Search

High-grade serous ovarian cancer has a high degree of malignancy, and at detection, it is prone to infiltration of surrounding soft tissues, as well as metastasis to the peritoneum and lymph nodes, peritoneal seeding, and distant metastasis. Whether recurrence occurs becomes an important reference for surgical planning and treatment methods for this disease. Current recurrence prediction models do not consider the potential pathological relationships between internal tissues of the entire ovary. They use convolutional neural networks to extract local region features for judgment, but the accuracy is low, and the cost is high. To address this issue, this paper proposes a new lightweight deep learning algorithm model for predicting recurrence of high-grade serous ovarian cancer. The model first uses ghost convolution (Ghost Conv) and coordinate attention (CA) to establish ghost counter residual (SCblock) modules to extract local feature information from images. Then, it captures global information and integrates multi-level information through proposed layered fusion Transformer (STblock) modules to enhance interaction between different layers. The Transformer module unfolds the feature map to compute corresponding region blocks, then folds it back to reduce computational cost. Finally, each STblock module fuses deep and shallow layer depth information and incorporates patient's clinical metadata for recurrence prediction. Experimental results show that compared to the mainstream lightweight mobile visual Transformer (MobileViT) network, the proposed slicer visual Transformer (SlicerViT) network improves accuracy, precision, sensitivity, and F1 score, with only 1/6 of the computational cost and half the parameter count. This research confirms that the proposed algorithm model is more accurate and efficient in predicting recurrence of high-grade serous ovarian cancer. In the future, it can serve as an auxiliary diagnostic technique to improve patient survival rates and facilitate the application of the model in embedded devices.

Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor's diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.

Hydrogel is a kind of degradable hydrophilic polymer, but excessive hydrophilicity leads to larger volume, lower elastic modulus and looser structure, which further affect its use. Especially in the field of biomedical engineering, excessive swelling of the hydrogel can compress the nerves and improve degradation rate resulting in mismatch of tissue growth and released ions. Therefore, anti-swelling hydrogel has been a research hotspot in recent years. This paper reviews the recent research progress on anti-swelling hydrogel, and expounds the application mechanism and preparation method of hydrogel in biomedical engineering, aiming to provide some references for researchers in the field of anti-swelling hydrogel.

The performance of a pulse oximeter based on photoelectric detection is greatly affected by motion noise (MA) in the photoplethysmographic (PPG) signal. This paper presents an algorithm for detecting motion oxygen saturation, which reconstructs a motion noise reference signal using ensemble of complete adaptive noise and empirical mode decomposition combined with multi-scale permutation entropy, and eliminates MA in the PPG signal using a convex combination least mean square adaptive filters to calculate dynamic oxygen saturation. The test results show that, under simulated walking and jogging conditions, the mean absolute error (MAE) of oxygen saturation estimated by the proposed algorithm and the reference oxygen saturation are 0.05 and 0.07, respectively, with means absolute percentage error (MAPE) of 0.05% and 0.07%, respectively. The overall Pearson correlation coefficient reaches 0.971 2. The proposed scheme effectively reduces motion artifacts in the corrupted PPG signal and is expected to be applied in portable photoelectric pulse oximeters to improve the accuracy of dynamic oxygen saturation measurement.

The establishment of brain metabolic network is based on 18 fluoro-deoxyglucose positron emission computed tomography ( 18 F-FDG PET) analysis, which reflect the brain functional network connectivity in normal physiological state or disease state. It is now applied to basic and clinical brain functional network research. In this paper, we constructed a metabolic network for the cerebral cortex firstly according to 18 F-FDG PET image data from patients with temporal lobe epilepsy (TLE).Then, a statistical analysis to the network properties of patients with left or right TLE and controls was performed. It is shown that the connectivity of the brain metabolic network is weakened in patients with TLE, the topology of the network is changed and the transmission efficiency of the network is reduced, which means the brain metabolic network connectivity is extensively impaired in patients with TLE. It is confirmed that the brain metabolic network analysis based on 18 F-FDG PET can provide a new perspective for the diagnose and therapy of epilepsy by utilizing PET images.

Sudden cardiac arrest (SCA) is a lethal cardiac arrhythmia that poses a serious threat to human life and health. However, clinical records of sudden cardiac death (SCD) electrocardiogram (ECG) data are extremely limited. This paper proposes an early prediction and classification algorithm for SCA based on deep transfer learning. With limited ECG data, it extracts heart rate variability features before the onset of SCA and utilizes a lightweight convolutional neural network model for pre-training and fine-tuning in two stages of deep transfer learning. This achieves early classification, recognition and prediction of high-risk ECG signals for SCA by neural network models. Based on 16 788 30-second heart rate feature segments from 20 SCA patients and 18 sinus rhythm patients in the international publicly available ECG database, the algorithm performance evaluation through ten-fold cross-validation shows that the average accuracy (Acc), sensitivity (Sen), and specificity (Spe) for predicting the onset of SCA in the 30 minutes prior to the event are 91.79%, 87.00%, and 96.63%, respectively. The average estimation accuracy for different patients reaches 96.58%. Compared to traditional machine learning algorithms reported in existing literatures, the method proposed in this paper helps address the requirement of large training datasets for deep learning models and enables early and accurate detection and identification of high-risk ECG signs before the onset of SCA.

Brain-computer interface (BCI) based on steady-state visual evoked potential (SSVEP) have attracted much attention in the field of intelligent robotics. Traditional SSVEP-based BCI systems mostly use synchronized triggers without identifying whether the user is in the control or non-control state, resulting in a system that lacks autonomous control capability. Therefore, this paper proposed a SSVEP asynchronous state recognition method, which constructs an asynchronous state recognition model by fusing multiple time-frequency domain features of electroencephalographic (EEG) signals and combining with a linear discriminant analysis (LDA) to improve the accuracy of SSVEP asynchronous state recognition. Furthermore, addressing the control needs of disabled individuals in multitasking scenarios, a brain-machine fusion system based on SSVEP-BCI asynchronous cooperative control was developed. This system enabled the collaborative control of wearable manipulator and robotic arm, where the robotic arm acts as a "third hand", offering significant advantages in complex environments. The experimental results showed that using the SSVEP asynchronous control algorithm and brain-computer fusion system proposed in this paper could assist users to complete multitasking cooperative operations. The average accuracy of user intent recognition in online control experiments was 93.0%, which provides a theoretical and practical basis for the practical application of the asynchronous SSVEP-BCI system.

With the development of brain-computer interface (BCI) technology and its translational application in clinical medicine, BCI medicine has emerged, ushering in profound changes to the practice of medicine, while also bringing forth a series of ethical issues related to BCI medicine. BCI medicine is progressively emerging as a new disciplinary focus, yet to date, there has been limited literature discussing it. Therefore, this paper focuses on BCI medicine, firstly providing an overview of the main potential medical applications of BCI technology. It then defines the discipline, outlines its objectives, methodologies, potential efficacy, and associated translational medical research. Additionally, it discusses the ethics associated with BCI medicine, and introduces the standardized operational procedures for BCI medical applications and the methods for evaluating the efficacy of BCI medical applications. Finally, it anticipates the challenges and future directions of BCI medicine. In the future, BCI medicine may become a new academic discipline or major in higher education. In summary, this article is hoped to provide thoughts and references for the development of the discipline of BCI medicine.

Colorectal cancer (CRC) is a common malignant tumor that seriously threatens human health. CRC presents a formidable challenge in terms of accurate identification due to its indistinct boundaries. With the widespread adoption of convolutional neural networks (CNNs) in image processing, leveraging CNNs for automatic classification and segmentation holds immense potential for enhancing the efficiency of colorectal cancer recognition and reducing treatment costs. This paper explores the imperative necessity for applying CNNs in clinical diagnosis of CRC. It provides an elaborate overview on research advancements pertaining to CNNs and their improved models in CRC classification and segmentation. Furthermore, this work summarizes the ideas and common methods for optimizing network performance and discusses the challenges faced by CNNs as well as future development trends in their application towards CRC classification and segmentation, thereby promoting their utilization within clinical diagnosis.

To address the conflict between the "fitness" and "feasibility" of body-fitted stents, this paper investigates the impact of various smoothing design strategies on the mechanical behaviour and apposition performance of stent. Based on the three-dimensional projection method, the projection region was fitted with the least squares method (fitting orders 1-6 corresponded to models 1-6, respectively) to achieve the effect of smoothing the body-fitted stent. The simulation included the crimping and expansion process of six groups of stents in stenotic vessels with different degrees of plaque calcification. Various metrics were analyzed, including bending stiffness, stent ruggedness, area residual stenosis rate, contact area fraction, and contact volume fraction. The study findings showed that the bending stiffness, stent ruggedness, area residual stenosis rate, contact area fraction and contact volume fraction increased with the fitting order's increase. Model 1 had the smallest contact area fraction and contact volume fraction, 77.63% and 83.49% respectively, in the incompletely calcified plaque environment. In the completely calcified plaque environment, these values were 72.86% and 82.21%, respectively. Additionally, it had the worst "fitness". Models 5 and 6 had similar values for stent ruggedness, with 32.15% and 32.38%, respectively, which indicated the worst "feasibility" for fabrication and implantation. Models 2, 3, and 4 had similar area residual stenosis rates in both plaque environments. In conclusion, it is more reasonable to obtain the body-fitted stent by using 2nd to 4th order fitting with the least squares method to the projected region. Among them, the body-fitted stent obtained by the 2nd order fitting performs better in the completely calcified environment.

Transcranial electrical stimulation (TES) is a non-invasive neuromodulation technique with great potential. Electrode optimization methods based on simulation models of individual TES field could provide personalized stimulation parameters according to individual variations in head tissue structure, significantly enhancing the stimulation accuracy of TES. However, the existing electrode optimization methods suffer from prolonged computation times (typically exceeding 1 d) and limitations such as disregarding the restricted number of output channels from the stimulator, further impeding their clinical applicability. Hence, this paper proposes an efficient and practical electrode optimization method. The proposed method simultaneously optimizes both the intensity and focality of TES within the target brain area while constraining the number of electrodes used, and it achieves faster computational speed. Compared to commonly used electrode optimization methods, the proposed method significantly reduces computation time by 85.9% while maintaining optimization effectiveness. Moreover, our method considered the number of available channels for the stimulator to distribute the current across multiple electrodes, further improving the tolerability of TES. The electrode optimization method proposed in this paper has the characteristics of high efficiency and easy operation, potentially providing valuable supporting data and references for the implementation of individualized TES.

Stroke is an acute cerebrovascular disease in which sudden interruption of blood supply to the brain or rupture of cerebral blood vessels cause damage to brain cells and consequently impair the patient's motor and cognitive abilities. A novel rehabilitation training model integrating brain-computer interface (BCI) and virtual reality (VR) not only promotes the functional activation of brain networks, but also provides immersive and interesting contextual feedback for patients. In this paper, we designed a hand rehabilitation training system integrating multi-sensory stimulation feedback, BCI and VR, which guides patients' motor imaginations through the tasks of the virtual scene, acquires patients' motor intentions, and then carries out human-computer interactions under the virtual scene. At the same time, haptic feedback is incorporated to further increase the patients' proprioceptive sensations, so as to realize the hand function rehabilitation training based on the multi-sensory stimulation feedback of vision, hearing, and haptic senses. In this study, we compared and analyzed the differences in power spectral density of different frequency bands within the EEG signal data before and after the incorporation of haptic feedback, and found that the motor brain area was significantly activated after the incorporation of haptic feedback, and the power spectral density of the motor brain area was significantly increased in the high gamma frequency band. The results of this study indicate that the rehabilitation training of patients with the VR-BCI hand function enhancement rehabilitation system incorporating multi-sensory stimulation can accelerate the two-way facilitation of sensory and motor conduction pathways, thus accelerating the rehabilitation process.

Slow wound healing has been a troublesome problem in clinic. In China, traditional methods such as antibiotics and silver sulfadiazine are used to treat skin wound, but the abuse use has many disadvantages, such as chronic wounds and pathogen resistance. Studies have shown that the microorganisms with symbiotic relationship with organisms have benefits on skin wound. Therefore, the way to develop and utilize probiotics to promote wound healing has become a new research direction. In this paper, we reviewed the studies on the bacteriotherapy in the world, described how the probiotics can play a role in promoting wound healing through local wound and intestine, and introduced some mature probiotics products and clinical trials, aiming to provide foundations for further development of bacteriotherapy and products.

In response to the issues of single-scale information loss and large model parameter size during the sampling process in U-Net and its variants for medical image segmentation, this paper proposes a multi-scale medical image segmentation method based on pixel encoding and spatial attention. Firstly, by redesigning the input strategy of the Transformer structure, a pixel encoding module is introduced to enable the model to extract global semantic information from multi-scale image features, obtaining richer feature information. Additionally, deformable convolutions are incorporated into the Transformer module to accelerate convergence speed and improve module performance. Secondly, a spatial attention module with residual connections is introduced to allow the model to focus on the foreground information of the fused feature maps. Finally, through ablation experiments, the network is lightweighted to enhance segmentation accuracy and accelerate model convergence. The proposed algorithm achieves satisfactory results on the Synapse dataset, an official public dataset for multi-organ segmentation provided by the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), with Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) scores of 77.65 and 18.34, respectively. The experimental results demonstrate that the proposed algorithm can enhance multi-organ segmentation performance, potentially filling the gap in multi-scale medical image segmentation algorithms, and providing assistance for professional physicians in diagnosis.

There are some problems in positron emission tomography/ computed tomography (PET/CT) lung images, such as little information of feature pixels in lesion regions, complex and diverse shapes, and blurred boundaries between lesions and surrounding tissues, which lead to inadequate extraction of tumor lesion features by the model. To solve the above problems, this paper proposes a dense interactive feature fusion Mask RCNN (DIF-Mask RCNN) model. Firstly, a feature extraction network with cross-scale backbone and auxiliary structures was designed to extract the features of lesions at different scales. Then, a dense interactive feature enhancement network was designed to enhance the lesion detail information in the deep feature map by interactively fusing the shallowest lesion features with neighboring features and current features in the form of dense connections. Finally, a dense interactive feature fusion feature pyramid network (FPN) network was constructed, and the shallow information was added to the deep features one by one in the bottom-up path with dense connections to further enhance the model's perception of weak features in the lesion region. The ablation and comparison experiments were conducted on the clinical PET/CT lung image dataset. The results showed that the APdet, APseg, APdet_s and APseg_s indexes of the proposed model were 67.16%, 68.12%, 34.97% and 37.68%, respectively. Compared with Mask RCNN (ResNet50), APdet and APseg indexes increased by 7.11% and 5.14%, respectively. DIF-Mask RCNN model can effectively detect and segment tumor lesions. It provides important reference value and evaluation basis for computer-aided diagnosis of lung cancer.

The simultaneous objectives of destroying tumor cells while protecting normal pelvic organs present a dual clinical and technical challenge within the realm of pelvic tumor radiotherapy. This article reviews the latest literatures, focusing on technological innovations in key aspects of radiotherapy such as positioning, planning, and delivery. These include positioning fixation techniques, organ-at-risk avoidance irradiation, non-coplanar irradiation techniques, as well as organ displacement protection and image-guided adaptive techniques. It summarizes and discusses the research progress made in the protection of critical organs during pelvic tumor radiotherapy. The paper emphasizes technological advancements in the protection of critical organs throughout the processes of radiotherapy positioning, planning, and implementation, aiming to provide references for further research on the protection of critical organs in the external irradiation treatment of pelvic tumors.

In the extraction of fetal electrocardiogram (ECG) signal, due to the unicity of the scale of the U-Net same-level convolution encoder, the size and shape difference of the ECG characteristic wave between mother and fetus are ignored, and the time information of ECG signals is not used in the threshold learning process of the encoder's residual shrinkage module. In this paper, a method of extracting fetal ECG signal based on multi-scale residual shrinkage U-Net model is proposed. First, the Inception and time domain attention were introduced into the residual shrinkage module to enhance the multi-scale feature extraction ability of the same level convolution encoder and the utilization of the time domain information of fetal ECG signal. In order to maintain more local details of ECG waveform, the maximum pooling in U-Net was replaced by Softpool. Finally, the decoder composed of the residual module and up-sampling gradually generated fetal ECG signals. In this paper, clinical ECG signals were used for experiments. The final results showed that compared with other fetal ECG extraction algorithms, the method proposed in this paper could extract clearer fetal ECG signals. The sensitivity, positive predictive value, and F1 scores in the 2013 competition data set reached 93.33%, 99.36%, and 96.09%, respectively, indicating that this method can effectively extract fetal ECG signals and has certain application values for perinatal fetal health monitoring.

Triply periodic minimal surface (TPMS) is widely used because it can be used to control the shape of porous scaffolds precisely by formula. In this paper, an I-wrapped package (I-WP) type porous scaffolds were constructed. The finite element method was used to study the relationship between the wall thickness and period, the morphology and mechanical properties of the scaffolds, as well as to study the compression and fluid properties. It was found that the porosity of I-WP type scaffolds with different wall thicknesses (0.1 ~ 0.2 mm) and periods (I-WP 1 ~ I-WP 5) ranged from 68.01% ~ 96.48%, and the equivalent elastic modulus ranged from 0.655 ~ 18.602 GPa; the stress distribution of the scaffolds tended to be uniform with the increase of periods and wall thicknesses; the equivalent elastic modulus of the I-WP type scaffolds was basically unchanged after the topology optimization, and the permeability was improved by 52.3%. In conclusion, for the I-WP type scaffolds, the period parameter can be adjusted first, then the wall thickness parameter can be controlled. Topology optimization can be combined to meet the design requirements. The I-WP scaffolds constructed in this paper have good mechanical properties and meet the requirements of repairing human bone tissue, which may provide a new choice for the design of artificial bone trabecular scaffolds.

This paper investigates the variation of lung tissue dielectric properties with tidal volume under in vivo conditions to provide reliable and valid a priori information for techniques such as microwave imaging. In this study, the dielectric properties of the lung tissue of 30 rabbits were measured in vivo using the open-end coaxial probe method in the frequency band of 100 MHz to 1 GHz, and 6 different sets of tidal volumes (30, 40, 50, 60, 70, 80 mL) were set up to study the trends of the dielectric properties, and the data at 2 specific frequency points (433 and 915 MHz) were analyzed statistically. It was found that the dielectric coefficient and conductivity of lung tissue tended to decrease with increasing tidal volume in the frequency range of 100 MHz to 1 GHz, and the differences in the dielectric properties of lung tissue for the 6 groups of tidal volumes at 2 specific frequency points were statistically significant. This paper showed that the dielectric properties of lung tissue tend to vary non-linearly with increasing tidal volume. Based on this, more accurate biological tissue parameters can be provided for bioelectromagnetic imaging techniques such as microwave imaging, which could provide a scientific basis and experimental data support for the improvement of diagnostic methods and equipment for lung diseases.

Accurately evaluating the local biomechanics of arterial wall is crucial for diagnosing and treating arterial diseases. Indentation measurement can be used to evaluate the local mechanical properties of the artery. However, the effects of the indenter's geometric structure and the analysis theory on measurement results remain uncertain. In this paper, four kinds of indenters were used to measure the pulmonary aorta, the proximal thoracic aorta and the distal thoracic aorta in pigs, and the arterial elastic modulus was calculated by Sneddon and Sirghi theory to explore the influence of the indenter geometry and analysis theory on the measured elastic modulus. The results showed that the arterial elastic modulus measured by cylindrical indenter was lower than that measured by spherical indenter. In addition, compared with the calculated results of Sirghi theory, the Sneddon theory, which does not take adhesion forces in account, resulted in slightly larger elastic modulus values. In conclusion, this study provides parametric support for effective measurement of arterial local mechanical properties by millimeter indentation technique.

The rapid development of high-throughput chromatin conformation capture (Hi-C) technology provides rich genomic interaction data between chromosomal loci for chromatin structure analysis. However, existing methods for identifying topologically associated domains (TADs) based on Hi-C data suffer from low accuracy and sensitivity to parameters. In this context, a TAD identification method based on spatial density clustering was designed and implemented in this paper. The method preprocessed the raw Hi-C data to obtain normalized Hi-C contact matrix data. Then, it computed the distance matrix between loci, generated a reachability graph based on the core distance and reachability distance of loci, and extracted clustering clusters. Finally, it extracted TAD boundaries based on clustering results. This method could identify TAD structures with higher coherence, and TAD boundaries were enriched with more ChIP-seq factors. Experimental results demonstrate that our method has advantages such as higher accuracy and practical significance in TAD identification.

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder. Due to the subtlety of symptoms in the early stages of AD, rapid and accurate clinical diagnosis is challenging, leading to a high rate of misdiagnosis. Current research on early diagnosis of AD has not sufficiently focused on tracking the progression of the disease over an extended period in subjects. To address this issue, this paper proposes an ensemble model for assisting early diagnosis of AD that combines structural magnetic resonance imaging (sMRI) data from two time points with clinical information. The model employs a three-dimensional convolutional neural network (3DCNN) and twin neural network modules to extract features from the sMRI data of subjects at two time points, while a multi-layer perceptron (MLP) is used to model the clinical information of the subjects. The objective is to extract AD-related features from the multi-modal data of the subjects as much as possible, thereby enhancing the diagnostic performance of the ensemble model. Experimental results show that based on this model, the classification accuracy rate is 89% for differentiating AD patients from normal controls (NC), 88% for differentiating mild cognitive impairment converting to AD (MCIc) from NC, and 69% for distinguishing non-converting mild cognitive impairment (MCInc) from MCIc, confirming the effectiveness and efficiency of the proposed method for early diagnosis of AD, as well as its potential to play a supportive role in the clinical diagnosis of early Alzheimer's disease.

Near-infrared fluorescence imaging technology, which possesses superior advantages including real-time and fast imaging, high spatial and temporal resolution, and deep tissue penetration, shows great potential for tumor imaging in vivo and therapy. Ⅰ-Ⅲ-Ⅵ quantum dots exhibit high brightness, broad excitation, easily tunable emission wavelength and superior stability, and do not contain highly toxic heavy metal elements such as cadmium or lead. These advantages make Ⅰ-Ⅲ-Ⅵ quantum dots attract widespread attention in biomedical field. This review summarizes the recent advances in the controlled synthesis of Ⅰ-Ⅲ-Ⅵ quantum dots and their applications in tumor imaging in vivo and therapy. Firstly, the organic-phase and aqueous-phase synthesis of Ⅰ-Ⅲ-Ⅵ quantum dots as well as the strategies for regulating the near-infrared photoluminescence are briefly introduced; secondly, representative biomedical applications of near-infrared-emitting cadmium-free quantum dots including early diagnosis of tumor, lymphatic imaging, drug delivery, photothermal and photodynamic therapy are emphatically discussed; lastly, perspectives on the future directions of developing quantum dots for biomedical application and the faced challenges are discussed. This paper may provide guidance and reference for further research and clinical translation of cadmium-free quantum dots in tumor diagnosis and treatment.

Motor imagery is often used in the fields of sports training and neurorehabilitation for its advantages of being highly targeted, easy to learn, and requiring no special equipment, and has become a major research paradigm in cognitive neuroscience. Transcranial direct current stimulation (tDCS), an emerging neuromodulation technique, modulates cortical excitability, which in turn affects functions such as locomotion. However, it is unclear whether tDCS has a positive effect on motor imagery task states. In this paper, 16 young healthy subjects were included, and the electroencephalogram (EEG) signals and near-infrared spectrum (NIRS) signals of the subjects were collected when they were performing motor imagery tasks before and after receiving tDCS, and the changes in multiscale sample entropy (MSE) and haemoglobin concentration were calculated and analyzed during the different tasks. The results found that MSE of task-related brain regions increased, oxygenated haemoglobin concentration increased, and total haemoglobin concentration rose after tDCS stimulation, indicating that tDCS increased the activation of task-related brain regions and had a positive effect on motor imagery. This study may provide some reference value for the clinical study of tDCS combined with motor imagery.

To achieve non-contact measurement of human heart rate and improve its accuracy, this paper proposes a method for measuring human heart rate based on multi-channel radar data fusion. The radar data were firstly extracted by human body position identification, phase extraction and unwinding, phase difference, band-pass filtering optimized by power spectrum entropy, and fast independent component analysis for each channel data. After overlaying and fusing the four-channel data, the heartbeat signal was separated using frost-optimized variational modal decomposition. Finally, a chirp Z-transform was introduced for heart rate estimation. After validation with 40 sets of data, the average root mean square error of the proposed method was 2.35 beats per minute, with an average error rate of 2.39%, a Pearson correlation coefficient of 0.97, a confidence interval of [-4.78, 4.78] beats per minute, and a consistency error of -0.04. The experimental results show that the proposed measurement method performs well in terms of accuracy, correlation, and consistency, enabling precise measurement of human heart rate.

Magnetic resonance imaging (MRI) plays a crucial role in the diagnosis of ischemic stroke. Accurate segmentation of the infarct is of great significance for selecting intervention treatment methods and evaluating the prognosis of patients. To address the issue of poor segmentation accuracy of existing methods for multiscale stroke lesions, a novel encoder-decoder architecture network based on depthwise separable convolution is proposed. Firstly, this network replaces the convolutional layer modules of the U-Net with redesigned depthwise separable convolution modules. Secondly, an modified Atrous spatial pyramid pooling (MASPP) is introduced to enlarge the receptive field and enhance the extraction of multiscale features. Thirdly, an attention gate (AG) structure is incorporated at the skip connections of the network to further enhance the segmentation accuracy of multiscale targets. Finally, Experimental evaluations are conducted using the ischemic stroke lesion segmentation 2022 challenge (ISLES2022) dataset. The proposed algorithm in this paper achieves Dice similarity coefficient (DSC), Hausdorff distance (HD), sensitivity (SEN), and precision (PRE) scores of 0.816 5, 3.668 1, 0.889 2, and 0.894 6, respectively, outperforming other mainstream segmentation algorithms. The experimental results demonstrate that the method in this paper effectively improves the segmentation of infarct lesions, and is expected to provide a reliable support for clinical diagnosis and treatment.

Automatic detection of pulmonary nodule based on computer tomography (CT) images can significantly improve the diagnosis and treatment of lung cancer. However, there is a lack of effective interactive tools to record the marked results of radiologists in real time and feed them back to the algorithm model for iterative optimization. This paper designed and developed an online interactive review system supporting the assisted diagnosis of lung nodules in CT images. Lung nodules were detected by the preset model and presented to doctors, who marked or corrected the lung nodules detected by the system with their professional knowledge, and then iteratively optimized the AI model with active learning strategy according to the marked results of radiologists to continuously improve the accuracy of the model. The subset 5-9 dataset of the lung nodule analysis 2016(LUNA16) was used for iteration experiments. The precision, F1-score and MioU indexes were steadily improved with the increase of the number of iterations, and the precision increased from 0.213 9 to 0.565 6. The results in this paper show that the system not only uses deep segmentation model to assist radiologists, but also optimizes the model by using radiologists' feedback information to the maximum extent, iteratively improving the accuracy of the model and better assisting radiologists.

Self-powered wearable piezoelectric sensing devices demand flexibility and high voltage electrical properties to meet personalized health and safety management needs. Aiming at the characteristics of piezoceramics with high piezoelectricity and low flexibility, this study designs a high-performance piezoelectric sensor based on multi-phase barium titanate (BTO) flexible piezoceramic film, namely multi-phase BTO sensor. The substrate-less self-supported multi-phase BTO films had excellent flexibility and could be bent 180° at a thickness of 33 μm, and exhibited good bending fatigue resistance in 1 × 10 4 bending cycles at a thickness of 5 μm. The prepared multi-phase BTO sensor could maintain good piezoelectric stability after 1.2 × 10 4 piezoelectric cycle tests. Based on the flexibility, high piezoelectricity, wearability, portability and battery-free self-powered characteristics of this sensor, the developed smart mask could monitor the respiratory signals of different frequencies and amplitudes in real time. In addition, by mounting the sensor on the hand or shoulder, different gestures and arm movements could also be detected. In summary, the multi-phase BTO sensor developed in this paper is expected to develop convenient and efficient wearable sensing devices for physiological health and behavioral activity monitoring applications.

The existing one-time identity authentication technology cannot continuously guarantee the legitimacy of user identity during the whole human-computer interaction session, and often requires active cooperation of users, which seriously limits the availability. This study proposes a new non-contact identity recognition technology based on cardiac micro-motion detection using ultra wideband (UWB) bio-radar. After the multi-point micro-motion echoes in the range dimension of the human heart surface area were continuously detected by ultra wideband bio-radar, the two-dimensional principal component analysis (2D-PCA) was exploited to extract the compressed features of the two-dimensional image matrix, namely the distance channel-heart beat sampling point (DC-HBP) matrix, in each accurate segmented heart beat cycle for identity recognition. In the practical measurement experiment, based on the proposed multi-range-bin & 2D-PCA feature scheme along with two conventional reference feature schemes, three typical classifiers were selected as representatives to conduct the heart beat identification under two states of normal breathing and breath holding. The results showed that the multi-range-bin & 2D-PCA feature scheme proposed in this paper showed the best recognition effect. Compared with the optimal range-bin & overall heart beat feature scheme, our proposed scheme held an overall average recognition accuracy of 6.16% higher (normal respiration: 6.84%; breath holding: 5.48%). Compared with the multi-distance unit & whole heart beat feature scheme, the overall average accuracy increase was 27.42% (normal respiration: 28.63%; breath holding: 26.21%) for our proposed scheme. This study is expected to provide a new method of undisturbed, all-weather, non-contact and continuous identification for authentication.

The deep learning-based automatic detection of epilepsy electroencephalogram (EEG), which can avoid the artificial influence, has attracted much attention, and its effectiveness mainly depends on the deep neural network model. In this paper, an attention-based multi-scale residual network (AMSRN) was proposed in consideration of the multiscale, spatio-temporal characteristics of epilepsy EEG and the information flow among channels, and it was combined with multiscale principal component analysis (MSPCA) to realize the automatic epilepsy detection. Firstly, MSPCA was used for noise reduction and feature enhancement of original epilepsy EEG. Then, we designed the structure and parameters of AMSRN. Among them, the attention module (AM), multiscale convolutional module (MCM), spatio-temporal feature extraction module (STFEM) and classification module (CM) were applied successively to signal reexpression with attention weighted mechanism as well as extraction, fusion and classification for multiscale and spatio-temporal features. Based on the Children's Hospital Boston-Massachusetts Institute of Technology ( CHB-MIT) public dataset, the AMSRN model achieved good results in sensitivity (98.56%), F1 score (98.35%), accuracy (98.41%) and precision (98.43%). The results show that AMSRN can make good use of brain network information flow caused by seizures to enhance the difference among channels, and effectively capture the multiscale and spatio-temporal features of EEG to improve the performance of epilepsy detection.

Computed tomography (CT) imaging is a vital tool for the diagnosis and assessment of lung adenocarcinoma, and using CT images to predict the recurrence-free survival (RFS) of lung adenocarcinoma patients post-surgery is of paramount importance in tailoring postoperative treatment plans. Addressing the challenging task of accurate RFS prediction using CT images, this paper introduces an innovative approach based on self-supervised pre-training and multi-task learning. We employed a self-supervised learning strategy known as "image transformation to image restoration" to pretrain a 3D-UNet network on publicly available lung CT datasets to extract generic visual features from lung images. Subsequently, we enhanced the network's feature extraction capability through multi-task learning involving segmentation and classification tasks, guiding the network to extract image features relevant to RFS. Additionally, we designed a multi-scale feature aggregation module to comprehensively amalgamate multi-scale image features, and ultimately predicted the RFS risk score for lung adenocarcinoma with the aid of a feed-forward neural network. The predictive performance of the proposed method was assessed by ten-fold cross-validation. The results showed that the consistency index (C-index) of the proposed method for predicting RFS and the area under curve (AUC) for predicting whether recurrence occurs within three years reached 0.691 ± 0.076 and 0.707 ± 0.082, respectively, and the predictive performance was superior to that of existing methods. This study confirms that the proposed method has the potential of RFS prediction in lung adenocarcinoma patients, which is expected to provide a reliable basis for the development of individualized treatment plans.

In this work, we investigated the influence of the bifurcation geometry of the iliac artery on the propagation properties of the pulse wave, and applied software to establish the straight bifurcation and curved bifurcation bi-directional fluid-solid coupling finite element analysis models based on the iliac artery, and compared and analyzed the influence of the bifurcation angle of the blood vessel on the propagation characteristics of the pulse wave. It was found that the bifurcation geometry had a significant effect on the pulse wave propagation in the iliac arteries, and the pressure and velocity pulse wave amplitudes predicted by these two models had a good agreement with that before the vessel bifurcation in a cardiac cycle. The curvilinear bifurcation model predicted the pulse wave amplitude to be lower and the pressure drop to be smaller after the bifurcation, which was more in line with the actual situation of the human body. In addition, the bifurcation point is accompanied by the stress concentration phenomenon in the vessel wall, and there is a transient increase in the velocity pulse waveform amplitude, which was consistent with the fact that the bifurcation site is prone to phenomena such as arterial stenosis and hardening. The preliminary results of this paper will provide some reference for the use of pulse waveforms in the diagnosis of arterial diseases.

Monitoring of bowel sounds is an important method to assess bowel motility during sleep, but it is seriously affected by snoring noise. In this paper, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method was applied to remove snoring noise from bowel sounds during sleep. Specifically, the noisy bowel sounds were first band-pass filtered, then decomposed by the CEEMDAN method, and finally the appropriate components were selected to reconstruct the pure bowel sounds. The results of semi-simulated and real data showed that the CEEMDAN method was better than empirical mode decomposition and wavelet denoising method. The CEEMDAN method is used to remove snoring noise from bowel sounds during sleep, which lays an important foundation for using bowel sounds to assess the intestinal motility during sleep.

Interventional micro-axial flow blood pump is widely used as an effective treatment for patients with cardiogenic shock. Hemolysis and coagulation are vital concerns in the clinical application of interventional micro-axial flow pumps. This paper reviewed hemolysis and coagulation models for micro-axial flow blood pumps. Firstly, the structural characteristics of commercial interventional micro-axial flow blood pumps and issues related to clinical applications were introduced. Then the basic mechanisms of hemolysis and coagulation were used to study the factors affecting erythrocyte damage and platelet activation in interventional micro-axial flow blood pumps, focusing on the current models of hemolysis and coagulation on different scales (macroscopic, mesoscopic, and microscopic). Since models at different scales have different perspectives on the study of hemolysis and coagulation, a comprehensive analysis combined with multi-scale models is required to fully consider the influence of complex factors of interventional pumps on hemolysis and coagulation.

Temporal interference (TI) as a new neuromodulation technique can be applied to non-invasive deep brain stimulation. In order to verify its effectiveness in the regulation of motor behavior in animals, this paper uses the TI method to focus the envelope electric field to the ventral posterior lateral nucleus (VPL) of the thalamus in the deep brain of mouse to regulate left- and right-turning motor behavior. The focusability of TI in the mouse VPL was analyzed by finite element method, and the focus area and volume were obtained by numerical calculation. A stimulator was used to generate TI current to stimulate the mouse VPL to verify the effectiveness of the TI stimulation method, and the accuracy of the focus location was further determined by c-Fos immunofluorescence experiments. The results showed that the electric field generated by TI stimulation was able to focus on the VPL nuclei when the stimulation current reached 800 μA; the mouse were able to make corresponding left and right turns according to the stimulation position; and the c-Fos positive cell markers in the VPL nuclei increased significantly after stimulation. This study confirms the feasibility of TI in regulating animal motor behavior and provides a non-invasive stimulation method for brain tissue for animal robots.

The PET/CT imaging technology combining positron emission tomography (PET) and computed tomography (CT) is the most advanced imaging examination method currently, and is mainly used for tumor screening, differential diagnosis of benign and malignant tumors, staging and grading. This paper proposes a method for breast cancer lesion segmentation based on PET/CT bimodal images, and designs a dual-path U-Net framework, which mainly includes three modules: encoder module, feature fusion module and decoder module. Among them, the encoder module uses traditional convolution for feature extraction of single mode image; The feature fusion module adopts collaborative learning feature fusion technology and uses Transformer to extract the global features of the fusion image; The decoder module mainly uses multi-layer perceptron to achieve lesion segmentation. This experiment uses actual clinical PET/CT data to evaluate the effectiveness of the algorithm. The experimental results show that the accuracy, recall and accuracy of breast cancer lesion segmentation are 95.67%, 97.58% and 96.16%, respectively, which are better than the baseline algorithm. Therefore, it proves the rationality of the single and bimodal feature extraction method combining convolution and Transformer in the experimental design of this article, and provides reference for feature extraction methods for tasks such as multimodal medical image segmentation or classification.

Conventional maximum intensity projection (MIP) images tend to ignore some morphological features in the detection of intracranial aneurysms, resulting in missed detection and misdetection. To solve this problem, a new method for intracranial aneurysm detection based on omni-directional MIP image is proposed in this paper. Firstly, the three-dimensional magnetic resonance angiography (MRA) images were projected with the maximum density in all directions to obtain the MIP images. Then, the region of intracranial aneurysm was prepositioned by matching filter. Finally, the Squeeze and Excitation (SE) module was used to improve the CaraNet model. Excitation and the improved model were used to detect the predetermined location in the omni-directional MIP image to determine whether there was intracranial aneurysm. In this paper, 245 cases of images were collected to test the proposed method. The results showed that the accuracy and specificity of the proposed method could reach 93.75% and 93.86%, respectively, significantly improved the detection performance of intracranial aneurysms in MIP images.

Pneumoconiosis ranks first among the newly-emerged occupational diseases reported annually in China, and imaging diagnosis is still one of the main clinical diagnostic methods. However, manual reading of films requires high level of doctors, and it is difficult to discriminate the staged diagnosis of pneumoconiosis imaging, and due to the influence of uneven distribution of medical resources and other factors, it is easy to lead to misdiagnosis and omission of diagnosis in primary healthcare institutions. Computer-aided diagnosis system can realize rapid screening of pneumoconiosis in order to assist clinicians in identification and diagnosis, and improve diagnostic efficacy. As an important branch of deep learning, convolutional neural network (CNN) is good at dealing with various visual tasks such as image segmentation, image classification, target detection and so on because of its characteristics of local association and weight sharing, and has been widely used in the field of computer-aided diagnosis of pneumoconiosis in recent years. This paper was categorized into three parts according to the main applications of CNNs (VGG, U-Net, ResNet, DenseNet, CheXNet, Inception-V3, and ShuffleNet) in the imaging diagnosis of pneumoconiosis, including CNNs in pneumoconiosis screening diagnosis, CNNs in staging diagnosis of pneumoconiosis, and CNNs in segmentation of pneumoconiosis foci to conduct a literature review. It aims to summarize the methods, advantages and disadvantages, and optimization ideas of CNN applied to the images of pneumoconiosis, and to provide a reference for the research direction of further development of computer-aided diagnosis of pneumoconiosis.

Emotion recognition refers to the process of determining and identifying an individual's current emotional state by analyzing various signals such as voice, facial expressions, and physiological indicators etc. Using electroencephalogram (EEG) signals and virtual reality (VR) technology for emotion recognition research helps to better understand human emotional changes, enabling applications in areas such as psychological therapy, education, and training to enhance people's quality of life. However, there is a lack of comprehensive review literature summarizing the combined researches of EEG signals and VR environments for emotion recognition. Therefore, this paper summarizes and synthesizes relevant research from the past five years. Firstly, it introduces the relevant theories of VR and EEG signal emotion recognition. Secondly, it focuses on the analysis of emotion induction, feature extraction, and classification methods in emotion recognition using EEG signals within VR environments. The article concludes by summarizing the research's application directions and providing an outlook on future development trends, aiming to serve as a reference for researchers in related fields.

In computer-aided medical diagnosis, obtaining labeled medical image data is expensive, while there is a high demand for model interpretability. However, most deep learning models currently require a large amount of data and lack interpretability. To address these challenges, this paper proposes a novel data augmentation method for medical image segmentation. The uniqueness and advantages of this method lie in the utilization of gradient-weighted class activation mapping to extract data efficient features, which are then fused with the original image. Subsequently, a new channel weight feature extractor is constructed to learn the weights between different channels. This approach achieves non-destructive data augmentation effects, enhancing the model's performance, data efficiency, and interpretability. Applying the method of this paper to the Hyper-Kvasir dataset, the intersection over union (IoU) and Dice of the U-net were improved, respectively; and on the ISIC-Archive dataset, the IoU and Dice of the DeepLabV3+ were also improved respectively. Furthermore, even when the training data is reduced to 70 %, the proposed method can still achieve performance that is 95 % of that achieved with the entire dataset, indicating its good data efficiency. Moreover, the data-efficient features used in the method have interpretable information built-in, which enhances the interpretability of the model. The method has excellent universality, is plug-and-play, applicable to various segmentation methods, and does not require modification of the network structure, thus it is easy to integrate into existing medical image segmentation method, enhancing the convenience of future research and applications.

The electroencephalogram (EEG) signal is the key signal carrier of the brain-computer interface (BCI) system. The EEG data collected by the whole-brain electrode arrangement is conducive to obtaining higher information representation. Personalized electrode layout, while ensuring the accuracy of EEG signal decoding, can also shorten the calibration time of BCI and has become an important research direction. This paper reviews the EEG signal channel selection methods in recent years, conducts a comparative analysis of the combined effects of different channel selection methods and different classification algorithms, obtains the commonly used channel combinations in motor imagery, P300 and other paradigms in BCI, and explains the application scenarios of the channel selection method in different paradigms are discussed, in order to provide stronger support for a more accurate and portable BCI system.

Medical image registration plays an important role in medical diagnosis and treatment planning. However, the current registration methods based on deep learning still face some challenges, such as insufficient ability to extract global information, large number of network model parameters, slow reasoning speed and so on. Therefore, this paper proposed a new model LCU-Net, which used parallel lightweight convolution to improve the ability of global information extraction. The problem of large number of network parameters and slow inference speed was solved by multi-scale fusion. The experimental results showed that the Dice coefficient of LCU-Net reached 0.823, the Hausdorff distance was 1.258, and the number of network parameters was reduced by about one quarter compared with that before multi-scale fusion. The proposed algorithm shows remarkable advantages in medical image registration tasks, and it not only surpasses the existing comparison algorithms in performance, but also has excellent generalization performance and wide application prospects.

Aiming at the status of muscle and joint damage caused on surgeons keeping surgical posture for a long time, this paper designs a medical multi-position auxiliary support exoskeleton with multi-joint mechanism by analyzing the surgical postures and conducting conformational studies on different joints respectively. Then by establishing a human-machine static model, this study obtains the joint torque and joint force before and after the human body wears the exoskeleton, and calibrates the strength of the exoskeleton with finite element analysis software. The results show that the maximum stress of the exoskeleton is less than the material strength requirements, the overall deformation is small, and the structural strength of the exoskeleton meets the use requirements. Finally, in this study, subjects were selected to participate in the plantar pressure test and biomechanical simulation with the man-machine static model, and the results were analyzed in terms of plantar pressure, joint torque and joint force, muscle force and overall muscle metabolism to assess the exoskeleton support performance. The results show that the exoskeleton has better support for the whole body and can reduce the musculoskeletal burden. The exoskeleton mechanism in this study better matches the actual working needs of surgeons and provides a new paradigm for the design of medical support exoskeleton mechanism.

Methylcellulose is a semi-flexible cellulose ether derivative, whose hydrogels are thermosensitive and reversible, with good biocompatibility and adjustable function, and its application has attracted much attention in the biomedical field. In this paper, the application of methylcellulose-based thermo-sensitive hydrogels in biomedical field was reviewed. Based on the mechanism of gelation and influencing factors of methylcellulose, this paper focused on the recent advances in biomedical applications of methylcellulose-based hydrogels, including drug delivery, regenerative medicine, and other related fields. The current achievements in these fields were summarized in the form of lists in this paper to provide ideas and tendencies for future research. Finally, the future development of multifunctional methylcellulose-based hydrogel materials with improved performance was also discussed.

The task of automatic generation of medical image reports faces various challenges, such as diverse types of diseases and a lack of professionalism and fluency in report descriptions. To address these issues, this paper proposes a multimodal medical imaging report based on memory drive method (mMIRmd). Firstly, a hierarchical vision transformer using shifted windows (Swin-Transformer) is utilized to extract multi-perspective visual features of patient medical images, and semantic features of textual medical history information are extracted using bidirectional encoder representations from transformers (BERT). Subsequently, the visual and semantic features are integrated to enhance the model's ability to recognize different disease types. Furthermore, a medical text pre-trained word vector dictionary is employed to encode labels of visual features, thereby enhancing the professionalism of the generated reports. Finally, a memory driven module is introduced in the decoder, addressing long-distance dependencies in medical image data. This study is validated on the chest X-ray dataset collected at Indiana University (IU X-Ray) and the medical information mart for intensive care chest x-ray (MIMIC-CXR) released by the Massachusetts Institute of Technology and Massachusetts General Hospital. Experimental results indicate that the proposed method can better focus on the affected areas, improve the accuracy and fluency of report generation, and assist radiologists in quickly completing medical image report writing.

Cardiac three-dimensional electrophysiological labeling technology is the prerequisite and foundation of atrial fibrillation (AF) ablation surgery, and invasive labeling is the current clinical method, but there are many shortcomings such as large trauma, long procedure duration, and low success rate. In recent years, because of its non-invasive and convenient characteristics, ex vivo labeling has become a new direction for the development of electrophysiological labeling technology. With the rapid development of computer hardware and software as well as the accumulation of clinical database, the application of deep learning technology in electrocardiogram (ECG) data is becoming more extensive and has made great progress, which provides new ideas for the research of ex vivo cardiac mapping and intelligent labeling of AF substrates. This paper reviewed the research progress in the fields of ECG forward problem, ECG inverse problem, and the application of deep learning in AF labeling, discussed the problems of ex vivo intelligent labeling of AF substrates and the possible approaches to solve them, prospected the challenges and future directions for ex vivo cardiac electrophysiology labeling.

The conventional fault diagnosis of patient monitors heavily relies on manual experience, resulting in low diagnostic efficiency and ineffective utilization of fault maintenance text data. To address these issues, this paper proposes an intelligent fault diagnosis method for patient monitors based on multi-feature text representation, improved bidirectional gate recurrent unit (BiGRU) and attention mechanism. Firstly, the fault text data was preprocessed, and the word vectors containing multiple linguistic features was generated by linguistically-motivated bidirectional encoder representation from Transformer. Then, the bidirectional fault features were extracted and weighted by the improved BiGRU and attention mechanism respectively. Finally, the weighted loss function is used to reduce the impact of class imbalance on the model. To validate the effectiveness of the proposed method, this paper uses the patient monitor fault dataset for verification, and the macro F 1 value has achieved 91.11%. The results show that the model built in this study can realize the automatic classification of fault text, and may provide assistant decision support for the intelligent fault diagnosis of the patient monitor in the future.

Physiological studies have revealed that rats perform spatial localization relying on grid cells and place cells in the entorhinal-hippocampal CA3 structure. The dynamic connection between the entorhinal-hippocampal structure and the prefrontal cortex is crucial for navigation. Based on these findings, this paper proposes a spatial navigation method based on the entorhinal-hippocampal-prefrontal information transmission circuit of the rat's brain, with the aim of endowing the mobile robot with strong spatial navigation capability. Using the hippocampal CA3-prefrontal spatial navigation model as a foundation, this paper constructed a dynamic self-organizing model with the hippocampal CA1 place cells as the basic unit to optimize the navigation path. The path information was then fed back to the impulse neural network via hippocampal CA3 place cells and prefrontal cortex action neurons, improving the convergence speed of the model and helping to establish long-term memory of navigation habits. To verify the validity of the method, two-dimensional simulation experiments and three-dimensional simulation robot experiments were designed in this paper. The experimental results showed that the method presented in this paper not only surpassed other algorithms in terms of navigation efficiency and convergence speed, but also exhibited good adaptability to dynamic navigation tasks. Furthermore, our method can be effectively applied to mobile robots.

Sleep stage classification is essential for clinical disease diagnosis and sleep quality assessment. Most of the existing methods for sleep stage classification are based on single-channel or single-modal signal, and extract features using a single-branch, deep convolutional network, which not only hinders the capture of the diversity features related to sleep and increase the computational cost, but also has a certain impact on the accuracy of sleep stage classification. To solve this problem, this paper proposes an end-to-end multi-modal physiological time-frequency feature extraction network (MTFF-Net) for accurate sleep stage classification. First, multi-modal physiological signal containing electroencephalogram (EEG), electrocardiogram (ECG), electrooculogram (EOG) and electromyogram (EMG) are converted into two-dimensional time-frequency images containing time-frequency features by using short time Fourier transform (STFT). Then, the time-frequency feature extraction network combining multi-scale EEG compact convolution network (Ms-EEGNet) and bidirectional gated recurrent units (Bi-GRU) network is used to obtain multi-scale spectral features related to sleep feature waveforms and time series features related to sleep stage transition. According to the American Academy of Sleep Medicine (AASM) EEG sleep stage classification criterion, the model achieved 84.3% accuracy in the five-classification task on the third subgroup of the Institute of Systems and Robotics of the University of Coimbra Sleep Dataset (ISRUC-S3), with 83.1% macro F1 score value and 79.8% Cohen's Kappa coefficient. The experimental results show that the proposed model achieves higher classification accuracy and promotes the application of deep learning algorithms in assisting clinical decision-making.

The pace of modern life is accelerating, the pressure of life is gradually increasing, and the long-term accumulation of mental fatigue poses a threat to health. By analyzing physiological signals and parameters, this paper proposes a method that can identify the state of mental fatigue, which helps to maintain a healthy life. The method proposed in this paper is a new recognition method of psychological fatigue state of electrocardiogram signals based on convolutional neural network and long short-term memory. Firstly, the convolution layer of one-dimensional convolutional neural network model is used to extract local features, the key information is extracted through pooling layer, and some redundant data is removed. Then, the extracted features are used as input to the long short-term memory model to further fuse the ECG features. Finally, by integrating the key information through the full connection layer, the accurate recognition of mental fatigue state is successfully realized. The results show that compared with traditional machine learning algorithms, the proposed method significantly improves the accuracy of mental fatigue recognition to 96.3%, which provides a reliable basis for the early warning and evaluation of mental fatigue.