RESUMEN

Although our knowledge of autism spectrum disorder (ASD) has been deepened, the accurate diagnosis of ASD from normal individuals is still left behind. In this study, we proposed to apply the spatial pattern of the network topology (SPN) to identify children with ASD from normal ones. Based on two independent batches of electroencephalogram datasets collected separately, the accurate recognition of ASD from normal children was achieved by applying the proposed SPN features. Since decreased long-range connectivity was identified for children with ASD, the SPN features extracted from the distinctive topological architecture between two groups in the first dataset were used to validate the capacity of SPN in classifying ASD, and the SPN features achieved the highest accuracy of 92.31%, which outperformed the other features e.g., power spectrum density (84.62%), network properties (76.92%), and sample entropy (73.08%). Moreover, within the second dataset, by using the model trained in the first dataset, the SPN also acquired the highest sensitivity in recognizing ASD, when compared to the other features. These results consistently illustrated that the functional brain network, especially the intrinsic spatial network topology, might be the potential biomarker for the diagnosis of ASD.

RESUMEN

Urinary tract infection (UTI) is one of the most common infectious diseases among children, but there is controversy regarding the use of preventive antibiotics for children first diagnosed with febrile pyelonephritis. To the best of our knowledge, no studies have addressed this issue by the deep learning technology. Therefore, in the current study, we conducted a study using Tc99m-DMSA renal static imaging data to investigate the need for preventive antibiotics on children first diagnosed with febrile pyelonephritis under 2 years old. The self-collected dataset comprised 64 children who did not require preventive antibiotic treatments and 112 children who did. Using several classic deep learning models, we verified that it is feasible to screen whether the first diagnosed children with febrile pyelonephritis require preventive antibacterial therapy, achieving a graded diagnosis. With the AlexNet model, we obtained accuracy of 84.05%, sensitivity of 81.71% and specificity of 86.70%, respectively. The experimental results indicate that deep learning technology could provide a new avenue to implement computer-assisted decision support for the diagnosis of the febrile pyelonephritis.

RESUMEN

The mean teacher model and its variants, as important methods in semi-supervised learning, have demonstrated promising performance in magnetic resonance imaging (MRI) data segmentation. However, the superior performance of teacher model through exponential moving average (EMA) is limited by the unreliability of unlabeled image, resulting in potentially unreliable predictions. In this paper, we propose a framework to optimized the teacher model with reliable expert-annotated data while preserving the advantages of EMA. To avoid the tight coupling that results from EMA, we leverage data augmentations to provide two distinct perspectives for the teacher and student models. The teacher model adopts weak data augmentation to provide supervision for the student model and optimizes itself with real annotations, while the student uses strong data augmentation to avoid overfitting on noise information. In addition, double softmax helps the model resist noise and continue learning meaningful information from the images, which is a key component in the proposed model. Extensive experiments show that the proposed method exhibits competitive performance on the Left Atrium segmentation MRI dataset (LA) and the Brain Tumor Segmentation MRI dataset (BraTS2019). For the LA dataset, we achieved a dice of 91.02% using only 20% labeled data, which is close to the dice of 91.14% obtained by the supervised approach using 100% labeled data. For the BraTs2019 dataset, the proposed method achieved 1.02% and 1.92% improvement on 5% and 10% labeled data, respectively, compared to the best baseline method on this dataset. This study demonstrates that the proposed model can be a potential candidate for medical image segmentation in semi-supervised learning scenario.

Asunto(s)

RESUMEN

In recent years, the growing awareness of public health has brought attention to low-dose computed tomography (LDCT) scans. However, the CT image generated in this way contains a lot of noise or artifacts, which make increasing researchers to investigate methods to enhance image quality. The advancement of deep learning technology has provided researchers with novel approaches to enhance the quality of LDCT images. In the past, numerous studies based on convolutional neural networks (CNN) have yielded remarkable results in LDCT image reconstruction. Nonetheless, they all tend to continue to design new networks based on the fixed network architecture of UNet shape, which also leads to more and more complex networks. In this paper, we proposed a novel network model with a reverse U-shape architecture for the noise reduction in the LDCT image reconstruction task. In the model, we further designed a novel multi-scale feature extractor and edge enhancement module that yields a positive impact on CT images to exhibit strong structural characteristics. Evaluated on a public dataset, the experimental results demonstrate that the proposed model outperforms the compared algorithms based on traditional U-shaped architecture in terms of preserving texture details and reducing noise, as demonstrated by achieving the highest PSNR, SSIM and RMSE value. This study may shed light on the reverse U-shaped network architecture for CT image reconstruction, and could investigate the potential on other medical image processing.

Asunto(s)

RESUMEN

Deformable medical image registration plays an essential role in clinical diagnosis and treatment. However, due to the large difference in image deformation, unsupervised convolutional neural network (CNN)-based methods cannot extract global features and local features simultaneously and cannot capture long-distance dependencies to solve the problem of excessive deformation. In this paper, an unsupervised end-to-end registration network is proposed for 3D MRI medical image registration, named AEAU-Net, which includes two-stage operations, i.e., an affine transformation and a deformable registration. These two operations are implemented by an affine transformation subnetwork and a deformable registration subnetwork, respectively. In the deformable registration subnetwork, termed as EAU-Net, we designed an efficient attention mechanism (EAM) module and a recursive residual path (RSP) module. The EAM module is embedded in the bottom layer of the EAU-Net to capture long-distance dependencies. The RSP model is used to obtain effective features by fusing deep and shallow features. Extensive experiments on two datasets, LPBA40 and Mindboggle101, were conducted to verify the effectiveness of the proposed method. Compared with baseline methods, this proposed method could obtain better registration performance. The ablation study further demonstrated the reasonability and validity of the designed architecture of the proposed method.

Asunto(s)

RESUMEN

[This corrects the article DOI: 10.1007/s11571-020-09577-7.].

RESUMEN

Steady-state visual evoked potential (SSVEP) is one of the most commonly used control signals in the brain-computer interface (BCI) systems. However, the conventional spatial filtering methods for SSVEP classification highly depend on the subject-specific calibration data. The need for the methods that can alleviate the demand for the calibration data becomes urgent. In recent years, developing the methods that can work in inter-subject scenario has become a promising new direction. As a popular deep learning model nowadays, Transformer has been used in EEG signal classification tasks owing to its excellent performance. Therefore, in this study, we proposed a deep learning model for SSVEP classification based on Transformer architecture in inter-subject scenario, termed as SSVEPformer, which was the first application of Transformer on the SSVEP classification. Inspired by previous studies, we adopted the complex spectrum features of SSVEP data as the model input, which could enable the model to simultaneously explore the spectral and spatial information for classification. Furthermore, to fully utilize the harmonic information, an extended SSVEPformer based on the filter bank technology (FB-SSVEPformer) was proposed to improve the classification performance. Experiments were conducted using two open datasets (Dataset 1: 10 subjects, 12 targets; Dataset 2: 35 subjects, 40 targets). The experimental results show that the proposed models could achieve better results in terms of classification accuracy and information transfer rate than other baseline methods. The proposed models validate the feasibility of deep learning models based on Transformer architecture for SSVEP data classification, and could serve as potential models to alleviate the calibration procedure in the practical application of SSVEP-based BCI systems.

Asunto(s)

RESUMEN

Multichannel electroencephalogram (EEG) is an array signal that represents brain neural networks and can be applied to characterize information propagation patterns for different emotional states. To reveal these inherent spatial graph features and increase the stability of emotion recognition, we propose an effective emotion recognition model that performs multicategory emotion recognition with multiple emotion-related spatial network topology patterns (MESNPs) by learning discriminative graph topologies in EEG brain networks. To evaluate the performance of our proposed MESNP model, we conducted single-subject and multisubject four-class classification experiments on two public datasets, MAHNOB-HCI and DEAP. Compared with existing feature extraction methods, the MESNP model significantly enhances the multiclass emotional classification performance in the single-subject and multisubject conditions. To evaluate the online version of the proposed MESNP model, we designed an online emotion monitoring system. We recruited 14 participants to conduct the online emotion decoding experiments. The average online experimental accuracy of the 14 participants was 84.56%, indicating that our model can be applied in affective brain-computer interface (aBCI) systems. The offline and online experimental results demonstrate that the proposed MESNP model effectively captures discriminative graph topology patterns and significantly improves emotion classification performance. Moreover, the proposed MESNP model provides a new scheme for extracting features from strongly coupled array signals.

RESUMEN

Augmented reality-based brain-computer interface (AR-BCI) system is one of the important ways to promote BCI technology outside of the laboratory due to its portability and mobility, but its performance in real-world scenarios has not been fully studied. In the current study, we first investigated the effect of ambient brightness on AR-BCI performance. 5 different light intensities were set as experimental conditions to simulate typical brightness in real scenes, while the same steady-state visual evoked potentials (SSVEP) stimulus was displayed in the AR glass. The data analysis results showed that SSVEP can be evoked under all 5 light intensities, but the response intensity became weaker when the brightness increased. The recognition accuracies of AR-SSVEP were negatively correlated to light intensity, the highest accuracies were 89.35% with FBCCA and 83.33% with CCA under 0 lux light intensity, while they decreased to 62.53% and 49.24% under 1200 lux. To solve the accuracy loss problem in high ambient brightness, we further designed a SSVEP recognition algorithm with iterative learning capability, named ensemble online adaptive CCA (eOACCA). The main strategy is to provide initial filters for high-intensity data by iteratively learning low-light-intensity AR-SSVEP data. The experimental results showed that the eOACCA algorithm had significant advantages under higher light intensities ( 600 lux). Compared with FBCCA, the accuracy of eOACCA under 1200 lux was increased by 13.91%. In conclusion, the current study contributed to the in-depth understanding of the performance variations of AR-BCI under different lighting conditions, and was helpful in promoting the AR-BCI application in complex lighting environments.

Asunto(s)

RESUMEN

Auditory verbal hallucinations (AVH) are a core positive symptom of schizophrenia and are regarded as a consequence of the functional breakdown in the related sensory process. Yet, the potential mechanism of AVH is still lacking. In the present study, we explored the difference between AVHs (n = 23) and non-AVHs (n = 19) in schizophrenia and healthy controls (n = 29) by using multidimensional electroencephalograms data during an auditory oddball task. Compared to healthy controls, both AVH and non-AVH groups showed reduced P300 amplitudes. Additionally, the results from brain networks analysis revealed that AVH patients showed reduced left frontal to posterior parietal/temporal connectivity compared to non-AVH patients. Moreover, using the fused network properties of both delta and theta bands as features for in-depth learning made it possible to identify the AVH from non-AVH patients at an accuracy of 80.95%. The left frontal-parietal/temporal networks seen in the auditory oddball paradigm might be underlying biomarkers of AVH in schizophrenia. This study demonstrated for the first time the functional breakdown of the auditory processing pathway in the AVH patients, leading to a better understanding of the atypical brain network of the AVH patients.

Asunto(s)

RESUMEN

In recent years, emotion recognition based on electroencephalography (EEG) has received growing interests in the brain-computer interaction (BCI) field. The neuroscience researches indicate that the left and right brain hemispheres demonstrate activity differences under different emotional activities, which could be an important principle for designing deep learning (DL) model for emotion recognition. Besides, owing to the nonstationarity of EEG signals, using convolution kernels of a single size may not sufficiently extract the abundant features for EEG classification tasks. Based on these two angles, we proposed a model termed Multi-Scales Bi-hemispheric Asymmetric Model (MSBAM) based on convolutional neural network (CNN) structure. Evaluated on the public DEAP and DREAMER datasets, MSBAM achieved over 99% accuracy for the two-class classification of low-level and high-level states in each of four emotional dimensions, i.e., arousal, valence, dominance and liking, respectively. This study further demonstrated the promising potential to design the DL model from the multi-scale characteristics of the EEG data and the neural mechanisms of the emotion cognition.

Asunto(s)

RESUMEN

Objective. Steady-state visual evoked potentials (SSVEPs) based brain-computer interface (BCI) has received great interests owing to the high information transfer rate and available large number of targets. However, the performance of frequency recognition methods heavily depends on the amount of the calibration data for intra-subject classification. Some research adopted the deep learning (DL) algorithm to conduct the inter-subject classification, which could reduce the calculation procedure, but the performance still has large room to improve compared with the intra-subject classification.Approach. To address these issues, we proposed an efficient SSVEP DL NETwork (termed SSVEPNET) based on one-dimensional convolution and long short-term memory (LSTM) module. To enhance the performance of SSVEPNET, we adopted the spectral normalization and label smoothing technologies during implementing the network architecture. We evaluated the SSVEPNET and compared it with other methods for the intra- and inter-subject classification under different conditions, i.e. two datasets, two time-window lengths (1 s and 0.5 s), three sizes of training data.Main results. Under all the experimental settings, the proposed SSVEPNET achieved the highest average accuracy for the intra- and inter-subject classification on the two SSVEP datasets, when compared with other traditional and DL baseline methods.Significance. The extensive experimental results demonstrate that the proposed DL model holds promise to enhance frequency recognition performance in SSVEP-based BCIs. Besides, the mixed network structures with convolutional neural network and LSTM, and the spectral normalization and label smoothing could be useful optimization strategies to design efficient models for electroencephalography data.

Asunto(s)

RESUMEN

Hemiplegia is a common dysfunction caused by the brain stroke and leads to movement disability. Although the lateralization of movement-related potential, the event-related desynchronization, and more complicated inter-regional information coupling have been investigated, seldom studies have focused on investigating the dynamic information exchanging among multiple brain regions during motor execution for post-stroke hemiplegic patients. With high temporal-resolution electroencephalogram (EEG), the time-varying network is able to reflect the dynamical complex network modalities corresponding to the movements at a millisecond level. In our present study, the wrist extension experiment was designed, along with related EEG datasets being collected. Thereafter, the corresponding time-varying networks underlying the wrist extension were accordingly constructed by adopting the adaptive directed transfer function and then statistically explored, to further uncover the dynamic network deficits (i.e., motor dysfunction) in post-stroke hemiplegic patients. Results of this study found the effective connectivity between the stroked motor area and other areas decreased in patients when compared to healthy controls; on the contrary, the enhanced connectivity between non-stroked motor areas and other areas, especially the frontal and parietal-occipital lobes, were further identified for patients during their accomplishing the designed wrist extension, which might dynamically compensate for the deficited patients' motor behaviors. These findings not only helped deepen our knowledge of the mechanism underlying the patients' motor behaviors, but also facilitated the real-time strategies for clinical therapy of brain stroke, as well as providing a reliable biomarker to predict the future rehabilitation. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-021-09738-2.

RESUMEN

Autism spectrum disorder (ASD) is associated with the impaired integrating and segregating of related information that is expanded within the large-scale brain network. The varying ASD symptom severities have been explored, relying on their behaviors and related brain activity, but how to effectively predict ASD symptom severity needs further exploration. In this study, we aim to investigate whether the ASD symptom severity could be predicted with electroencephalography (EEG) metrics. Based on a publicly available dataset, the EEG brain networks were constructed, and four types of EEG metrics were calculated. Then, we statistically compared the brain network differences among ASD children with varying severities, i.e., high/low autism diagnostic observation schedule (ADOS) scores, as well as with the typically developing (TD) children. Thereafter, the EEG metrics were utilized to validate whether they could facilitate the prediction of the ASD symptom severity. The results demonstrated that both high- and low-scoring ASD children showed the decreased long-range frontal-occipital connectivity, increased anterior frontal connectivity and altered network properties. Furthermore, we found that the four types of EEG metrics are significantly correlated with the ADOS scores, and their combination can serve as the features to effectively predict the ASD symptom severity. The current findings will expand our knowledge of network dysfunction in ASD children and provide new EEG metrics for predicting the symptom severity.

Asunto(s)

RESUMEN

As one of the important psychological stress reactions, Micro-expressions (MEs) are spontaneous and subtle facial movements, which usually occur in a high-stake situation and can reveal genuine human feelings and cognition. ME, Recognition (MER) has essential applications in many fields such as lie detection, criminal investigation, and psychological healing. However, due to the challenges of learning discriminative ME features via fleeting facial subtle reactions as well as the shortage of available MEs data, this research topic is still far from well-studied. To this end, in this paper, we propose a deep prototypical learning framework, namely ME-PLAN, with a local attention mechanism for the MER problem. Specifically, ME-PLAN consists of two components, i.e., a 3D residual prototypical network and a local-wise attention module, where the former aims to learn the precise ME feature prototypes through expression-related knowledge transfer and episodic training, and the latter could facilitate the attention to the local facial movements. Furthermore, to alleviate the dilemma that most MER methods need to depend on manually annotated apex frames, we propose an apex frame spotting method with Unimodal Pattern Constrained (UPC) and further extract ME key-frames sequences based on the detected apex frames to train our proposed ME-PLAN in an end-to-end manner. Finally, through extensive experiments and interpretable analysis regarding the apex frame spotting and MER on composite-database, we demonstrate the superiority and effectiveness of the proposed methods.

Asunto(s)

RESUMEN

The clinical therapy of schizophrenia (SCZ) replies on the corresponding accurate and reliable recognition. Although efforts have been paid, the diagnosis of SCZ is still roughly subjective, it is thus urgent to search for related objective physiological parameters. Motivated by the great potential of resting-state networks in underling the brain deficits among different SCZ groups, in this study, we then developed a multi-class feature extraction approach that could effectively extract the spatial network topology and facilitate the recognition of the SCZ, by combining a network structure based supervised learning with an ensemble co-decision strategy. The results demonstrated that the multi-class spatial pattern of the network (MSPN) features outperformed the other conventional electrophysiological features, such as relative power spectrums and network properties, and achieved the highest classification accuracy of 71.58% in the alpha band. These findings did validate that the resting-state MSPN is a promising tool for the clinical assessment of the SCZ.

Asunto(s)

RESUMEN

The state of neck motion reflects cervical health. To detect the motion state of the human neck is of important significance to healthcare intelligence. A practical neck motion detector should be wearable, flexible, power efficient, and low cost. Here, we report such a neck motion detector comprising a self-powered triboelectric sensor group and a deep learning block. Four flexible and stretchable silicon rubber based triboelectric sensors are integrated on a neck collar. With different neck motions, these four sensors lead-out voltage signals with different amplitudes and/or directions. Thus, the combination of these four signals can represent one motion state. Significantly, a carbon-doped silicon rubber layer is attached between the neck collar and the sensors to shield the external electric field (i.e., electrical changes at the skin surface) for a far more robust identification. Furthermore, a deep learning model based on the convolutional neural network is designed to recognize 11 classes of neck motion including eight directions of bending, two directions of twisting, and one resting state with an average recognition accuracy of 92.63%. This developed neck motion detector has promising applications in neck monitoring, rehabilitation, and control.

Asunto(s)

RESUMEN

Steady-state visual evoked potential (SSVEP) is one of the commonly used control signals in brain-computer interface (BCI) systems. The SSVEP-based BCI has the advantages of high information transmission rate and short training time, which has become an important branch of BCI research field. In this review paper, the main progress on frequency recognition algorithm for SSVEP in past five years are summarized from three aspects, i.e., unsupervised learning algorithms, supervised learning algorithms and deep learning algorithms. Finally, some frontier topics and potential directions are explored.

Asunto(s)

RESUMEN

Objective.Electroencephalogram (EEG)-based motor imagery (MI) brain-computer interface offers a promising way to improve the efficiency of motor rehabilitation and motor skill learning. In recent years, the power of dynamic network analysis for MI classification has been proved. In fact, its usability mainly depends on the accurate estimation of brain connection. However, traditional dynamic network estimation strategies such as adaptive directed transfer function (ADTF) are designed in the L2-norm. Usually, they estimate a series of pseudo connections caused by outliers, which results in biased features and further limits its online application. Thus, how to accurately infer dynamic causal relationship under outlier influence is urgent.Approach.In this work, we proposed a novel ADTF, which solves the dynamic system in the L1-norm space (L1-ADTF), so as to restrict the outlier influence. To enhance its convergence, we designed an iteration strategy with the alternating direction method of multipliers, which could be used for the solution of the dynamic state-space model restricted in the L1-norm space. Furthermore, we compared L1-ADTF to traditional ADTF and its dual extension across both simulation and real EEG experiments.Main results.A quantitative comparison between L1-ADTF and other ADTFs in simulation studies demonstrates that fewer bias errors and more desirable dynamic state transformation patterns can be captured by the L1-ADTF. Application to real MI EEG datasets seriously noised by ocular artifacts also reveals the efficiency of the proposed L1-ADTF approach to extract the time-varying brain neural network patterns, even when more complex noises are involved.Significance.The L1-ADTF may not only be capable of tracking time-varying brain network state drifts robustly but may also be useful in solving a wide range of dynamic systems such as trajectory tracking problems and dynamic neural networks.

Asunto(s)