSA reached the highest average online performance in 2D tasks at 49% Percent Valid Correct (PVC), statistically outperforms MI alone (42%), and was higher, but not statistically significant, than OSA alone (45%). MI+OSA had a similar performance to each subject's best individual method between MI alone and OSA alone (50%) and 9 subjects reached their highest average BCI performance using MI+OSA. CONCLUSION: Integrating MI and OSA leads to improved performance over MI alone at the group level and is the best BCI paradigm option for some subjects. SIGNIFICANCE: This work proposes a new BCI control paradigm that integrates two existing paradigms and demonstrates its value by showing that it can improve users' BCI performance.

Variability of the Surface Area of the V1, V2, and V3 Maps in a Large Sample of Human Observers.

How variable is the functionally defined structure of early visual areas in human cortex and how much variability is shared between twins? Here we quantify individual differences in the best understood functionally defined regions of cortex: V1, V2, V3. The Human Connectome Project 7T Retinotopy Dataset includes retinotopic measurements from 181 subjects (109 female, 72 male), including many twins. We trained four "anatomists" to manually define V1-V3 using retinotopic features. These definitions were more accurate than automated anatomical templates and showed that surface areas for these maps varied more than threefold across individuals. This threefold variation was little changed when normalizing visual area size by the surface area of the entire cerebral cortex. In addition to varying in size, we find that visual areas vary in how they sample the visual field. Specifically, the cortical magnification function differed substantially among individuals, with the relative amount of cortex devoted to central vision varying by more than a factor of 2. To complement the variability analysis, we examined the similarity of visual area size and structure across twins. Whereas the twin sample sizes are too small to make precise heritability estimates (50 monozygotic pairs, 34 dizygotic pairs), they nonetheless reveal high correlations, consistent with strong effects of the combination of shared genes and environment on visual area size. Collectively, these results provide the most comprehensive account of individual variability in visual area structure to date, and provide a robust population benchmark against which new individuals and developmental and clinical populations can be compared.SIGNIFICANCE STATEMENT Areas V1, V2, and V3 are among the best studied functionally defined regions in human cortex. Using the largest retinotopy dataset to date, we characterized the variability of these regions across individuals and the similarity between twin pairs. We find that the size of visual areas varies dramatically (up to 3.5×) across healthy young adults, far more than the variability of the cerebral cortex size as a whole. Much of this variability appears to arise from inherited factors, as we find very high correlations in visual area size between monozygotic twin pairs, and lower but still substantial correlations between dizygotic twin pairs. These results provide the most comprehensive assessment of how functionally defined visual cortex varies across the population to date.

On the Deep Learning Models for EEG-Based Brain-Computer Interface Using Motor Imagery.

Motor imagery (MI) based brain-computer interface (BCI) is an important BCI paradigm which requires powerful classifiers. Recent development of deep learning technology has prompted considerable interest in using deep learning for classification and resulted in multiple models. Finding the best performing models among them would be beneficial for designing better BCI systems and classifiers going forward. However, it is difficult to directly compare performance of various models through the original publications, since the datasets used to test the models are different from each other, too small, or even not publicly available. In this work, we selected five MI-EEG deep classification models proposed recently: EEGNet, Shallow & Deep ConvNet, MB3D and ParaAtt, and tested them on two large, publicly available, databases with 42 and 62 human subjects. Our results show that the models performed similarly on one dataset while EEGNet performed the best on the second with a relatively small training cost using the parameters that we evaluated.

Immediate effects of short-term meditation on sensorimotor rhythm-based brain-computer interface performance.

Introduction: Meditation has been shown to enhance a user's ability to control a sensorimotor rhythm (SMR)-based brain-computer interface (BCI). For example, prior work have demonstrated that long-term meditation practices and an 8-week mindfulness-based stress reduction (MBSR) training have positive behavioral and neurophysiological effects on SMR-based BCI. However, the effects of short-term meditation practice on SMR-based BCI control are still unknown. Methods: In this study, we investigated the immediate effects of a short, 20-minute meditation on SMR-based BCI control. Thirty-seven subjects performed several runs of one-dimensional cursor control tasks before and after two types of 20-minute interventions: a guided mindfulness meditation exercise and a recording of a narrator reading a journal article. Results: We found that there is no significant change in BCI performance and Electroencephalography (EEG) BCI control signal following either 20-minute intervention. Moreover, the change in BCI performance between the meditation group and the control group was found to be not significant. Discussion: The present results suggest that a longer period of meditation is needed to improve SMR-based BCI control.

A novel mouse model for the study of endogenous neural stem and progenitor cells after traumatic brain injury.

Traumatic brain injury (TBI) is a leading cause of death and disability in the US. Neural stem/progenitor cells (NSPCs) persist in the adult brain and represent a potential cell source for tissue regeneration and wound healing after injury. The Notch signaling pathway is critical for embryonic development and adult brain injury response. However, the specific role of Notch signaling in the injured brain is not well characterized. Our previous study has established a Notch1CR2-GFP reporter mouse line in which the Notch1CR2 enhancer directs GFP expression in NSPCs and their progeny. In this study, we performed closed head injury (CHI) in the Notch1CR2-GFP mice to study the response of injury-activated NSPCs. We show that CHI induces neuroinflammation, cell death, and the expression of typical TBI markers (e.g., ApoE, Il1b, and Tau), validating the animal model. In addition, CHI induces cell proliferation in GFP+ cells expressing NSPC markers, e.g., Notch1 and Nestin. A significant higher percentage of GFP+ astrocytes and GABAergic neurons was observed in the injured brain, with no significant change in oligodendrocyte lineage between the CHI and sham animal groups. Since injury is known to activate astrogliosis, our results suggest that injury-induced GFP+ NSPCs preferentially differentiate into GABAergic neurons. Our study establishes that Notch1CR2-GFP transgenic mouse is a useful tool for the study of NSPC behavior in vivo after TBI. Unveiling the potential of NSPCs response to TBI (e.g., proliferation and differentiation) will identify new therapeutic strategy for the treatment of brain trauma.