Objective: Electroencephalogram (EEG) based brain–computer interfaces (BCI) in motor imagery (MI) have developed rapidly in recent years. A reliable feature extraction method is essential because of a low signal-to-noise ratio (SNR) and time-dependent covariates of EEG signals. Because of efficient application in various fields, deep learning has been adopted in EEG signal processing and has obtained competitive results compared with the traditional methods. However, designing and training an end-to-end network to fully extract potential features from EEG signals remains a challenge in MI. Approach: In this study, we propose a parallel multiscale filter bank convolutional neural network (MSFBCNN) for MI classification. We introduce a layered end-to-end network structure, in which a feature-extraction network is used to extract temporal and spatial features. To enhance the transfer learning ability, we propose a network initialization and fine-tuning strategy to train an individual model for inter-subject classification on small datasets. We compare our MSFBCNN with the state-of-the-art approaches on open datasets. Results: The proposed method has a higher accuracy than the baselines in intra-subject classification. In addition, the transfer learning experiments indicate that our network can build an individual model and obtain acceptable results in inter-subject classification. The results suggest that the proposed network has superior performance, robustness, and transfer learning ability.

Visual cognition such as face recognition requires a high level of functional interaction between distributed regions of a network. It has been reported that the fusiform gyrus (FG) is an important brain area involved in facial cognition; altered connectivity of FG to some other regions may lead to a deficit in visual cognition especially face recognition. However, whether functional connectivity between the FG and other brain regions changes remains unclear during the resting state in amnestic mild cognitive impairment (aMCI) subjects. Here, we employed a resting state functional MRI (fMRI) to examine changes in functional connectivity of left/right FG comparing aMCI patients with age-matched control subjects. Forty-eight aMCI and thirty-eight control subjects from the Alzheimer’s disease Neuroimaging Initiative (ADNI) were analyzed. We focused on the correlation between low frequency fMRI signal fluctuations in the FG and those in all other brain regions. Compared to the control group, we found some discrepant regions in the aMCI group which presented increased or decreased connectivity with the left/right FG including the left precuneus, left lingual gyrus, right thalamus, supramarginal gyrus, left supplementary motor area, left inferior temporal gyrus, and left parahippocampus. More importantly, we also obtained that both left and right FG have increased functional connections with the left middle occipital gyrus (MOG) and right anterior cingulate gyrus (ACC) in aMCI patients. That was not a coincidence and might imply that the MOG and ACC also play a critical role in visual cognition, especially face recognition. These findings in a large part supported our hypothesis and provided a new insight in understanding the important subtype of MCI.

It is well established that expertise modulates evoked brain activity in response to specific stimuli. Recently, researchers have begun to investigate how expertise influences the resting brain. Among these studies, most focused on the connectivity features within/across regions, i.e., connectivity patterns/strength. However, little concern has been given to a more fundamental issue whether or not expertise modulates baseline brain activity. We investigated this question using amplitude of low-frequency (<0.08 Hz) fluctuation (ALFF) as the metric of brain activity and a novel expertise model, i.e., acupuncturists, due to their robust proficiency in tactile perception and emotion regulation. After the psychophysical and behavioral expertise screening procedure, 23 acupuncturists and 23 matched non-acupuncturists (NA) were enrolled. Our results explicated higher ALFF for acupuncturists in the left ventral medial prefrontal cortex (VMPFC) and the contralateral hand representation of the primary somatosensory area (SI) (corrected for multiple comparisons). Additionally, ALFF of VMPFC was negatively correlated with the outcomes of the emotion regulation task (corrected for multiple comparisons). We suggest that our study may reveal a novel connection between the neuroplasticity mechanism and resting state activity, which would upgrade our understanding of the central mechanism of learning. Furthermore, by showing that expertise can affect the baseline brain activity as indicated by ALFF, our findings may have profound implication for functional neuroimaging studies especially those involving expert models, in that difference in baseline brain activity may either smear the spatial pattern of activations for task data or introduce biased results into connectivity-based analysis for resting data.

Most previous studies exploring the neural mechanism of psychogenic erectile dysfunction (pED) focused on brain activity under tasks. We suggest that the resting brain activity is equally important in pED studies, in that the patterns of spontaneous neural activities is independent of modalities of sensory input, therefore providing substantial information regarding the central mechanism of pED. Our previous study reported the altered baseline activity in right anterior insula (aINS) in pED patients. Also, the insula is a pivotal region in sexual behavior, which is suggested to be able to directly mediate erection. Therefore, the current study employed resting-state fMRI to examine alterations in functional connectivity of the aINS comparing pED patients with matched control subjects. After rigorous participant inclusion procedure, 27 pED patients and 27 healthy male controls were enrolled. Our results elucidated the disrupted homogeneity within the right aINS and aberrant connection patterns between the right aINS and the right dorsolateral prefrontal cortex (dlPFC), as well as the right aINS and the right temporoparietal junction (TPJ) respectively in pED group, as compared with the healthy controls. In conclusion, our results demonstrated the aberrant insula-centered functional connectivity in pED, which may be related to the abnormal representation of internal bodily state or needs in pED patients and thus further affect the inhibitory control in the sexual context. We hope that these findings may shed new light on the understanding of the central mechanism of pED.

Recent neuroimaging studies have elucidated many interesting and promising findings on sexuality regarding the neural underpinnings of both normal and abnormal sexual processes. Psychogenic erectile dysfunction (pED) consists of a major part of male sexual dysfunction in China, but the understanding of the central mechanism of pED is still in its infancy. It is commonly appreciated that pED is a functional disorder, which can be attributed predominantly or exclusively to psychological factors, such as anxiety, depression, loss of self-esteem, and psychosocial stresses. Most previous studies probed the central response in the brain of pED patients using sexual-related stimuli. However, little concern has been given to a more fundamental issue whether the baseline brain activity is altered in pED or not. With rs-fMRI data, the current study aimed to explain the central mechanism behind pED by investigating the alterations in baseline brain activity in patients with pED, as indexed by the amplitude of low-frequency (0.01–0.08 Hz) fluctuation (ALFF). After the psychological screening and urological examination procedure, 26 pED patients and 26 healthy matched controls were enrolled. Our results explicated significantly lower baseline brain activity in the right anterior insula and right orbitofrontal cortex for pED patients (multiple comparison corrected). Additionally, the voxel-wise correlation analysis showed that ALFF of the right anterior insula was correlated with the outcomes of erectile function (multiple comparison corrected). Our results implied there was impaired cognitive and motivational processing of sexual stimuli in pED patients. Our current findings may shed light on the neural pathology underlying pED. We hope that our study has provided a new angle looking into pED research by investigating resting state brain activity. Furthermore, we suggest that the current study may put forward a more subtle conception of insular influence on pED, which may help foster new specific, mechanistic insights.