RESUMO
In this paper, a novel spatio-temporal self-constructing graph neural network (ST-SCGNN) is proposed for cross-subject emotion recognition and consciousness detection. For spatio-temporal feature generation, activation and connection pattern features are first extracted and then combined to leverage their complementary emotion-related information. Next, a self-constructing graph neural network with a spatio-temporal model is presented. Specifically, the graph structure of the neural network is dynamically updated by the self-constructing module of the input signal. Experiments based on the SEED and SEED-IV datasets showed that the model achieved average accuracies of 85.90% and 76.37%, respectively. Both values exceed the state-of-the-art metrics with the same protocol. In clinical besides, patients with disorders of consciousness (DOC) suffer severe brain injuries, and sufficient training data for EEG-based emotion recognition cannot be collected. Our proposed ST-SCGNN method for cross-subject emotion recognition was first attempted in training in ten healthy subjects and testing in eight patients with DOC. We found that two patients obtained accuracies significantly higher than chance level and showed similar neural patterns with healthy subjects. Covert consciousness and emotion-related abilities were thus demonstrated in these two patients. Our proposed ST-SCGNN for cross-subject emotion recognition could be a promising tool for consciousness detection in DOC patients.
Assuntos
Estado de Consciência , Emoções , Humanos , Benchmarking , Redes Neurais de Computação , EletroencefalografiaRESUMO
Electroencephalography (EEG) is a commonly used technology for monitoring brain activities and diagnosing sleep disorders. Clinically, doctors need to manually stage sleep based on EEG signals, which is a time-consuming and laborious task. In this study, we propose a few-shot EEG sleep staging termed transductive prototype optimization network (TPON) method, which aims to improve the performance of EEG sleep staging. Compared with traditional deep learning methods, TPON uses a meta-learning algorithm, which generalizes the classifier to new classes that are not visible in the training set, and only have a few examples for each new class. We learn the prototypes of existing objects through meta-training, and capture the sleep features of new objects through the "learn to learn" method of meta-learning. The prototype distribution of the class is optimized and captured by using support set and unlabeled high confidence samples to increase the authenticity of the prototype. Compared with traditional prototype networks, TPON can effectively solve too few samples in few-shot learning and improve the matching degree of prototypes in prototype network. The experimental results on the public SleepEDF-2013 dataset show that the proposed algorithm outperform than most advanced algorithms in the overall performance. In addition, we experimentally demonstrate the feasibility of cross-channel recognition, which indicates that there are many similar sleep EEG features between different channels. In future research, we can further explore the common features among different channels and investigate the combination of universal features in sleep EEG. Overall, our method achieves high accuracy in sleep stage classification, demonstrating the effectiveness of this approach and its potential applications in other medical fields.
RESUMO
Background: Brain computer interface (BCI) technology may provide a new way of communication for some patients with disorder of consciousness (DOC), which can directly connect the brain and external devices. However, the DOC patients' EEG differ significantly from that of the normal person and are difficult to collected, the decoding algorithm currently only is trained based on a small amount of the patient's own data and performs poorly. Methods: In this study, a decoding algorithm called WD-ADSTCN based on domain adaptation is proposed to improve the DOC patients' P300 signal detection. We used the Wasserstein distance to filter the normal population data to increase the training data. Furthermore, an adversarial approach is adopted to resolve the differences between the normal and patient data. Results: The results showed that in the cross-subject P300 detection of DOC patients, 7 of 11 patients achieved an average accuracy of over 70%. Furthermore, their clinical diagnosis changed and CRS-R scores improved three months after the experiment. Conclusion: These results demonstrated that the proposed method could be employed in the P300 BCI system for the DOC patients, which has important implications for the clinical diagnosis and prognosis of these patients.
RESUMO
Electroencephalogram (EEG) is a crucial and widely utilized technique in neuroscience research. In this paper, we introduce a novel graph neural network called the spatial-temporal graph attention network with a transformer encoder (STGATE) to learn graph representations of emotion EEG signals and improve emotion recognition performance. In STGATE, a transformer-encoder is applied for capturing time-frequency features which are fed into a spatial-temporal graph attention for emotion classification. Using a dynamic adjacency matrix, the proposed STGATE adaptively learns intrinsic connections between different EEG channels. To evaluate the cross-subject emotion recognition performance, leave-one-subject-out experiments are carried out on three public emotion recognition datasets, i.e., SEED, SEED-IV, and DREAMER. The proposed STGATE model achieved a state-of-the-art EEG-based emotion recognition performance accuracy of 90.37% in SEED, 76.43% in SEED-IV, and 76.35% in DREAMER dataset, respectively. The experiments demonstrated the effectiveness of the proposed STGATE model for cross-subject EEG emotion recognition and its potential for graph-based neuroscience research.
RESUMO
The brain-computer interface (BCI) provides a direct communication pathway between the human brain and external devices. However, the models trained for existing subjects perform poorly on new subjects, which is termed the subject calibration problem. In this paper, we propose a semi-supervised meta learning (SSML) method for subject-transfer calibration. The proposed SSML learns a model-agnostic meta learner with existing subjects and then fine-tunes the meta learner in a semi-supervised learning manner, i.e. using a few labelled samples and many unlabelled samples of the target subject for calibration. It is significant for BCI applications in which labelled data are scarce or expensive while unlabelled data are readily available. Three different BCI paradigms are tested: event-related potential detection, emotion recognition and sleep staging. The SSML achieved classification accuracies of 0.95, 0.89 and 0.83 in the benchmark datasets of three paradigms. The runtime complexity of SSML grows linearly as the number of samples of target subject increases so that is possible to apply it in real-time systems. This study is the first attempt to apply semi-supervised model-agnostic meta learning methodology for subject calibration. The experimental results demonstrated the effectiveness and potential of the SSML method for subject-transfer BCI applications.
Assuntos
Interfaces Cérebro-Computador , Humanos , Eletroencefalografia/métodos , Potenciais Evocados , Aprendizado de Máquina Supervisionado , Encéfalo , AlgoritmosRESUMO
For patients with disorders of consciousness, such as unresponsive wakefulness syndrome (UWS) patients and minimally conscious state (MCS) patients, their long treatment cycle and high cost commonly put a heavy burden on the patient's family and society. Therefore, it is vital to accurately diagnose and predict consciousness recovery for such patients. In this paper, we explored the role of the P300 signal based on an audiovisual BCI in the classification and prognosis prediction of patients with disorders of consciousness. This experiment included 18 patients: 10 UWS patients and 8 MCS- patients. At the three-month follow-up, we defined patients with an improved prognosis (from UWS to MCS-, from UWS to MCS+, or from MCS- to MCS+) as "improved patients" and those who stayed in UWS/MCS as "not improved patients". First, we compared and analyzed different types of patients, and the results showed that the P300 detection accuracy rate of "improved" patients was significantly higher than that of "not improved" patients. Furthermore, the P300 detection accuracy of traumatic brain injury (TBI) patients was significantly higher than that of non-traumatic brain injury (NTBI, including acquired brain injury and cerebrovascular disease) patients. We also found that there was a positive linear correlation between P300 detection accuracy and CRS-R score, and patients with higher P300 detection accuracy were likely to achieve higher CRS-R scores. In addition, we found that the patients with higher P300 detection accuracies tend to have better prognosis in this audiovisual BCI. These findings indicate that the detection accuracy of P300 is significantly correlated with the level of consciousness, etiology, and prognosis of patients. P300 can be used to represent the preservation level of consciousness in clinical neurophysiology and predict the possibility of recovery in patients with disorders of consciousness.
RESUMO
In recent years, neuroimaging studies have remarkably demonstrated the presence of cognitive motor dissociation in patients with disorders of consciousness (DoC). These findings accelerated the development of brain-computer interfaces (BCIs) as clinical tools for behaviorally unresponsive patients. This article reviews the recent progress of BCIs in patients with DoC and discusses the open challenges. In view of the practical application of BCIs in patients with DoC, four aspects of the relevant literature are introduced: consciousness detection, auxiliary diagnosis, prognosis, and rehabilitation. For each aspect, the paradigm design, brain signal processing methods, and experimental results of representative BCI systems are analyzed. Furthermore, this article provides guidance for BCI design for patients with DoC and discusses practical challenges for future research.
Assuntos
Interfaces Cérebro-Computador , Estado de Consciência , Transtornos da Consciência/diagnóstico , Eletroencefalografia , Humanos , PrognósticoRESUMO
Recently, many studies have investigated the role of gene-signature on the prognostic assessment of breast cancer (BC), however, the tumor heterogeneity and sequencing noise have limited the clinical usage of these models. Pathway-based approaches are more stable to the perturbation of certain gene expression. In this study, we constructed a prognostic classifier based on survival-related pathway crosstalk analysis. We estimated pathway's deregulation scores (PDSs) for samples collected from public databases to select survival-related pathways. After pathway crosstalk analysis, we conducted K-means clustering analysis to cluster the patients into G1 and G2 subgroups. The survival outcome of the G2 subgroup was significantly worse than the G1 subgroup. Internal and external dataset exhibits high consistency with the training dataset. Significant differences were found between G2 and G1 subgroups on pathway activity, gene mutation, immune cell infiltration levels, and in particular immune cells/pathway's activities were significantly negatively associated with BC patient's outcomes. In conclusion, we established a novel classifier reflecting the overall survival risk of BC and successfully validated its clinical usage on multiple BC datasets, which could offer clinicians inspiration in formulating the clinical treatment plan.
RESUMO
The poor performance of single-gene lists for prognostic predictions in independent cohorts has limited their clinical use. Here, we employed a pathway-based approach using embedded biological features to identify reproducible prognostic markers as an alternative. We used pathway activity score, sure independence screening, and K-means clustering analyses to identify and cluster colorectal cancer patients into two distinct subgroups, G2 (aggressive) and G1 (moderate). The differences between these two groups with respect to survival, somatic mutation, pathway activity, and tumor-infiltration by immunocytes were compared. These comparisons revealed that the survival rates in the G2 subgroup were significantly reduced compared to that in the G1 subgroup; further, the mutational burden rates in several oncogenes, including KRAS, DCLK1, and EPHA5, were significantly higher in the G2 subgroup than in the G1 subgroup. The enhanced activity of the critical pathways such as MYC and epithelial-mesenchymal transition may also lead to the progression of colorectal cancer. Taken together, we established a novel prognostic classification system that offers meritorious insights into the hallmarks of colorectal cancer.
RESUMO
Autism spectrum disorder (ASD) is a specific brain disease that causes communication impairments and restricted interests. Functional connectivity analysis methodology is widely used in neuroscience research and shows much potential in discriminating ASD patients from healthy controls. However, due to heterogeneity of ASD patients, the performance of conventional functional connectivity classification methods is relatively poor. Graph neural network is an effective graph representation method to model structured data like functional connectivity. In this paper, we proposed a functional graph discriminative network (FGDN) for ASD classification. On the basis of pre-built graph templates, the proposed FGDN is able to effectively distinguish ASD patient from health controls. Moreover, we studied the size of training set for effective training, inter-site predictions, and discriminative brain regions. Discriminative brain regions were determined by the proposed model to investigate its applicability and biomarkers for ASD identification. For functional connectivity classification and analysis, FGDN is not only an effective tool for ASD identification but also a potential technique in neuroscience research.
RESUMO
PURPOSE: Serum carcinoembryonic antigen (SCEA) level is often measured in patients with CRC but suffers from poor sensitivity and specificity as a diagnostic biomarker. CEA is more abundant in stool than in serum, but it has not been widely studied. This study aimed to elucidate the efficacy of fecal CEA (FCEA) as a potential non-invasive biomarker for early diagnosis of CRC. MATERIALS AND METHODS: We retrospectively analyzed the determination of FCEA and SCEA levels by electrochemiluminescence. We evaluated the diagnostic accuracy of FCEA and SCEA levels in early-stage CRC patients and healthy controls using ROC curve. RESULTS: A total of 298 people were included: 115 patients with CRC, 35 patients with adenomatous polyp (APC), 46 patients with non-gastrointestinal cancer (NGC), and 102 healthy controls (HC). The FCEA concentrations in CRC and APC patients were significantly higher than that of NGC and HC, and this is different from SCEA expression in APC and NGC. As a diagnostic biomarker of CRC, FCEA had significantly larger AUC compared with SCEA (.802 vs .735, P < .001). For identifying early-stage colorectal cancer, FCEA showed better diagnostic efficacy (AUC: .831) than SCEA (AUC: .750), and the combination of the 2 biomarkers was even higher (AUC: .896). The sensitivity of FCEA was higher than that of SCEA (78.7% vs 29.8%). When SCEA was negative, 80.3% of CRC and 54.6% of APC cases could be identified by FCEA. CONCLUSION: Compared with SCEA, FCEA has more advantages in the diagnosis of the early stage of colorectal cancer and adenomatous polyps.
Assuntos
Antígeno Carcinoembrionário/análise , Neoplasias Colorretais/diagnóstico , Neoplasias Colorretais/imunologia , Fezes/citologia , Adulto , Idoso , Biomarcadores Tumorais , Antígeno Carcinoembrionário/sangue , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estadiamento de Neoplasias , Curva ROC , Estudos Retrospectivos , Sensibilidade e EspecificidadeRESUMO
The volume expansion during Li ion insertion/extraction remains an obstacle for the application of Sn-based anode in lithium ion-batteries. Herein, the nanoporous (np) Cu6Sn5 alloy and Cu6Sn5/Sn composite were applied as a lithium-ion battery anode. The as-dealloyed np-Cu6Sn5 has an ultrafine ligament size of 40 nm and a high BET-specific area of 15.9 m2 g-1. The anode shows an initial discharge capacity as high as 1200 mA h g-1, and it remains a capacity of higher than 600 mA h g-1 for the initial five cycles at 0.1 A g-1. After 100 cycles, the anode maintains a stable capacity higher than 200 mA h g-1 for at least 350 cycles, with outstanding Coulombic efficiency. The ex situ XRD patterns reveal the reverse phase transformation between Cu6Sn5 and Li2CuSn. The Cu6Sn5/Sn composite presents a similar cycling performance with a slightly inferior rate performance compared to np-Cu6Sn5. The study demonstrates that dealloyed nanoporous Cu6Sn5 alloy could be a promising candidate for lithium-ion batteries.
RESUMO
As a physiological process and high-level cognitive behavior, emotion is an important subarea in neuroscience research. Emotion recognition across subjects based on brain signals has attracted much attention. Due to individual differences across subjects and the low signal-to-noise ratio of EEG signals, the performance of conventional emotion recognition methods is relatively poor. In this paper, we propose a self-organized graph neural network (SOGNN) for cross-subject EEG emotion recognition. Unlike the previous studies based on pre-constructed and fixed graph structure, the graph structure of SOGNN are dynamically constructed by self-organized module for each signal. To evaluate the cross-subject EEG emotion recognition performance of our model, leave-one-subject-out experiments are conducted on two public emotion recognition datasets, SEED and SEED-IV. The SOGNN is able to achieve state-of-the-art emotion recognition performance. Moreover, we investigated the performance variances of the models with different graph construction techniques or features in different frequency bands. Furthermore, we visualized the graph structure learned by the proposed model and found that part of the structure coincided with previous neuroscience research. The experiments demonstrated the effectiveness of the proposed model for cross-subject EEG emotion recognition.
RESUMO
In addition to helping develop products that aid the disabled, brain-computer interface (BCI) technology can also become a modality of entertainment for all people. However, most BCI games cannot be widely promoted due to the poor control performance or because they easily cause fatigue. In this paper, we propose a P300 brain-computer-interface game (MindGomoku) to explore a feasible and natural way to play games by using electroencephalogram (EEG) signals in a practical environment. The novelty of this research is reflected in integrating the characteristics of game rules and the BCI system when designing BCI games and paradigms. Moreover, a simplified Bayesian convolutional neural network (SBCNN) algorithm is introduced to achieve high accuracy on limited training samples. To prove the reliability of the proposed algorithm and system control, 10 subjects were selected to participate in two online control experiments. The experimental results showed that all subjects successfully completed the game control with an average accuracy of 90.7% and played the MindGomoku an average of more than 11 min. These findings fully demonstrate the stability and effectiveness of the proposed system. This BCI system not only provides a form of entertainment for users, particularly the disabled, but also provides more possibilities for games.
Assuntos
Interfaces Cérebro-Computador , Aprendizado Profundo , Teorema de Bayes , Eletroencefalografia , Humanos , Reprodutibilidade dos TestesRESUMO
With the continuous development of portable noninvasive human sensor technologies such as brain-computer interfaces (BCI), multimodal emotion recognition has attracted increasing attention in the area of affective computing. This paper primarily discusses the progress of research into multimodal emotion recognition based on BCI and reviews three types of multimodal affective BCI (aBCI): aBCI based on a combination of behavior and brain signals, aBCI based on various hybrid neurophysiology modalities and aBCI based on heterogeneous sensory stimuli. For each type of aBCI, we further review several representative multimodal aBCI systems, including their design principles, paradigms, algorithms, experimental results and corresponding advantages. Finally, we identify several important issues and research directions for multimodal emotion recognition based on BCI.
RESUMO
Segmentation of cardiac ventricle from magnetic resonance images is significant for cardiac disease diagnosis, progression assessment, and monitoring cardiac conditions. Manual segmentation is so time consuming, tedious, and subjective that automated segmentation methods are highly desired in practice. However, conventional segmentation methods performed poorly in cardiac ventricle, especially in the right ventricle. Compared with the left ventricle, whose shape is a simple thick-walled circle, the structure of the right ventricle is more complex due to ambiguous boundary, irregular cavity, and variable crescent shape. Hence, effective feature extractors and segmentation models are preferred. In this paper, we propose a dilated-inception net (DIN) to extract and aggregate multi-scale features for right ventricle segmentation. The DIN outperforms many state-of-the-art models on the benchmark database of right ventricle segmentation challenge. In addition, the experimental results indicate that the proposed model has potential to reach expert-level performance in right ventricular epicardium segmentation. More importantly, DIN behaves similarly to clinical expert with high correlation coefficients in four clinical cardiac indices. Therefore, the proposed DIN is promising for automated cardiac right ventricle segmentation in clinical applications.
Assuntos
Técnicas de Imagem Cardíaca/métodos , Ventrículos do Coração/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Adulto , Idoso , Algoritmos , Aprendizado Profundo , Feminino , Humanos , Masculino , Pessoa de Meia-IdadeRESUMO
The fog radio access network (F-RAN) equipped with enhanced remote radio heads (eRRHs), which can pre-store some requested files in the edge cache and support mobile edge computing (MEC). To guarantee the quality-of-service (QoS) and energy efficiency of F-RAN, a proper content caching strategy is necessary to avoid coarse content storing locally in the cache or frequent fetching from a centralized baseband signal processing unit (BBU) pool via backhauls. In this paper we investigate the relationships among eRRH/terminal activities and content requesting in F-RANs, and propose an edge content caching strategy for eRRHs by mining out mobile network behavior information. Especially, to attain the inference for appropriate content caching, we establish a pre-mapping containing content preference information and geographical influence by an efficient non-uniformed accelerated matrix completion algorithm. The energy consumption analysis is given in order to discuss the energy saving properties of the proposed edge content caching strategy. Simulation results demonstrate our theoretical analysis on the inference validity of the pre-mapping construction method in static and dynamic cases, and show the energy efficiency achieved by the proposed edge content pre-caching strategy.
RESUMO
Detecting event-related potential (ERP) is a challenging problem because of its low signal-to-noise ratio and complex spatial-temporal features. Conventional detection methods usually rely on the ensemble averaging technique, which may eliminate subtle but important information in ERP signals and lead to poor detection performance. Inspired by the good performance of discriminative restricted Boltzmann machine (DRBM) in feature extraction and classification, we propose a spatial-temporal DRBM (ST-DRBM) to extract spatial and temporal features for ERP detection. The experimental results and statistical analyses demonstrate that the proposed method is able to achieve state-of-the-art ERP detection performance. The ST-DRBM is not only an effective ERP detector, but also a practical tool for ERP analysis. Based on the proposed model, similar scalp distribution and temporal variations were found in the ERP signals of different sessions, which indicated the feasibility of cross-session ERP detection. Given its state-of-the-art performance and effective analytical technique, ST-DRBM is promising for ERP-based brain-computer interfaces and neuroscience research.
Assuntos
Algoritmos , Eletroencefalografia/instrumentação , Potenciais Evocados/fisiologia , Adulto , Mapeamento Encefálico , Interfaces Cérebro-Computador , Auxiliares de Comunicação para Pessoas com Deficiência , Potenciais Evocados P300/fisiologia , Feminino , Humanos , Masculino , Modelos Neurológicos , Processamento de Sinais Assistido por Computador , Razão Sinal-Ruído , Percepção Espacial/fisiologia , Percepção do Tempo/fisiologia , Adulto JovemRESUMO
Detecting and Please provide the correct one analyzing the event-related potential (ERP) remains an important problem in neuroscience. Due to the low signal-to-noise ratio and complex spatio-temporal patterns of ERP signals, conventional methods usually rely on ensemble averaging technique for reliable detection, which may obliterate subtle but important information in each trial of ERP signals. Inspired by deep learning methods, we propose a novel hybrid network termed ERP-NET. With hybrid deep structure, the proposed network is able to learn complex spatial and temporal patterns from single-trial ERP signals. To verify the effectiveness of ERP-NET, we carried out a few ERP detection experiments that the proposed model achieved cutting-edge performance. The experimental results demonstrate that the patterns learned by the ERP-NET are discriminative ERP components in which the ERP signals are properly characterized. More importantly, as an effective approach to single-trial analysis, ERP-NET is able to discover new ERP patterns which are significant to neuroscience study as well as BCI applications. Therefore, the proposed ERP-NET is a promising tool for the research on ERP signals.
Assuntos
Eletroencefalografia/métodos , Potenciais Evocados/fisiologia , Redes Neurais de Computação , Algoritmos , Interfaces Cérebro-Computador , Eletroencefalografia/instrumentação , Potenciais Evocados P300/fisiologia , Humanos , Desenho de Prótese , Processamento de Sinais Assistido por Computador , Razão Sinal-RuídoRESUMO
Porcine circovirus (PCV) is grouped into two types: PCV1 and PCV2. PCV1 is isolated from cultured cells and usually causes no clinical diseases in pigs. PCV2 is a pathogen of severe pig disease and a great threat to swine health and production. In our study, to investigate the codon usage bias of PCV, the genomic sequences of PCV1 and PCV2 were analyzed. The results showed that the codon usage bias of PCV was very low. An effective number of codons (ENC) plot analysis indicated that mutational pressure influences the codon usage bias of PCV. Neutrality plot analysis showed that mutation bias dominated over natural selection in shaping the codon usage bias of PCV1, but mutation bias and natural selection contributed equally to the codon usage bias of PCV2. Principal component analysis showed that different ORFs and dinucleotide patterns were also factors influencing the codon usage bias of PCV. Our study is helpful in understanding the codon usage pattern of PCV and the evolution of PCV.