Deep learning-based ultrasonographic classification of canine chronic kidney disease.

Objectives: In veterinary medicine, attempts to apply artificial intelligence (AI) to ultrasonography have rarely been reported, and few studies have investigated the value of AI in ultrasonographic diagnosis. This study aimed to develop a deep learning-based model for classifying the status of canine chronic kidney disease (CKD) using renal ultrasonographic images and assess its diagnostic performance in comparison with that of veterinary imaging specialists, thereby verifying its clinical utility. Materials and methods: In this study, 883 ultrasonograms were obtained from 198 dogs, including those diagnosed with CKD according to the International Renal Interest Society (IRIS) guidelines and healthy dogs. After preprocessing and labeling each image with its corresponding IRIS stage, the renal regions were extracted and classified based on the IRIS stage using the convolutional neural network-based object detection algorithm You Only Look Once. The training scenarios consisted of multi-class classification, categorization of images into IRIS stages, and four binary classifications based on specific IRIS stages. To prevent model overfitting, we balanced the dataset, implemented early stopping, used lightweight models, and applied dropout techniques. Model performance was assessed using accuracy, recall, precision, F1 score, and receiver operating characteristic curve and compared with the diagnostic accuracy of four specialists. Inter- and intra-observer variabilities among specialists were also evaluated. Results: The developed model exhibited a low accuracy of 0.46 in multi-class classification. However, a significant performance improvement was observed in binary classifications, with the model designed to distinguish stage 3 or higher showing the highest accuracy of 0.85. In this classification, recall, precision, and F1 score values were all 0.85, and the area under the curve was 0.89. Compared with radiologists, whose accuracy ranged from 0.48 to 0.62 in this experimental scenario, the AI model exhibited superiority. Intra-observer reliability among radiologists was substantial, whereas inter-observer variability showed a moderate level of agreement. Conclusions: This study developed a deep-learning framework capable of reliably classifying CKD IRIS stages 3 and 4 in dogs using ultrasonograms. The developed framework demonstrated higher accuracy than veterinary imaging specialists and provided more objective and consistent interpretations. Therefore, deep-learning-based ultrasound diagnostics are potentially valuable tools for diagnosing CKD in dogs.

Automatic Sleep Stage Classification Using Nasal Pressure Decoding Based on a Multi-Kernel Convolutional BiLSTM Network.

Sleep quality is an essential parameter of a healthy human life, while sleep disorders such as sleep apnea are abundant. In the investigation of sleep and its malfunction, the gold-standard is polysomnography, which utilizes an extensive range of variables for sleep stage classification. However, undergoing full polysomnography, which requires many sensors that are directly connected to the heaviness of the setup and the discomfort of sleep, brings a significant burden. In this study, sleep stage classification was performed using the single dimension of nasal pressure, dramatically decreasing the complexity of the process. In turn, such improvements could increase the much needed clinical applicability. Specifically, we propose a deep learning structure consisting of multi-kernel convolutional neural networks and bidirectional long short-term memory for sleep stage classification. Sleep stages of 25 healthy subjects were classified into 3-class (wake, rapid eye movement (REM), and non-REM) and 4-class (wake, REM, light, and deep sleep) based on nasal pressure. Following a leave-one-subject-out cross-validation, in the 3-class the accuracy was 0.704, the F1-score was 0.490, and the kappa value was 0.283 for the overall metrics. In the 4-class, the accuracy was 0.604, the F1-score was 0.349, and the kappa value was 0.217 for the overall metrics. This was higher than the four comparative models, including the class-wise F1-score. This result demonstrates the possibility of a sleep stage classification model only using easily applicable and highly practical nasal pressure recordings. This is also likely to be used with interventions that could help treat sleep-related diseases.

Targeting of CYP2E1 by miRNAs in alcohol-induced intestine injury.

Although binge alcohol-induced gut leakage has been studied extensively in the context of reactive oxygen species-mediated signaling, it was recently revealed that post-transcriptional regulation plays an essential role as well. Ethanol (EtOH)-inducible cytochrome P450-2E1 (CYP2E1), a key enzyme in EtOH metabolism, promotes alcohol-induced hepatic steatosis and inflammatory liver disease, at least in part by mediating changes in intestinal permeability. For instance, gut leakage and elevated intestinal permeability to endotoxins have been shown to be regulated by enhancing CYP2E1 mRNA and CYP2E1 protein levels. Although it is understood that EtOH promotes CYP2E1 induction and activation, the mechanisms that regulate CYP2E1 expression in the context of intestinal damage remain poorly defined. Specific miRNAs, including miR-132, miR-212, miR-378, and miR-552, have been shown to repress the expression of CYP2E1, suggesting that these miRNAs contribute to EtOH-induced intestinal injury. Here, we have shown that CYP2E1 expression is regulated post-transcriptionally through miRNA-mediated degradation, as follows: (1) the RNA-binding protein AU-binding factor 1 (AUF1) binds mature miRNAs, including CYP2E1-targeting miRNAs, and this binding modulates the degradation of corresponding target mRNAs upon EtOH treatment; (2) the serine/threonine kinase mammalian Ste20-like kinase 1 (MST1) mediates oxidative stress-induced phosphorylation of AUF1. Those findings suggest that reactive oxygen species-mediated signaling modulates AUF1/miRNA interaction through MST1-mediated phosphorylation. Thus, our study demonstrates the critical functions of AUF1 phosphorylation by MST1 in the decay of miRNAs targeting CYP2E1, the stabilization of CYP2E1 mRNA in the presence of EtOH, and the relationship of this pathway to subsequent intestinal injury.

Inhibitory effect of doxycycline conjugated with deoxycholic acid and polyethylenimine conjugate on nasal fibroblast differentiation and extracellular production.

BACKGROUND: Chronic rhinosinusitis (CRS) is an inflammatory disease affecting the sinuses or nose. Persistent inflammatory responses can lead to tissue remodeling, which is a pathological characteristics of CRS. Activation of fibroblasts in the nasal mucosal stroma, differentiation and collagen deposition, and subepithelial fibrosis have been associated with CRS. OBJECTIVES: We aimed to assess the inhibitory effects of doxycycline and deoxycholic acid-polyethyleneimine conjugate (DA3-Doxy) on myofibroblast differentiation and extracellular matrix (ECM) production in nasal fibroblasts stimulated with TGF-ß1. METHODS: To enhance efficacy, we prepared DA3-Doxy using a conjugate of low-molecular-weight polyethyleneimine (PEI) (MW 1800) and deoxycholic acid (DA) and Doxy. The synthesis of the DA3-Doxy polymer was confirmed using nuclear magnetic resonance, and the critical micelle concentration required for cationic micelle formation through self-assembly was determined. Subsequently, the Doxy loading efficiency of DA3 was assessed. The cytotoxicity of Doxy, DA3, PEI, and DA-Doxy in nasal fibroblasts was evaluated using the WST-1 assay. The anti-tissue remodeling and anti-inflammatory effects of DA3-Doxy and DA3 were examined using real-time polymerase chain reaction (Real-time PCR), immunocytochemistry, western blot, and Sircol assay. RESULTS: Both DA3 and DA3-Doxy exhibited cytotoxicity at 10 µg/ml in nasal fibroblasts. Doxy partially inhibited α-smooth muscle actin, collagen types I and III, and fibronectin. However, DA3-Doxy significantly inhibited α-SMA, collagen types I and III, and fibronectin at 5 µg/ml. DA3-Doxy also modulated TGF-ß1-induced changes in the expression of MMP 1, 2, and 9. Nonetheless, TGF-ß1-induced expression of MMP3 was further increased by DA3-Doxy. The expression of TIMP 1 and 2 was partially reduced with 5 µg/ml DA3-Doxy. CONCLUSIONS: Although initially developed for the delivery of genetic materials or drugs, DA3 exhibits inhibitory effects on myofibroblast differentiation and ECM production. Therefore, it holds therapeutic potential for CRS, and a synergistic effect can be expected when loaded with CRS treatment drugs.

Multi-Task Heterogeneous Ensemble Learning-Based Cross-Subject EEG Classification Under Stroke Patients.

Robot-assisted motor training is applied for neurorehabilitation in stroke patients, using motor imagery (MI) as a representative paradigm of brain-computer interfaces to offer real-life assistance to individuals facing movement challenges. However, the effectiveness of training with MI may vary depending on the location of the stroke lesion, which should be considered. This paper introduces a multi-task electroencephalogram-based heterogeneous ensemble learning (MEEG-HEL) specifically designed for cross-subject training. In the proposed framework, common spatial patterns were used for feature extraction, and the features according to stroke lesions are shared and selected through sequential forward floating selection. The heterogeneous ensembles were used as classifiers. Nine patients with chronic ischemic stroke participated, engaging in MI and motor execution (ME) paradigms involving finger tapping. The classification criteria for the multi-task were established in two ways, taking into account the characteristics of stroke patients. In the cross-subject session, the first involved a direction recognition task for two-handed classification, achieving a performance of 0.7419 (±0.0811) in MI and 0.7061 (±0.1270) in ME. The second task focused on motor assessment for lesion location, resulting in a performance of 0.7457 (±0.1317) in MI and 0.6791 (±0.1253) in ME. Comparing the specific-subject session, except for ME on the motor assessment task, performance on both tasks was significantly higher than the cross-subject session. Furthermore, classification performance was similar to or statistically higher in cross-subject sessions compared to baseline models. The proposed MEEG-HEL holds promise in improving the practicality of neurorehabilitation in clinical settings and facilitating the detection of lesions.

Spectral Graph Neural Network-Based Multi-Atlas Brain Network Fusion for Major Depressive Disorder Diagnosis.

Major Depressive Disorder (MDD) imposes a substantial burden within the healthcare domain, impacting millions of individuals worldwide. Functional Magnetic Resonance Imaging (fMRI) has emerged as a promising tool for the objective diagnosis of MDD, enabling the investigation of functional connectivity patterns in the brain associated with this disorder. However, most existing methods focus on a single brain atlas, which limits their ability to capture the complex, multi-scale nature of functional brain networks. To address these limitations, we propose a novel multi-atlas fusion method that incorporates early and late fusion in a unified framework. Our method introduces the concept of the holistic Functional Connectivity Network (FCN), which captures both intra-atlas relationships within individual atlases and inter-regional relationships between atlases with different brain parcellation scales. This comprehensive representation enables the identification of potential disease-related patterns associated with MDD in the early stage of our framework. Moreover, by decoding the holistic FCN from various perspectives through multiple spectral Graph Convolutional Neural Networks and fusing their results with decision-level ensembles, we further improve the performance of MDD diagnosis. Our approach is easily implemented with minimal modifications to existing model structures and demonstrates a robust performance across different baseline models. Our method, evaluated on public resting-state fMRI datasets, surpasses the current multi-atlas fusion methods, enhancing the accuracy of MDD diagnosis. The proposed novel multi-atlas fusion framework provides a more reliable MDD diagnostic technique. Experimental results show our approach outperforms both single- and multi-atlas-based methods, demonstrating its effectiveness in advancing MDD diagnosis.

DeepHealthNet: Adolescent Obesity Prediction System Based on a Deep Learning Framework.

The global prevalence of childhood and adolescent obesity is a major concern due to its association with chronic diseases and long-term health risks. Artificial intelligence technology has been identified as a potential solution to accurately predict obesity rates and provide personalized feedback to adolescents. This study highlights the importance of early identification and prevention of obesity-related health issues. To develop effective algorithms for the prediction of obesity rates and provide personalized feedback, factors such as height, weight, waist circumference, calorie intake, physical activity levels, and other relevant health information must be taken into account. Therefore, by collecting health datasets from 321 adolescents who participated in Would You Do It! application, we proposed an adolescent obesity prediction system that provides personalized predictions and assists individuals in making informed health decisions. Our proposed deep learning framework, DeepHealthNet, effectively trains the model using data augmentation techniques, even when daily health data are limited, resulting in improved prediction accuracy (acc: 0.8842). Additionally, the study revealed variations in the prediction of the obesity rate between boys (acc: 0.9320) and girls (acc: 0.9163), allowing the identification of disparities and the determination of the optimal time to provide feedback. Statistical analysis revealed that the performance of the proposed deep learning framework was more statistically significant (p 0.001) compared to the other general models. The proposed system has the potential to effectively address childhood and adolescent obesity.

Mature microRNA-binding protein QKI promotes microRNA-mediated gene silencing.

Although Argonaute (AGO) proteins have been the focus of microRNA (miRNA) studies, we observed AGO-free mature miRNAs directly interacting with RNA-binding proteins, implying the sophisticated nature of fine-tuning gene regulation by miRNAs. To investigate microRNA-binding proteins (miRBPs) globally, we analyzed PAR-CLIP data sets to identify RBP quaking (QKI) as a novel miRBP for let-7b. Potential existence of AGO-free miRNAs were further verified by measuring miRNA levels in genetically engineered AGO-depleted human and mouse cells. We have shown that QKI regulates miRNA-mediated gene silencing at multiple steps, and collectively serves as an auxiliary factor empowering AGO2/let-7b-mediated gene silencing. Depletion of QKI decreases interaction of AGO2 with let-7b and target mRNA, consequently controlling target mRNA decay. This finding indicates that QKI is a complementary factor in miRNA-mediated mRNA decay. QKI, however, also suppresses the dissociation of let-7b from AGO2, and slows the assembly of AGO2/miRNA/target mRNA complexes at the single-molecule level. We also revealed that QKI overexpression suppresses cMYC expression at post-transcriptional level, and decreases proliferation and migration of HeLa cells, demonstrating that QKI is a tumour suppressor gene by in part augmenting let-7b activity. Our data show that QKI is a new type of RBP implicated in the versatile regulation of miRNA-mediated gene silencing.

Low-Dose Ionizing Radiation-Crosslinking Immunoprecipitation (LDIR-CLIP) Identified Irradiation-Sensitive RNAs for RNA-Binding Protein HuR-Mediated Decay.

Although ionizing radiation (IR) is widely used for therapeutic and research purposes, studies on low-dose ionizing radiation (LDIR) are limited compared with those on other IR approaches, such as high-dose gamma irradiation and ultraviolet irradiation. High-dose IR affects DNA damage response and nucleotide-protein crosslinking, among other processes; however, the molecular consequences of LDIR have been poorly investigated. Here, we developed a method to profile RNA species crosslinked to an RNA-binding protein, namely, human antigen R (HuR), using LDIR and high-throughput RNA sequencing. The RNA fragments isolated via LDIR-crosslinking and immunoprecipitation sequencing were crosslinked to HuR and protected from RNase-mediated digestion. Upon crosslinking HuR to target mRNAs such as PAX6, ZFP91, NR2F6, and CAND2, the transcripts degraded rapidly in human cell lines. Additionally, PAX6 and NR2F6 downregulation mediated the beneficial effects of LDIR on cell viability. Thus, our approach provides a method for investigating post-transcriptional gene regulation using LDIR.

Changes in socioeconomic status and patient outcomes in kidney transplantation recipients in South Korea.

Background: Socioeconomic status is an important factor affecting the accessibility and prognosis of kidney transplantation. We aimed to investigate changes in kidney transplant recipients' socioeconomic status in South Korea and whether such changes were associated with patient prognosis. Methods: This retrospective nationwide observational cohort study in South Korea included kidney transplant recipients between 2007 and 2016. South Korea provides a single-insurer health insurance service, and information on the socioeconomic status of the recipients is identifiable through the claims database. First, a generalized linear mixed model was used to investigate changes in recipients' socioeconomic status as an outcome. Second, the risk of graft failure was analyzed using Cox regression as another outcome to investigate whether changes in socioeconomic status were associated with patient prognosis. Results: Among the 15,215 kidney transplant recipients included in the study, economic levels (defined based on insurance fee percentiles) and employment rates declined within the first 2 years after transplantation. Beyond 2 years, the employment rate increased significantly, while no significant changes were observed in economic status. Patients whose economic status did not improve 3 years after kidney transplantation showed a higher risk of death than those whose status improved. When compared to those who remained employed after kidney transplantation, unemployment was associated with a significantly higher risk of death-censored graft failure. Conclusions: The socioeconomic status of kidney transplant recipients changed dynamically after kidney transplantation, and these changes were associated with patient prognosis.

ZBTB7A suppresses glioblastoma tumorigenesis through the transcriptional repression of EPB41L5.

Glioblastoma multiforme (GBM), the most aggressive and malignant glioma, has a poor prognosis. Although patients with GBM are treated with surgery, chemotherapy, and radiation therapy, GBM is highly resistant to treatment, making it difficult and expensive to treat. In this study, we analyzed the Gene Expression Profiling Interactive Analysis dataset, the Cancer Genome Atlas dataset, and Gene Expression Omnibus array data. ZBTB7A (also called FBI1/POKEMON/LRF) was found to be highly expressed in low-grade glioma but significantly downregulated in patients with GBM. ZBTB7A is a transcription factor that plays an important role in many developmental stages, including cell proliferation. The activation of epithelial-mesenchymal transition (EMT) is a key process in cancer progression and metastasis. Erythrocyte membrane protein band 4.1 like 5 (EPB41L5) is an essential protein for EMT progression and metastasis in various types of cancer. We found that ZBTB7A depletion in U87 cells induced GBM progression and metastasis. Based on RNA sequencing data, ZBTB7A directly binds to the promoter of the EPB41L5 gene, reducing its expression and inhibiting GBM progression. We demonstrated that ZBTB7A dramatically inhibits GBM tumor growth through transcriptional repression of EPB41L5. Thus, both ZBTB7A and EPB41L5 may be potential biomarkers and novel therapeutic targets for GBM treatment. Overall, we discovered the role of a novel tumor suppressor that directly inhibits GBM progression (ZBTB7A) and identified EPB41L5 as a therapeutic target protein for patients with GBM.

Real-Time Deep Neurolinguistic Learning Enhances Noninvasive Neural Language Decoding for Brain-Machine Interaction.

Electroencephalogram (EEG)-based brain-machine interface (BMI) has been utilized to help patients regain motor function and has recently been validated for its use in healthy people because of its ability to directly decipher human intentions. In particular, neurolinguistic research using EEGs has been investigated as an intuitive and naturalistic communication tool between humans and machines. In this study, the human mind directly decoded the neural languages based on speech imagery using the proposed deep neurolinguistic learning. Through real-time experiments, we evaluated whether BMI-based cooperative tasks between multiple users could be accomplished using a variety of neural languages. We successfully demonstrated a BMI system that allows a variety of scenarios, such as essential activity, collaborative play, and emotional interaction. This outcome presents a novel BMI frontier that can interact at the level of human-like intelligence in real time and extends the boundaries of the communication paradigm.

Prototype-based Domain Generalization Framework for Subject-Independent Brain-Computer Interfaces.

Brain-computer interface (BCI) is challenging to use in practice due to the inter/intra-subject variability of electroencephalography (EEG). The BCI system, in general, necessitates a calibration technique to obtain subject/session-specific data in order to tune the model each time the system is utilized. This issue is acknowledged as a key hindrance to BCI, and a new strategy based on domain generalization has recently evolved to address it. In light of this, we've concentrated on developing an EEG classification framework that can be applied directly to data from unknown domains (i.e. subjects), using only data acquired from separate subjects previously. For this purpose, in this paper, we proposed a framework that employs the open-set recognition technique as an auxiliary task to learn subject-specific style features from the source dataset while helping the shared feature extractor with mapping the features of the unseen target dataset as a new unseen domain. Our aim is to impose cross-instance style in-variance in the same domain and reduce the open space risk on the potential unseen subject in order to improve the generalization ability of the shared feature extractor. Our experiments showed that using the domain information as an auxiliary network increases the generalization performance. Clinical relevance-This study suggests a strategy to improve the performance of the subject-independent BCI systems. Our framework can help to reduce the need for further calibration and can be utilized for a range of mental state monitoring tasks (e.g. neurofeedback, identification of epileptic seizures, and sleep disorders).

2020 International brain-computer interface competition: A review.

The brain-computer interface (BCI) has been investigated as a form of communication tool between the brain and external devices. BCIs have been extended beyond communication and control over the years. The 2020 international BCI competition aimed to provide high-quality neuroscientific data for open access that could be used to evaluate the current degree of technical advances in BCI. Although there are a variety of remaining challenges for future BCI advances, we discuss some of more recent application directions: (i) few-shot EEG learning, (ii) micro-sleep detection (iii) imagined speech decoding, (iv) cross-session classification, and (v) EEG(+ear-EEG) detection in an ambulatory environment. Not only did scientists from the BCI field compete, but scholars with a broad variety of backgrounds and nationalities participated in the competition to address these challenges. Each dataset was prepared and separated into three data that were released to the competitors in the form of training and validation sets followed by a test set. Remarkable BCI advances were identified through the 2020 competition and indicated some trends of interest to BCI researchers.

Mathematical modeling of dark fermentation of macroalgae for hydrogen and volatile fatty acids production.

A mathematical model of H2 and volatile fatty acids (VFAs) production via dark fermentation of particulate macroalgal substrates is presented. Carbohydrates, proteins, and lipids in the particulate substrate are convert to H2, CO2, and VFAs via disintegration/solubilization, hydrolysis, and acidogenesis. Hydrolysis is modeled using a combined surface-limiting model combined with a first-order reaction model to describe both microbial hydrolysis and physical solubilization. Experimental and published data obtained using Saccharina japonica as the substrate are used to calibrate and validate the model. The model prediction featured a good accuracy, with high R2 of 0.912 - 0.976 for all end products. The physical solubilisation accounts for 28.4% of the total hydrolysis. By the model simulation, a H2 production of 103.2 mL/g-VS and VFA production of 0.41 g/g-VS are found at optimum conditions of 20 g-TS/L (13.2 g-VS/L) of substrate concentration and 7.0 of initial pH.

miR-3189-targeted GLUT3 repression by HDAC2 knockdown inhibits glioblastoma tumorigenesis through regulating glucose metabolism and proliferation.

BACKGROUND: Epigenetic regulations frequently appear in Glioblastoma (GBM) and are highly associated with metabolic alterations. Especially, Histone deacetylases (HDACs) correlates with the regulation of tumorigenesis and cell metabolism in GBM progression, and HDAC inhibitors report to have therapeutic efficacy in GBM and other neurological diseases; however, GBM prevention and therapy by HDAC inhibition lacks a mechanism in the focus of metabolic reprogramming. METHODS: HDAC2 highly express in GBM and is analyzed in TCGA/GEPIA databases. Therefore, HDAC2 knockdown affects GBM cell death. Analysis of RNA sequencing and qRT-PCR reveals that miR-3189 increases and GLUT3 decreases by HDAC2 knockdown. GBM tumorigenesis also examines by using in vivo orthotopic xenograft tumor models. The metabolism change in HDAC2 knockdown GBM cells measures by glucose uptake, lactate production, and OCR/ECAR analysis, indicating that HDAC2 knockdown induces GBM cell death by inhibiting GLUT3. RESULTS: Notably, GLUT3 was suppressed by increasing miR-3189, demonstrating that miR-3189-mediated GLUT3 inhibition shows an anti-tumorigenic effect and cell death by regulating glucose metabolism in HDAC2 knockdown GBM. CONCLUSIONS: Our findings will demonstrate the central role of HDAC2 in GBM tumorigenesis through the reprogramming of glucose metabolism by controlling miR-3189-inhibited GLUT3 expression, providing a potential new therapeutic strategy for GBM treatment.

Motor Imagery Classification Using Inter-Task Transfer Learning via a Channel-Wise Variational Autoencoder-Based Convolutional Neural Network.

Highly sophisticated control based on a brain-computer interface (BCI) requires decoding kinematic information from brain signals. The forearm is a region of the upper limb that is often used in everyday life, but intuitive movements within the same limb have rarely been investigated in previous BCI studies. In this study, we focused on various forearm movement decoding from electroencephalography (EEG) signals using a small number of samples. Ten healthy participants took part in an experiment and performed motor execution (ME) and motor imagery (MI) of the intuitive movement tasks (Dataset I). We propose a convolutional neural network using a channel-wise variational autoencoder (CVNet) based on inter-task transfer learning. We approached that training the reconstructed ME-EEG signals together will also achieve more sufficient classification performance with only a small amount of MI-EEG signals. The proposed CVNet was validated on our own Dataset I and a public dataset, BNCI Horizon 2020 (Dataset II). The classification accuracies of various movements are confirmed to be 0.83 (±0.04) and 0.69 (±0.04) for Dataset I and II, respectively. The results show that the proposed method exhibits performance increases of approximately 0.09~0.27 and 0.08~0.24 compared with the conventional models for Dataset I and II, respectively. The outcomes suggest that the training model for decoding imagined movements can be performed using data from ME and a small number of data samples from MI. Hence, it is presented the feasibility of BCI learning strategies that can sufficiently learn deep learning with a few amount of calibration dataset and time only, with stable performance.

Multiscale Convolutional Transformer for EEG Classification of Mental Imagery in Different Modalities.

A new kind of sequence-to-sequence model called a transformer has been applied to electroencephalogram (EEG) systems. However, the majority of EEG-based transformer models have applied attention mechanisms to the temporal domain, while the connectivity between brain regions and the relationship between different frequencies have been neglected. In addition, many related studies on imagery-based brain-computer interface (BCI) have been limited to classifying EEG signals within one type of imagery. Therefore, it is important to develop a general model to learn various types of neural representations. In this study, we designed an experimental paradigm based on motor imagery, visual imagery, and speech imagery tasks to interpret the neural representations during mental imagery in different modalities. We conducted EEG source localization to investigate the brain networks. In addition, we propose the multiscale convolutional transformer for decoding mental imagery, which applies multi-head attention over the spatial, spectral, and temporal domains. The proposed network shows promising performance with 0.62, 0.70, and 0.72 mental imagery accuracy with the private EEG dataset, BCI competition IV 2a dataset, and Arizona State University dataset, respectively, as compared to the conventional deep learning models. Hence, we believe that it will contribute significantly to overcoming the limited number of classes and low classification performances in the BCI system.

NeuroGrasp: Real-Time EEG Classification of High-Level Motor Imagery Tasks Using a Dual-Stage Deep Learning Framework.

Brain-computer interfaces (BCIs) have been widely employed to identify and estimate a user's intention to trigger a robotic device by decoding motor imagery (MI) from an electroencephalogram (EEG). However, developing a BCI system driven by MI related to natural hand-grasp tasks is challenging due to its high complexity. Although numerous BCI studies have successfully decoded large body parts, such as the movement intention of both hands, arms, or legs, research on MI decoding of high-level behaviors such as hand grasping is essential to further expand the versatility of MI-based BCIs. In this study, we propose NeuroGrasp, a dual-stage deep learning framework that decodes multiple hand grasping from EEG signals under the MI paradigm. The proposed method effectively uses an EEG and electromyography (EMG)-based learning, such that EEG-based inference at test phase becomes possible. The EMG guidance during model training allows BCIs to predict hand grasp types from EEG signals accurately. Consequently, NeuroGrasp improved classification performance offline, and demonstrated a stable classification performance online. Across 12 subjects, we obtained an average offline classification accuracy of 0.68 (±0.09) in four-grasp-type classifications and 0.86 (±0.04) in two-grasp category classifications. In addition, we obtained an average online classification accuracy of 0.65 (±0.09) and 0.79 (±0.09) across six high-performance subjects. Because the proposed method has demonstrated a stable classification performance when evaluated either online or offline, in the future, we expect that the proposed method could contribute to different BCI applications, including robotic hands or neuroprosthetics for handling everyday objects.

Endoplasmic reticulum stress increases LECT2 expression via ATF4.

Non-alcoholic fatty liver disease (NAFLD) is frequently associated with obesity, insulin resistance, and endoplasmic reticulum (ER) stress. Elevated circulating levels of the hepatokine leukocyte cell-derived chemotaxin-2 (LECT2) have also been noted in NAFLD; however, the mechanism underlying this association is unclear. To investigate a possible link between ER stress/unfolded protein response (UPR) signaling and LECT2 secretion, HepG2 cells were incubated with ER stress inducers with or without an ER stress-reducing chemical chaperone. Additionally, UPR pathway genes were knocked down and overexpressed, and a ChIP assay was performed. In diet-induced obese mice, hepatic expression of LECT2 and activating transcription factor 4 (ATF4) was measured. In HepG2 cells, LECT2 expression was increased by ER stressors, an effect blocked by the chemical chaperone. Among UPR pathway proteins, only knockdown of ATF4 suppressed ER stress-induced LECT2 expression, while overexpression of ATF4 enhanced LECT2 expression. The ChIP assay revealed that ATF4 binds to three putative binding sites on the LECT2 promoter and binding is promoted by an ER stress inducer. In steatotic livers of obese mice, LECT2 and ATF4 expression was concomitantly elevated. Our data indicate that activation of ER stress/UPR signaling induces LECT2 expression in steatotic liver; specifically, ATF4 appears to mediate upregulation of LECT2 transcription.