生物医学工程学杂志最新文献

{"title":"[Electroencephalogram emotion recognition based on state-space models combined with spatio-temporal feature].","authors":"Chunli Wang, Jiahao Zhang, Jiarong Dou, Chenming Wang, Wenwen Chang","doi":"10.7507/1001-5515.202508024","DOIUrl":"10.7507/1001-5515.202508024","url":null,"abstract":"<p><p>To address the challenges of spatiotemporal feature heterogeneity, insufficient utilization of frequency band information, and weak cross-subject generalization in electroencephalogram (EEG)-based emotion recognition, this paper proposes a hierarchical spatiotemporal feature learning architecture named spatio-temporal mamba (ST-Mamba) based on state space models. Firstly, the proposed conv-spatio-temporal (CST) dual-branch collaborative module integrates the local feature extraction capability of convolutional neural network (CNN) with the global modeling ability of state space models. Through adaptive weighted fusion, it effectively mitigates the issue of inadequate modeling of inter-channel relationships in EEG signals. Secondly, the designed multi-band spatio-temporal feature pyramid (MBSTP) module adaptively weights features from different frequency bands via a frequency-band attention mechanism, while capturing spatial topological dependencies across brain regions through a hierarchical fusion strategy. Additionally, a data augmentation framework efficiently enhances the model's cross-subject generalization by applying augmentations in the frequency, temporal, and spatial domains. The proposed model achieves average accuracies of 95.56% and 84.47% on the Shanghai Jiao Tong University emotion EEG dataset (SEED), version III (SEED-III) and version IV (SEED-IV), respectively. Experiments demonstrate that the state space model effectively alleviates the over-smoothing issue in deep networks, offering a novel solution to spatiotemporal heterogeneity and cross-subject generalization challenges in EEG-based emotion recognition.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"311-318"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112232/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Optimized decomposition of dynamic electroencephalography-functional near infrared spectroscopy brain functional networks for the analysis of repetitive transcranial magnetic stimulation combined with motor training].","authors":"Jiewei Lu, Jianeng Lin, Yinuo Liu, Ying Zhang, Chunfang Wang, Jianda Han, Ningbo Yu","doi":"10.7507/1001-5515.202510062","DOIUrl":"10.7507/1001-5515.202510062","url":null,"abstract":"<p><p>Repetitive transcranial magnetic stimulation combined with motor training effectively promotes motor recovery in stroke patients. However, its underlying neurophysiological mechanisms remain unclear. Existing single-modal neuroimaging techniques are limited by the incapacity to fully characterize the neural mechanisms of combined interventions. To address the above problem, this paper proposed an optimized decomposition method for dynamic brain functional networks based on electroencephalography and functional near-infrared spectroscopy, in order to reveal the potential neural mechanisms underlying the improvement of motor function in stroke patients through combined repetitive transcranial magnetic stimulation and motor training from a multimodal perspective. Twenty-seven stroke patients were recruited to participate in a clinical trial for this study. The results showed that the real stimulation group exhibited significantly increased flexibility in the frontoparietal network after intervention, with the magnitude of change significantly correlated with clinical improvement, whereas no significant changes were observed in the sham stimulation group. In conclusion, this study reveals the brain functional rehabilitation mechanism under combined intervention, contributing to the development of personalized rehabilitation strategies.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"293-301"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112235/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Cluster-guided adaptive Transformer for muscle fatigue prediction].","authors":"Bo Fan, Xueliang Bao, Lei Ding, Jiao Wu","doi":"10.7507/1001-5515.202601012","DOIUrl":"10.7507/1001-5515.202601012","url":null,"abstract":"<p><p>Due to the significant non-stationarity and feature distribution discrepancies in surface electromyography (sEMG) signals during muscle fatigue monitoring, traditional fixed-parameter Transformer models often struggle to accurately capture the complex evolution of time-frequency characteristics across different fatigue stages. To address this limitation, this paper proposes a K-means clustering-guided neural architecture search method (CG-NAS) to achieve adaptive optimization of Transformer architectures based on data distribution characteristics. The method first classified input EMG features using the K-means clustering algorithm and constructed Gaussian distributions characterized by mean and variance to quantify the complexity of each cluster. These distribution priors then guided the neural architecture search process, enabling dynamic alignment between the architecture search space and data characteristics: for low-complexity data clusters with small mean and variance, lightweight Transformer architectures were selected, whereas for high-complexity clusters, architectures with greater width and depth were allocated. Experimental results demonstrated the superior performance of CG-NAS in muscle fatigue index prediction tasks, achieving a mean absolute error of 0.098 2 and a coefficient of determination of 0.957 3, significantly outperforming multiple benchmark models. The study shows that CG-NAS effectively aligns with the nonlinear evolution of time-frequency features during the fatigue process and provides an efficient and robust solution for fatigue monitoring.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"250-258"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112217/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Research on weighted hypergraph attention neural network for the diagnosis of psychiatric disorders using brain functional connectivity networks].","authors":"Xiuwei Lin, Zhifeng Wang, Haotao Yan, Siao Zeng, Peizhou Wang, Zetao Wu, Xin Yu, Junxi Han","doi":"10.7507/1001-5515.202510012","DOIUrl":"10.7507/1001-5515.202510012","url":null,"abstract":"<p><p>The hypergraph neural network (HGNN) has demonstrated efficacy in modeling high-order interactions among brain regions, thus providing a promising framework for analyzing brain functional connectivity networks in the context of psychiatric research. The present study proposes a phase-amplitude coupling-weighted hypergraph attention neural network (PAC-HyperGAT) model for the diagnosis of psychiatric diseases. The proposed methodology first constructs a functional hypergraph using elastic net-based sparse regression and then assigns physiologically meaningful weights to hyperedges by quantifying the phase-amplitude coupling strength among nodes within each hyperedge. In light of these findings, the present study proposes a novel hypergraph attention convolution kernel. The efficacy of this approach is evidenced by its enhancement of the node-level message passing mechanism, a feat that facilitates the integration of hyperedge weight information. This phenomenon, in turn, results in an enhancement of the discriminative ability of brain functional connectivity network representations. The proposed model is systematically evaluated on publicly available electroencephalogram datasets for attention deficit hyperactivity disorder (ADHD) and major depressive disorder (MDD). The experimental results demonstrate that PAC-HyperGAT attains an accuracy of (72.14 ± 9.19) % in ADHD classification, surpassing the performance of existing brain functional connectivity network methods across a range of evaluation metrics. The model exhibits notable efficacy in MDD classification, signifying substantial cross-disorder generalization capabilities. Furthermore, PAC-HyperGAT has demonstrated efficacy in identifying brain regions associated with these disorders. In summary, the proposed model demonstrates excellent generalizability, robustness, and neurobiological interpretability, providing a reliable analytical framework for objective diagnosis and mechanistic investigation of psychiatric diseases.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"319-327"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112229/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Research progress on the acquisition technology of magnetocardiography].","authors":"Bochao Kang, Ming Dong, Yi Chang, Jingyi Wang, Tairan Zhao, Lihong Fan","doi":"10.7507/1001-5515.202504002","DOIUrl":"10.7507/1001-5515.202504002","url":null,"abstract":"<p><p>For certain cardiovascular diseases such as coronary artery disease and arrhythmia, electrocardiogram as a conventional cardiac function monitoring method has limitations such as insufficient resolution and unreliable accuracy in diagnosis. In contrast, magnetocardiography (MCG) offers several advantages, such as being unaffected by uneven human body conductivity and skin-electrode contact, and providing higher spatial resolution, which make it more effective than electrocardiogram for pathological characterization and lesion localization. The acquisition technology of MCG, which is a vital component of the overall MCG system, has predominantly utilized superconducting quantum interference device. In recent years innovative cases of MCG acquisition using atomic magnetometers and magneto-resistive sensors have also appeared in academia. In this paper, the MCG acquisition technologies based on three distinct magnetic sensors are reviewed. Firstly, the current research progress on each MCG acquisition technology is introduced. After that, the enhancement approaches of various technologies for improving cardiac magnetic signal acquisition and magnetic shielding conditions are discussed. Subsequently, differences between each technology are analyzed and the existing development difficulties and solutions of MCG technology are discussed. Finally, an outlook on the application prospect of MCG in the clinical field is provided, aiming to provide references for the continuous optimization of MCG technology and accelerate its adoption as a reliable diagnostic method for cardiovascular diseases.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"405-413"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112219/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Exogenous nitric oxide suppresses K _ATP channel activity through S-nitrosylation].","authors":"Xuefei Wang, Yuxin Zhang, Weicao Hu, Xuewei Hao","doi":"10.7507/1001-5515.202511038","DOIUrl":"10.7507/1001-5515.202511038","url":null,"abstract":"<p><p>The inhibitory effect of exogenous nitric oxide (NO) on the open state of ATP-sensitive potassium channels (K _ATP) and its underlying mechanism remain unclear. In this study, patch-clamp and molecular biology techniques are used to investigate this issue. In acutely isolated rat mesenteric artery smooth muscle cells and human embryonic kidney 293 cells (HEK293) expressing inwardly rectifying potassium channel 6.1 subunit/sulfonylurea receptor 2B subunit (Kir6.1/SUR2B), sodium nitroprusside (SNP) was found to significantly inhibit the activity of open K _ATP channels. Detection using biotin-labeled glutathione ethyl ester (BioGEE) combined with Western blotting showed that Kir6.1 subunit glutathionylation level was significantly decreased after SNP treatment. These results indicate that exogenous NO directly inhibits the activity of open K _ATP channels by nitrosylating key cysteine residues of the Kir6.1 subunit and competitively inhibiting glutathionylation at this site. This study provides new experimental evidence for the molecular mechanism of NO in vascular regulation.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"391-397"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112221/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Mesothelial impairment induced by peritoneal dialysis and its potential protective strategies].","authors":"Yu Ban, Yingying Mei, Botao Chen, Wen Tang, Hongyan Kang","doi":"10.7507/1001-5515.202511048","DOIUrl":"10.7507/1001-5515.202511048","url":null,"abstract":"<p><p>Peritoneal dialysis serves as a critical treatment modality for end-stage renal disease. Extensive clinical practice has demonstrated that long-term exposure to high-glucose non-physiological peritoneal dialysis solutions can induce peritoneal injury, which is directly associated with a decline in ultrafiltration function and solute clearance capacity. This represents a significant cause of technical failure in dialysis and adverse clinical outcomes, such as peritonitis. Mesothelial cells and the glycocalyx on their surface, acting as the direct barrier between the peritoneum and the dialysis solution, play essential roles in regulating multiple pathophysiological processes, including fibrosis and inflammation, and are crucial for maintaining peritoneal function. This review provides a brief introduction to mesothelial cells and the glycocalyx, with a focus on elucidating the injury to the mesothelium and glycocalyx caused by high-glucose non-physiological peritoneal dialysis solutions, the associated injury mechanisms, and potential protective strategies. The aim is to offer insights for developing novel therapeutic approaches to preserve the structural and functional integrity of the peritoneum and extend the survival of patients undergoing peritoneal dialysis.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"398-404"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112211/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Research progress on intelligent brain age prediction methods in diagnosis of Parkinson's disease].","authors":"Shuangchang Zheng, Yulei Zhang, Qingyi Zhang, Zezhou Hao, Yanling Yang, Liang Zhou, Xufeng Yao","doi":"10.7507/1001-5515.202504010","DOIUrl":"10.7507/1001-5515.202504010","url":null,"abstract":"<p><p>With the increasing aging worldwide, the age-related neurodegenerative diseases are becoming more and more prevalent. Brain age, as a critical biological marker for assessing normal brain aging and indicating disease progression, has been widely applied in the early diagnosis and evaluation of neurodegenerative diseases such as Parkinson's disease (PD). This paper systematically elaborates on three types of methods for PD brain age prediction: statistical methods, traditional Machine learning (ML), and Deep learning (DL), from the perspectives of methodological overview and clinical application of PD brain age predication. For the first aspect, the PD brain age prediction workflow, statistical methods, ML methods, and DL methods are sequentially outlined; in the second aspect, the current clinical application status of the three types of PD brain age prediction methods is introduced. Finally, a summary and outlook are provided. This review not only provides important references for research on PD brain age prediction, but also offers novel approaches for evaluating human brain health, thus holding significant scientific and clinical value.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"421-427"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13123701/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Musculoskeletal biomechanical analysis of the three-dimensional gastrocnemius and soleus muscles].","authors":"Zhihao Tang, Jinghao Xu, Zhongmin Jin, Junyan Li","doi":"10.7507/1001-5515.202509045","DOIUrl":"10.7507/1001-5515.202509045","url":null,"abstract":"<p><p>Musculoskeletal models based on multibody dynamics have been widely applied in human biomechanics research; however, conventional one-dimensional (1D) muscle models are limited in their ability to represent realistic muscle geometry and fiber architecture, resulting in restricted biomechanical predictions. Although three-dimensional (3D) finite element (FE) muscle models can provide more detailed mechanical information, high computational cost limits their application at the whole lower-limb scale. To address these limitations, this study develops a unilateral lower-limb musculoskeletal model with hybrid muscles based on the TLEM2.0 database, in which the soleus-gastrocnemius muscle group was represented using 3D FE models, while the remaining muscles were modeled using 1D Hill-type formulations. By coupling FE analysis with muscle recruitment optimization, muscle activation patterns of the right lower limb during the stance phase of level walking were obtained. Model predictions were validated against in <i>vivo</i> knee joint reaction forces and surface electromyography (sEMG) data. The results demonstrated good agreement between the predicted and experimentally measured knee joint reaction forces, and the predicted force patterns of the medial and lateral gastrocnemius muscles corresponded well with sEMG trends. In addition, the model enabled detailed observation of muscle deformation as well as internal tensile stress and strain distributions in the 3D muscles during gait. This hybrid musculoskeletal modeling framework achieves a balance between computational efficiency and biomechanical fidelity, providing an effective platform for investigating lower-limb muscle biomechanics.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"227-234"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112216/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Optical coherence tomography angiography image segmentation based on multi-scale dilated convolution and dual attention network].","authors":"Qinghao Zeng, Zhang Xiao, Bin He, Rushu Peng","doi":"10.7507/1001-5515.202505030","DOIUrl":"10.7507/1001-5515.202505030","url":null,"abstract":"<p><p>Optical coherence tomography angiography (OCTA) is an emerging non-invasive ophthalmic imaging modality. The morphology and contour of the foveal avascular zone (FAZ) are critical biomarkers for the diagnosis of various ophthalmic and systemic diseases; therefore, achieving its accurate segmentation is of substantial clinical significance. To address challenges such as low contrast, indistinct boundaries, and structural confusion with the surrounding retinal vasculature in OCTA images, this paper proposes a multi-scale dilated convolution and dual attention network (MSAD-Net). By integrating a multi-scale dilated convolution module (MSDM) to capture extensive multi-scale contextual information and employing a dual attention module (DAM) to integrate complementary channel and spatial features, thereby synergistically boosting the feature representation of key regions. Experimental results demonstrated that the model achieved superior performance and robust generalization across multiple evaluation metrics, including the Dice similarity coefficient, Jaccard index, precision, and recall-on two public datasets. These findings confirm the robustness of MSAD-Net in the fine segmentation of the FAZ, providing high-precision technical support for the clinical quantitative analysis of ophthalmic diseases.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"43 2","pages":"373-381"},"PeriodicalIF":0.0,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13112228/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}