RESUMO
Early diagnosis of mild cognitive impairment (MCI) fascinates screening high-risk Alzheimer's disease (AD). White matter is found to degenerate earlier than gray matter and functional connectivity during MCI. Although studies reveal white matter degenerates in the limbic system for MCI, how other white matter degenerates during MCI remains unclear. In our method, regions of interest with a high level of resting-state functional connectivity with hippocampus were selected as seeds to track fibers based on diffusion tensor imaging (DTI). In this way, hippocampus-temporal and thalamus-related fibers were selected, and each fiber's DTI parameters were extracted. Then, statistical analysis, machine learning classification, and Pearson's correlations with behavior scores were performed between MCI and normal control (NC) groups. Results show that: 1) the mean diffusivity of hippocampus-temporal and thalamus-related fibers are significantly higher in MCI and could be used to classify 2 groups effectively. 2) Compared with normal fibers, the degenerated fibers detected by the DTI indexes, especially for hippocampus-temporal fibers, have shown significantly higher correlations with cognitive scores. 3) Compared with the hippocampus-temporal fibers, thalamus-related fibers have shown significantly higher correlations with depression scores within MCI. Our results provide novel biomarkers for the early diagnoses of AD.
Assuntos
Doença de Alzheimer , Disfunção Cognitiva , Substância Branca , Doença de Alzheimer/diagnóstico por imagem , Encéfalo , Disfunção Cognitiva/diagnóstico por imagem , Imagem de Tensor de Difusão/métodos , Hipocampo/diagnóstico por imagem , Humanos , Tálamo/diagnóstico por imagem , Substância Branca/diagnóstico por imagemRESUMO
The brain-computer interface (BCI), also known as a brain-machine interface (BMI), has attracted extensive attention in biomedical applications. More importantly, BCI technologies have substantially revolutionized early predictions, diagnostic techniques, and rehabilitation strategies addressing acute diseases because of BCI's innovations and clinical translations. Therefore, in this chapter, a comprehensive description of the basic concepts of BCI will be exhibited, and various visualization techniques employed in BCI's medical applications will be discussed.
Assuntos
Interfaces Cérebro-Computador , Eletroencefalografia/métodosRESUMO
A significant industrial transformation in China's tourism sector is currently taking place in response to carbon peak and carbon neutrality targets. This paper applies the data envelopment analysis (DEA) model to calculate the efficiency of the tourism industry under carbon emission constraints and further investigates its influencing factors through the Tobit regression. The results are as follows: (1) The tourism efficiency under carbon emission constraints of China from 2000 to 2019 showed a trend of first rising and then declining, and there were obvious regional differences; (2) from 2000 to 2019, the total factor productivity of tourism in China increased significantly, while the contributions of technical progress, pure technical efficiency, and scale efficiency decreased sequentially; (3) the factors of industrial structure, transportation convenience, economic development level, degree of opening to the outside world, and the level of scientific and technological development have varying degrees of influence on tourism efficiency. Based on the analysis results, this paper puts forward several policy suggestions on tourism efficiency and low-carbon development. The findings of this paper have some bearing on developing nations' efforts to boost tourism efficiency and realize high-quality industry growth within the framework of sustainable development.
Assuntos
Monitoramento Ambiental , Turismo , Indústrias , China , CarbonoRESUMO
The human auditory cortex is recently found to contribute to the frequency following response (FFR) and the cortical component has been shown to be more relevant to speech perception. However, it is not clear how cortical FFR may contribute to the processing of speech fundamental frequency (F0) and the dynamic pitch. Using intracranial EEG recordings, we observed a significant FFR at the fundamental frequency (F0) for both speech and speech-like harmonic complex stimuli in the human auditory cortex, even in the missing fundamental condition. Both the spectral amplitude and phase coherence of the cortical FFR showed a significant harmonic preference, and attenuated from the primary auditory cortex to the surrounding associative auditory cortex. The phase coherence of the speech FFR was found significantly higher than that of the harmonic complex stimuli, especially in the left hemisphere, showing a high timing fidelity of the cortical FFR in tracking dynamic F0 in speech. Spectrally, the frequency band of the cortical FFR was largely overlapped with the range of the human vocal pitch. Taken together, our study parsed the intrinsic properties of the cortical FFR and reveals a preference for speech-like sounds, supporting its potential role in processing speech intonation and lexical tones.
Assuntos
Córtex Auditivo/fisiologia , Estimulação Acústica , Adolescente , Adulto , Criança , Eletroencefalografia , Epilepsia/fisiopatologia , Potenciais Evocados Auditivos/fisiologia , Feminino , Humanos , Masculino , Percepção da Altura Sonora/fisiologia , Fala , Percepção da Fala/fisiologia , Adulto JovemRESUMO
In tonal languages such as Chinese, lexical tone with varying pitch contours serves as a key feature to provide contrast in word meaning. Similar to phoneme processing, behavioral studies have suggested that Chinese tone is categorically perceived. However, its underlying neural mechanism remains poorly understood. By conducting cortical surface recordings in surgical patients, we revealed a cooperative cortical network along with its dynamics responsible for this categorical perception. Based on an oddball paradigm, we found amplified neural dissimilarity between cross-category tone pairs, rather than between within-category tone pairs, over cortical sites covering both the ventral and dorsal streams of speech processing. The bilateral superior temporal gyrus (STG) and the middle temporal gyrus (MTG) exhibited increased response latencies and enlarged neural dissimilarity, suggesting a ventral hierarchy that gradually differentiates the acoustic features of lexical tones. In addition, the bilateral motor cortices were also found to be involved in categorical processing, interacting with both the STG and the MTG and exhibiting a response latency in between. Moreover, the motor cortex received enhanced Granger causal influence from the semantic hub, the anterior temporal lobe, in the right hemisphere. These unique data suggest that there exists a distributed cooperative cortical network supporting the categorical processing of lexical tone in tonal language speakers, not only encompassing a bilateral temporal hierarchy that is shared by categorical processing of phonemes but also involving intensive speech-motor interactions over the right hemisphere, which might be the unique machinery responsible for the reliable discrimination of tone identities.
Assuntos
Córtex Motor/fisiologia , Rede Nervosa/fisiologia , Percepção da Altura Sonora/fisiologia , Percepção da Fala/fisiologia , Lobo Temporal/fisiologia , Adulto , Povo Asiático , Mapeamento Encefálico , Epilepsia Resistente a Medicamentos/diagnóstico por imagem , Epilepsia Resistente a Medicamentos/patologia , Epilepsia Resistente a Medicamentos/fisiopatologia , Eletrodos Implantados , Eletroencefalografia , Feminino , Humanos , Idioma , Masculino , SemânticaRESUMO
Climate change has become an unavoidable problem in achieving sustainable development. As one of the major industries worldwide, tourism can make a significant contribution to mitigating climate change. The main objective of the paper is to assess the development level of low-carbon tourism from multi-aspect, using the Yellow River Basin as an example. Firstly, this study quantified tourism carbon dioxide emissions and tourism economy, and analyzed their evolution characteristics. The interaction and coordination degree between tourism carbon dioxide emissions and tourism economy were then analyzed using the improved coupling coordination degree model. Finally, this study analyzed the change in total factor productivity of low-carbon tourism by calculating the Malmquist-Luenberger productivity index. The results showed that: (1) the tourism industry in the Yellow River Basin has the characteristics of the initial environmental Kuznets curve. (2) There was a strong interaction between tourism carbon dioxide emissions and tourism economy, which was manifested as mutual promotion. (3) The total factor productivity of low-carbon tourism was increasing. Based on the above results, it could be concluded that the development level of low-carbon tourism in the Yellow River Basin has been continuously improved from 2000 to 2019, but it is still in the early development stage with the continuous growth of carbon dioxide emissions.
RESUMO
Emotion recognition is crucial for human-computer interaction, and electroencephalography (EEG) stands out as a valuable tool for capturing and reflecting human emotions. In this study, we propose a hierarchical hybrid model called Mixed Attention-based Convolution and Transformer Network (MACTN). This model is designed to collectively capture both local and global temporal information and is inspired by insights from neuroscientific research on the temporal dynamics of emotions. First, we introduce depth-wise temporal convolution and separable convolution to extract local temporal features. Then, a self-attention-based transformer is used to integrate the sparse global emotional features. Besides, channel attention mechanism is designed to identify the most task-relevant channels, facilitating the capture of relationships between different channels and emotional states. Extensive experiments are conducted on three public datasets under both offline and online evaluation modes. In the multi-class cross-subject online evaluation using the THU-EP dataset, MACTN demonstrates an approximate 8% enhancement in 9-class emotion recognition accuracy in comparison to state-of-the-art methods. In the multi-class cross-subject offline evaluation using the DEAP and SEED datasets, a comparable performance is achieved solely based on the raw EEG signals, without the need for prior knowledge or transfer learning during the feature extraction and learning process. Furthermore, ablation studies have shown that integrating self-attention and channel-attention mechanisms improves classification performance. This method won the Emotional BCI Competition's final championship in the World Robot Contest. The source code is available at https://github.com/ThreePoundUniverse/MACTN.
RESUMO
BACKGROUND: Abnormalities in structural-functional connectivity (SC-FC) coupling have been identified globally in patients with major depressive disorder (MDD). However, investigations have neglected the variability and hierarchical distribution of these abnormalities across different brain regions. Furthermore, the biological mechanisms underlying regional SC-FC coupling patterns are not well understood. METHODS: We enrolled 182 patients with MDD and 157 healthy control (HC) subjects, quantifying the intergroup differences in regional SC-FC coupling. The extreme gradient boosting (XGBoost), support vector machines (SVM) and random forest (RF) models were constructed to assess the potential of SC-FC coupling as biomarkers for MDD diagnosis and symptom prediction. Then, we examined the link between changes in regional SC-FC coupling in patients with MDD, neurotransmitter distributions, and gene expression. RESULTS: We observed increased regional SC-FC coupling in default mode network (T = 3.233) and decreased coupling in frontoparietal network (T = -3.471) in MDD relative to HC. XGBoost (AUC = 0.853), SVM (AUC = 0.832) and RF (p < 0.05) models exhibited good prediction performance. The alterations in regional SC-FC coupling in patients with MDD were correlated with the distributions of four neurotransmitters (p < 0.05) and expression maps of specific genes. These genes were strongly enriched in genes implicated in excitatory neurons, inhibitory neurons, cellular metabolism, synapse function, and immune signaling. These findings were replicated on two brain atlases. CONCLUSIONS: This work enhances our understanding of MDD and pave the way for the development of additional targeted therapeutic interventions.
RESUMO
Functional near-infrared spectroscopy (fNIRS) is a noninvasive brain imaging technique that has gradually been applied in emotion recognition research due to its advantages of high spatial resolution, real time, and convenience. However, the current research on emotion recognition based on fNIRS is mainly limited to within-subject, and there is a lack of related work on emotion recognition across subjects. Therefore, in this paper, we designed an emotion evoking experiment with videos as stimuli and constructed the fNIRS emotion recognition database. On this basis, deep learning technology was introduced for the first time, and a dual-branch joint network (DBJNet) was constructed, creating the ability to generalize the model to new participants. The decoding performance obtained by the proposed model shows that fNIRS can effectively distinguish positive versus neutral versus negative emotions (accuracy is 74.8%, F1 score is 72.9%), and the decoding performance on the 2-category emotion recognition task of distinguishing positive versus neutral (accuracy is 89.5%, F1 score is 88.3%), negative versus neutral (accuracy is 91.7%, F1 score is 91.1%) proved fNIRS has a powerful ability to decode emotions. Furthermore, the results of the ablation study of the model structure demonstrate that the joint convolutional neural network branch and the statistical branch achieve the highest decoding performance. The work in this paper is expected to facilitate the development of fNIRS affective brain-computer interface.
RESUMO
Objective.Patient-dependent seizure detection based on intracranial electroencephalography (iEEG) has made significant progress. However, due to the difference in the locations and number of iEEG electrodes used for each patient, patient-independent seizure detection based on iEEG has not been carried out. Additionally, current seizure detection algorithms based on deep learning have outperformed traditional machine learning algorithms in many performance metrics. However, they still have shortcomings of large memory footprints and slow inference speed.Approach.To solve the above problems of the current study, we propose a novel lightweight convolutional neural network model combining the Convolutional Block Attention Module (CBAM). Its performance for patient-independent seizure detection is evaluated on two long-term continuous iEEG datasets: SWEC-ETHZ and TJU-HH. Finally, we reproduce four other patient-independent methods to compare with our method and calculate the memory footprints and inference speed for all methods.Main results.Our method achieves 83.81% sensitivity (SEN) and 85.4% specificity (SPE) on the SWEC-ETHZ dataset and 86.63% SEN and 92.21% SPE on the TJU-HH dataset. In particular, it takes only 11 ms to infer 10 min iEEG (128 channels), and its memory footprint is only 22 kB. Compared to baseline methods, our method not only achieves better patient-independent seizure detection performance but also has a smaller memory footprint and faster inference speed.Significance.To our knowledge, this is the first iEEG-based patient-independent seizure detection study. This facilitates the application of seizure detection algorithms to the future clinic.
Assuntos
Eletrocorticografia , Eletroencefalografia , Humanos , Eletrocorticografia/métodos , Eletroencefalografia/métodos , Convulsões/diagnóstico , Redes Neurais de Computação , AlgoritmosRESUMO
Automatic seizure detection algorithms are necessary for patients with refractory epilepsy. Many excellent algorithms have achieved good results in seizure detection. Still, most of them are based on discontinuous intracranial electroencephalogram (iEEG) and ignore the impact of different channels on detection. This study aimed to evaluate the proposed algorithm using continuous, long-term iEEG to show its applicability in clinical routine. In this study, we introduced the ability of the transformer network to calculate the attention between the channels of input signals into seizure detection. We proposed an end-to-end model that included convolution and transformer layers. The model did not need feature engineering or format transformation of the original multi-channel time series. Through evaluation on two datasets, we demonstrated experimentally that the transformer layer could improve the performance of the seizure detection algorithm. For the SWEC-ETHZ iEEG dataset, we achieved 97.5% event-based sensitivity, 0.06/h FDR, and 13.7 s latency. For the TJU-HH iEEG dataset, we achieved 98.1% event-based sensitivity, 0.22/h FDR, and 9.9 s latency. In addition, statistics showed that the model allocated more attention to the channels close to the seizure onset zone within 20 s after the seizure onset, which improved the explainability of the model. This paper provides a new method to improve the performance and explainability of automatic seizure detection.
Assuntos
Eletroencefalografia , Convulsões , Humanos , Eletroencefalografia/métodos , Convulsões/diagnóstico , Algoritmos , Fatores de TempoRESUMO
Background: Detection of mild cognitive impairment (MCI) is essential to screen high risk of Alzheimer's disease (AD). However, subtle changes during MCI make it challenging to classify in machine learning. The previous pathological analysis pointed out that the hippocampus is the critical hub for the white matter (WM) network of MCI. Damage to the white matter pathways around the hippocampus is the main cause of memory decline in MCI. Therefore, it is vital to biologically extract features from the WM network driven by hippocampus-related regions to improve classification performance. Methods: Our study proposes a method for feature extraction of the whole-brain WM network. First, 42 MCI and 54 normal control (NC) subjects were recruited using diffusion tensor imaging (DTI), resting-state functional magnetic resonance imaging (rs-fMRI), and T1-weighted (T1w) imaging. Second, mean diffusivity (MD) and fractional anisotropy (FA) were calculated from DTI, and the whole-brain WM networks were obtained. Third, regions of interest (ROIs) with significant functional connectivity to the hippocampus were selected for feature extraction, and the hippocampus (HIP)-related WM networks were obtained. Furthermore, the rank sum test with Bonferroni correction was used to retain significantly different connectivity between MCI and NC, and significant HIP-related WM networks were obtained. Finally, the classification performances of these three WM networks were compared to select the optimal feature and classifier. Results: (1) For the features, the whole-brain WM network, HIP-related WM network, and significant HIP-related WM network are significantly improved in turn. Also, the accuracy of MD networks as features is better than FA. (2) For the classification algorithm, the support vector machine (SVM) classifier with radial basis function, taking the significant HIP-related WM network in MD as a feature, has the optimal classification performance (accuracy = 89.4%, AUC = 0.954). (3) For the pathologic mechanism, the hippocampus and thalamus are crucial hubs of the WM network for MCI. Conclusion: Feature extraction from the WM network driven by hippocampus-related regions provides an effective method for the early diagnosis of AD.
RESUMO
Objective. Decoding imagined speech from brain signals could provide a more natural, user-friendly way for developing the next generation of the brain-computer interface (BCI). With the advantages of non-invasive, portable, relatively high spatial resolution and insensitivity to motion artifacts, the functional near-infrared spectroscopy (fNIRS) shows great potential for developing the non-invasive speech BCI. However, there is a lack of fNIRS evidence in uncovering the neural mechanism of imagined speech. Our goal is to investigate the specific brain regions and the corresponding cortico-cortical functional connectivity features during imagined speech with fNIRS.Approach. fNIRS signals were recorded from 13 subjects' bilateral motor and prefrontal cortex during overtly and covertly repeating words. Cortical activation was determined through the mean oxygen-hemoglobin concentration changes, and functional connectivity was calculated by Pearson's correlation coefficient.Main results. (a) The bilateral dorsal motor cortex was significantly activated during the covert speech, whereas the bilateral ventral motor cortex was significantly activated during the overt speech. (b) As a subregion of the motor cortex, sensorimotor cortex (SMC) showed a dominant dorsal response to covert speech condition, whereas a dominant ventral response to overt speech condition. (c) Broca's area was deactivated during the covert speech but activated during the overt speech. (d) Compared to overt speech, dorsal SMC(dSMC)-related functional connections were enhanced during the covert speech.Significance. We provide fNIRS evidence for the involvement of dSMC in speech imagery. dSMC is the speech imagery network's key hub and is probably involved in the sensorimotor information processing during the covert speech. This study could inspire the BCI community to focus on the potential contribution of dSMC during speech imagery.
Assuntos
Interfaces Cérebro-Computador , Córtex Motor , Córtex Sensório-Motor , Hemodinâmica , Humanos , FalaRESUMO
The electroencephalography (EEG) microstate has recently emerged as a new whole-brain mapping tool for studying the temporal dynamics of the human brain. Meanwhile, the neuromodulation effect of external stimulation on the human brain is of increasing interest to neuroscientists. Acupuncture, which originated in ancient China, is recognized as an external neuromodulation method with therapeutic effects. Effective acupuncture could elicit the deqi effect, which is a combination of multiple sensations. However, whether the EEG microstate could be used to reveal the neuromodulation effect of acupuncture with deqi remains largely unclear. In this study, multichannel EEG data were recorded from 16 healthy subjects during acupuncture manipulation, as well as during pre- and post-manipulation tactile controls and pre- and post-acupuncture rest controls. As the basic acupuncture unit for regulating the central nervous system, the Hegu acupoint was used in this study, and each subject's acupuncture deqi behavior scores were collected. To reveal the neuroimaging evidence of acupuncture with deqi, EEG microstate analysis was conducted to obtain the microstate maps and microstate parameters for different conditions. Furthermore, Pearson's correlation was analyzed to investigate the correlation relationship between microstate parameters and deqi behavioral scores. Results showed that: (1) compared with tactile controls, acupuncture manipulation caused significantly increased deqi behavioral scores. (2) Acupuncture manipulation significantly increased the duration, occurrence, and contribution parameters of microstate C, whereas it decreased those parameters of microstate D. (3) Microstate C's duration parameter showed a significantly positive correlation with acupuncture deqi behavior scores. (4) Acupuncture manipulation significantly increased the transition probabilities with microstate C as node, whereas it reduced the transition probabilities with microstate D as node. (5) Microstate BâC's transition probability also showed a significantly positive correlation with acupuncture deqi behavior scores. Taken together, the temporal dynamic feature of EEG microstate could be used as objective neuroimaging evidence to reveal the neuromodulation effect of acupuncture with deqi.
RESUMO
[This corrects the article DOI: 10.3389/fnins.2021.693623.].
RESUMO
As a world intangible cultural heritage, acupuncture is considered an essential modality of complementary and alternative therapy to Western medicine. Despite acupuncture's long history and public acceptance, how the cortical network is modulated by acupuncture remains largely unclear. Moreover, as the basic acupuncture unit for regulating the central nervous system, how the cortical network is modulated during acupuncture at the Hegu acupoint is mostly unclear. Here, multi-channel functional near-infrared spectroscopy (fNIRS) data were recorded from twenty healthy subjects for acupuncture manipulation, pre- and post-manipulation tactile controls, and pre- and post-acupuncture rest controls. Results showed that: (1) acupuncture manipulation caused significantly increased acupuncture behavioral deqi performance compared with tactile controls. (2) The bilateral prefrontal cortex (PFC) and motor cortex were significantly inhibited during acupuncture manipulation than controls, which was evidenced by the decreased power of oxygenated hemoglobin (HbO) concentration. (3) The bilateral PFC's hemodynamic responses showed a positive correlation trend with acupuncture behavioral performance. (4) The network connections with bilateral PFC as nodes showed significantly increased functional connectivity during acupuncture manipulation compared with controls. (5) Meanwhile, the network's efficiency was improved by acupuncture manipulation, evidenced by the increased global efficiency and decreased shortest path length. Taken together, these results reveal that a cooperative PFC-Motor functional network could be modulated by acupuncture manipulation at the Hegu acupoint. This study provides neuroimaging evidence that explains acupuncture's neuromodulation effects on the cortical network.
RESUMO
Objective. By detecting abnormal white matter changes, diffusion magnetic resonance imaging (MRI) contributes to the detection of juvenile myoclonic epilepsy (JME). In addition, deep learning has greatly improved the detection performance of various brain disorders. However, there is almost no previous study effectively detecting JME by a deep learning approach with diffusion MRI.Approach. In this study, the white matter structural connectivity was generated by tracking the white matter fibers in detail based on Q-ball imaging and neurite orientation dispersion and density imaging. Four advanced deep convolutional neural networks (CNNs) were deployed by using the transfer learning approach, in which the transfer rate searching strategy was proposed to achieve the best detection performance.Main results. Our results showed: (a) Compared to normal control, the white matter' neurite density of JME was significantly decreased. The most significantly abnormal fiber tracts between the two groups were found to be cortico-cortical connection tracts. (b) The proposed transfer rate searching approach contributed to find each CNN's best performance, in which the best JME detection accuracy of 92.2% was achieved by using the Inception_resnet_v2 network with a 16% transfer rate.Significance. The results revealed: (a) Through detection of the abnormal white matter changes, the white matter structural connectivity can be used as a useful biomarker for detecting JME, which helps to characterize the pathophysiology of epilepsy. (b) The proposed transfer rate, as a new hyperparameter, promotes the CNNs transfer learning performance in detecting JME.
Assuntos
Epilepsia Mioclônica Juvenil , Substância Branca , Biomarcadores , Humanos , Epilepsia Mioclônica Juvenil/diagnóstico por imagem , Redes Neurais de Computação , Substância Branca/diagnóstico por imagemRESUMO
Epilepsy is one of the largest neurological diseases in the world, and juvenile myoclonic epilepsy (JME) usually occurs in adolescents, giving patients tremendous burdens during growth, which really needs the early diagnosis. Advanced diffusion magnetic resonance imaging (MRI) could detect the subtle changes of the white matter, which could be a non-invasive early diagnosis biomarker for JME. Transfer learning can solve the problem of insufficient clinical samples, which could avoid overfitting and achieve a better detection effect. However, there is almost no research to detect JME combined with diffusion MRI and transfer learning. In this study, two advanced diffusion MRI methods, high angle resolved diffusion imaging (HARDI) and neurite orientation dispersion and density imaging (NODDI), were used to generate the connectivity matrix which can describe tiny changes in white matter. And three advanced convolutional neural networks (CNN) based transfer learning were applied to detect JME. A total of 30 participants (15 JME patients and 15 normal controls) were analyzed. Among the three CNN models, Inception_resnet_v2 based transfer learning is better at detecting JME than Inception_v3 and Inception_v4, indicating that the "short cut" connection can improve the ability to detect JME. Inception_resnet_v2 achieved to detect JME with the accuracy of 75.2% and the AUC of 0.839. The results support that diffusion MRI and CNN based transfer learning have the potential to improve the automated detection of JME.
Assuntos
Epilepsia Mioclônica Juvenil , Adolescente , Imagem de Difusão por Ressonância Magnética , Humanos , Aprendizado de Máquina , Imageamento por Ressonância Magnética , Epilepsia Mioclônica Juvenil/diagnóstico , Redes Neurais de ComputaçãoRESUMO
In tonal languages, like Chinese, lexical tone serves as a key feature to provide contrast in word meaning. Behavior studies suggest that Mandarin Chinese tone is categorically perceived. However, the neural mechanism underlying Mandarin tone perception is still poorly understood. In this study, an Oddball paradigm was designed by selecting two standard-deviant stimulus pairs with same physical distance but different category labels, among the synthesized tones with continuously varying pitch contours. Using electrocorticography (ECoG) recording over human auditory cortex, high temporal and spatial resolution cortical neural signals were used for the first time to investigate the cortical processing of lexical tone. Here, we found different neural responses to the two standard-deviant tone pairs, and the difference increased from low to high level along the hierarchy of human auditory cortex. In the two dimensional neural space, cross-category neural distance of lexical tones is selectively amplified on those high level electrodes. These findings support a hierarchical and categorical model of Mandarin tone perception, and favor the using of high-level electrodes for a better performance of lexical tone discrimination in speech brain computer interface.