Frontiers in Neuroscience最新文献

{"title":"Mapping curvature domains in human V4 using CBV-sensitive layer-fMRI at 3T.","authors":"Elisa Zamboni, Isaac Watson, Rüdiger Stirnberg, Laurentius Huber, Elia Formisano, Rainer Goebel, Aneurin J Kennerley, Antony B Morland","doi":"10.3389/fnins.2025.1537026","DOIUrl":"10.3389/fnins.2025.1537026","url":null,"abstract":"<p><strong>Introduction: </strong>A full understanding of how we see our world remains a fundamental research question in vision neuroscience. While topographic profiling has allowed us to identify different visual areas, the exact functional characteristics and organization of areas up in the visual hierarchy (beyond V1 & V2) is still debated. It is hypothesized that visual area V4 represents a vital intermediate stage of processing spatial and curvature information preceding object recognition. Advancements in magnetic resonance imaging hardware and acquisition techniques (e.g., non-BOLD functional MRI) now permits the capture of cortical layer-specific functional properties and organization of the human brain (including the visual system) at high precision.</p><p><strong>Methods: </strong>Here, we use functional cerebral blood volume measures to study the modularity in how responses to contours (curvature) are organized within area V4 of the human brain. To achieve this at 3 Tesla (a clinically relevant field strength) we utilize optimized high-resolution 3D-Echo Planar Imaging (EPI) Vascular Space Occupancy (VASO) measurements.</p><p><strong>Results: </strong>Data here provide the first evidence of curvature domains in human V4 that are consistent with previous findings from non-human primates. We show that VASO and BOLD tSNR maps for functional imaging align with high field equivalents, with robust time series of changes to visual stimuli measured across the visual cortex. V4 curvature preference maps for VASO show strong modular organization compared to BOLD imaging contrast. It is noted that BOLD has a much lower sensitivity (due to known venous vasculature weightings) and specificity to stimulus contrast. We show evidence that curvature domains persist across the cortical depth. The work advances our understanding of the role of mid-level area V4 in human processing of curvature and shape features.</p><p><strong>Impact: </strong>Knowledge of how the functional architecture and hierarchical integration of local contours (curvature) contribute to formation of shapes can inform computational models of object recognition. Techniques described here allow for quantification of individual differences in functional architecture of mid-level visual areas to help drive a better understanding of how changes in functional brain organization relate to difference in visual perception.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1537026"},"PeriodicalIF":3.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11897262/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143614629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Chronic unpredictable mild stress induces anxiety-like behavior in female C57BL/6N mice, accompanied by alterations in inflammation and the kynurenine pathway of tryptophan metabolism.","authors":"Yanqin Luo, Ning Jiang, Yiwen Zhang, Yongzhi Zhao, Fang Chen, Xueyan Li, Meng Qiang, Guirong Zeng, Qinghu He, Xinmin Liu, Chunhui Shan","doi":"10.3389/fnins.2025.1556744","DOIUrl":"10.3389/fnins.2025.1556744","url":null,"abstract":"<p><p>Chronic stress can impact brain function through various mechanisms, contributing to the development of anxiety disorders. Chronic unpredictable mild stress (CUMS) is a well-established model for studying the effects of chronic stress. This study assessed the impacts of different durations of CUMS on anxiety-like behavior, inflammation, and tryptophan metabolism in female C57BL/6N mice. The results revealed significant behavioral changes after 2-4 weeks of CUMS. Specifically, the open arms ratio and open arms time ratio in the elevated plus maze (EPM) decreased, the latency to feed in the novelty-suppressed feeding test (NSFT) was prolonged, and the number of transitions in the light/dark box (LDB) was decreased. After 1 week of CUMS, the levels of some pro-inflammatory cytokines (such as IL-1β and iNOS) and anti-inflammatory cytokines (including IL-10) began to rise. After 2 weeks of CUMS, most pro-inflammatory cytokines (IL-1β, IL-6, CD86, iNOS) and the anti-inflammatory cytokines TGF-β and CD11b showed an increase, while some anti-inflammatory cytokines (Arg-1, IL-10) began to decrease. After 3 weeks of stress, the pro-inflammatory cytokine TNF-α also significantly increased, while the anti-inflammatory cytokine TGF-β began to decline. By 4 weeks of CUMS, the anti-inflammatory cytokine CD11b also started to decrease. Regarding tryptophan metabolism, after 3-4 weeks of CUMS, serotonin (5-HT) levels in the hippocampus of the mice began to decrease. Additionally, the kynurenine pathway in tryptophan metabolism shifted more towards the KYN-QA branch, resulting in the reduction in the neuroprotective substance kynurenic acid (KYNA), while neurotoxic substances such as 3-hydroxykynurenine (3-HK) and quinolinic acid (QA) accumulated. In summary, female C57BL/6N mice exhibit anxiety-like behavior after 2 weeks of CUMS, accompanied by inflammatory responses. After 3-4 weeks of CUMS, anxiety-like behavior persists, with exacerbated inflammatory responses and disturbances in tryptophan metabolism.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1556744"},"PeriodicalIF":3.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11897007/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143614601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Persistent homology for MCI classification: a comparative analysis between graph and Vietoris-Rips filtrations.","authors":"Debanjali Bhattacharya, Rajneet Kaur, Ninad Aithal, Neelam Sinha, Thomas Gregor Issac","doi":"10.3389/fnins.2025.1518984","DOIUrl":"10.3389/fnins.2025.1518984","url":null,"abstract":"<p><strong>Introduction: </strong>Mild cognitive impairment (MCI), often linked to early neurodegeneration, is associated with subtle disruptions in brain connectivity. In this paper, the applicability of persistent homology, a cutting-edge topological data analysis technique is explored for classifying MCI subtypes.</p><p><strong>Method: </strong>The study examines brain network topology derived from fMRI time series data. In this regard, we investigate two methods for computing persistent homology: (1) Vietoris-Rips filtration, which leverages point clouds generated from fMRI time series to capture dynamic and global changes in brain connectivity, and (2) graph filtration, which examines connectivity matrices based on static pairwise correlations. The obtained persistent topological features are quantified using Wasserstein distance, which enables a detailed comparison of brain network structures.</p><p><strong>Result: </strong>Our findings show that Vietoris-Rips filtration significantly outperforms graph filtration in brain network analysis. Specifically, it achieves a maximum accuracy of 85.7% in the Default Mode Network, for classifying MCI using in-house dataset.</p><p><strong>Discussion: </strong>This study highlights the superior ability of Vietoris-Rips filtration to capture intricate brain network patterns, offering a robust tool for early diagnosis and precise classification of MCI subtypes.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1518984"},"PeriodicalIF":3.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11897488/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143614630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"How a patient-led advocacy organization supports the road to diagnosis and treatment of creatine transporter deficiency.","authors":"Heidi Wallis, Sangeetha Iyer, Emily K Reinhardt","doi":"10.3389/fnins.2025.1548182","DOIUrl":"10.3389/fnins.2025.1548182","url":null,"abstract":"<p><p>The current era of drug development has evolved significantly. Patient advocacy organizations are moving beyond simply supporting community members and are taking the reins to improve the speed of diagnoses, initiate therapeutic discoveries, and lay the groundwork to ensure successful clinical trials. The Association for Creatine Deficiencies (ACD) is an international parent-led patient advocacy organization focused on the three ultra-rare neurodevelopmental monogenic disorders resulting in Cerebral Creatine Deficiency Syndromes (CCDS). These include X-linked creatine transporter deficiency (CTD), guanidinoacetate methyltransferase (GAMT) deficiency, and l-arginine:glycine amidinotransferase (AGAT) deficiency. While each is rare in its own right, the unified CCDS community is effectively advancing the field of CCDS with each disorder benefiting from progress made in the other two disease areas. ACD collaborators include caregivers, academic researchers, clinicians, industry partners, and policymakers. Since its founding in 2012, the organization has evolved and achieved significant milestones. These include advancements in disease diagnosis, investments in various therapeutic modalities, creation of a collaborative research community, a unified patient community contributing essential patient data, and repositories of patient-derived specimens. The initiatives of ACD are intended to create the earliest diagnosis possible through newborn screening, to have an effective treatment, and to make disease management strategies available to all members of the CCDS community, including those diagnosed at later stages and experiencing greater effects of the diseases.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1548182"},"PeriodicalIF":3.2,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11897708/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143614627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bibliometric analysis of cognitive dysfunction after traumatic brain injury.","authors":"Jihua Hu, Ruiting Zhu, Xin Zhang, Yuchen Zhang, Jixin Liu, Wenyang Wang, Chiyin Li, Tong Yang, Ming Zhang, Xuan Niu","doi":"10.3389/fnins.2025.1534735","DOIUrl":"10.3389/fnins.2025.1534735","url":null,"abstract":"<p><strong>Background: </strong>Cognitive dysfunction after traumatic brain injury (TBI) significantly reduces quality of life and imposes a heavy burden on society. A detailed examination of research trends of cognitive dysfunction following TBI has not yet been conducted. This study aimed to examine the bibliometric analysis of cognitive dysfunction after traumatic brain injury over the past 20 years.</p><p><strong>Methods: </strong>Literature on bibliometric analysis was retrieved from the Web of Science Core Collection (WoSCC) and Science Citation Index Expanded (SCI-E) from 2004 to 2023. The type of literature and the language were refined. A total of 1,902 articles were used for bibliometric analysis, including 1,543 (81.1%) original articles and 359 (18.9%) review articles. Data were retrieved on June 5, 2024.</p><p><strong>Results: </strong>The publication volume of articles was increasing year by year, with articles published in 537 journals. The <i>Journal of Neurotrauma</i>, with 130 articles, was the most productive and influential journal. The University of California System led in the number of articles published. There were 9,002 authors from 62 countries/regions. The USA and China were the top-ranked countries by article count. Pandharipande PP authored the highly cited article. Pick CG, as the author with the highest h-index. The top three of author keywords were traumatic brain injury, cognitive impairment, and mild traumatic brain injury. The topics of cognitive dysfunction after TBI were ferroptosis, cognitive decline, spinal cord injury, and prognosis.</p><p><strong>Conclusion: </strong>Our findings provide valuable insights into cognitive dysfunction following TBI and highlight emerging trends for future research.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1534735"},"PeriodicalIF":3.2,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893989/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143604620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parameter optimization of 3D convolutional neural network for dry-EEG motor imagery brain-machine interface.","authors":"Nobuaki Kobayashi, Musashi Ino","doi":"10.3389/fnins.2025.1469244","DOIUrl":"10.3389/fnins.2025.1469244","url":null,"abstract":"<p><p>Easing the behavioral restrictions of those in need of care not only improves their own quality of life (QoL) but also reduces the burden on care workers and may help reduce the number of care workers in countries with declining birthrates. The brain-machine interface (BMI), in which appliances and machines are controlled only by brain activity, can be used in nursing care settings to alleviate behavioral restrictions and reduce stress for those in need of care. It is also expected to reduce the workload of care workers. In this study, we focused on motor imagery (MI) classification by deep-learning to construct a system that can identify MI obtained by electroencephalography (EEG) measurements with high accuracy and a low latency response. By completing the system on the edge, the privacy of personal MI data can be ensured, and the system is ubiquitous, which improves user convenience. On the other hand, however, the edge is limited by hardware resources, and the implementation of models with a huge number of parameters and high computational cost, such as deep-learning, on the edge is challenging. Therefore, by optimizing the MI measurement conditions and various parameters of the deep-learning model, we attempted to reduce the power consumption and improve the response latency of the system by minimizing the computational cost while maintaining high classification accuracy. In addition, we investigated the use of a 3-dimension convolutional neural network (3D CNN), which can retain spatial locality as a feature to further improve the classification accuracy. We propose a method to maintain a high classification accuracy while enabling processing on the edge by optimizing the size and number of kernels and the layer structure. Furthermore, to develop a practical BMI system, we introduced dry electrodes, which are more comfortable for daily use, and optimized the number of parameters and memory consumption size of the proposed model to maintain classification accuracy even with fewer electrodes, less recall time, and a lower sampling rate. Compared to EEGNet, the proposed 3D CNN reduces the number of parameters, the number of multiply-accumulates, and memory footprint by approximately 75.9%, 16.3%, and 12.5%, respectively, while maintaining the same level of classification accuracy with the conditions of eight electrodes, 3.5 seconds sample window size, and 125 Hz sampling rate in 4-class dry-EEG MI.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1469244"},"PeriodicalIF":3.2,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893816/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143604621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward autonomous event-based sensorimotor control with supervised gait learning and obstacle avoidance for robot navigation.","authors":"Shahin Hashemkhani, Vijay Shankaran Vivekanand, Samarth Chopra, Rajkumar Kubendran","doi":"10.3389/fnins.2025.1492436","DOIUrl":"10.3389/fnins.2025.1492436","url":null,"abstract":"<p><p>Miniature robots are useful during disaster response and accessing remote or unsafe areas. They need to navigate uneven terrains without supervision and under severe resource constraints such as limited compute, storage and power budget. Event-based sensorimotor control in edge robotics has potential to enable fully autonomous and adaptive robot navigation systems capable of responding to environmental fluctuations by learning new types of motion and real-time decision making to avoid obstacles. This work presents a novel bio-inspired framework with a hierarchical control system to address these limitations, utilizing a tunable multi-layer neural network with a hardware-friendly Central Pattern Generator (CPG) as the core coordinator to govern the precise timing of periodic motion. Autonomous operation is managed by a Dynamic State Machine (DSM) at the top of the hierarchy, providing the necessary adaptability to handle environmental challenges such as obstacles or uneven terrain. The multi-layer neural network uses a nonlinear neuron model which employs mixed feedback at multiple timescales to produce rhythmic patterns of bursting events to control the motors. A comprehensive study of the architecture's building blocks is presented along with a detailed analysis of network equations. Finally, we demonstrate the proposed framework on the Petoi robot, which can autonomously learn walk and crawl gaits using supervised Spike-Time Dependent Plasticity (STDP) learning algorithm, transition between the learned gaits stored as new states, through the DSM for real-time obstacle avoidance. Measured results of the system performance are summarized and compared with other works to highlight our unique contributions.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1492436"},"PeriodicalIF":3.2,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893847/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143604623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The influence of circadian rhythm disruption during Ramadan on metabolic responses to physical activity: a pilot study.","authors":"Najeha Rizwana Anwardeen, Khaled Naja, Shamma Almuraikhy, Maha Sellami, Hadaia Saleh Al-Amri, Nebu Philip, Faleh Tamimi, Ahmed Agil, Mohamed A Elrayess","doi":"10.3389/fnins.2025.1542016","DOIUrl":"10.3389/fnins.2025.1542016","url":null,"abstract":"<p><strong>Background: </strong>Circadian rhythms and sleep patterns are important regulators of metabolic health. During Ramadan intermittent fasting (RIF), the sleep-wake cycles are often disrupted, which can affect physical activity (PA) and related metabolic responses. Limited knowledge is available on how sleep disruption influences PA in the general population during RIF. This pilot study aimed to examine the metabolic responses to moderate PA under normal and disrupted sleep patterns during RIF.</p><p><strong>Methods: </strong>A pilot study was conducted on 12 participants comprising of individuals with normal (<i>n</i> = 5) and disrupted sleep patterns (<i>n</i> = 7). Blood samples were collected, and measurements of clinical traits, cytokines, homeostasis model assessment of insulin resistance (HOMA-IR) and metabolic profiles were performed before and after intervention. Orthogonal partial least square - discriminant analysis (OPLS-DA) and linear regressions were performed to assess metabolic responses to PA during RIF under different patterns.</p><p><strong>Results and conclusion: </strong>Fasting participants with normal sleep patterns exhibited lower HOMA-IR (<i>β</i> = -0.416, <i>p</i> = 0.047) in response to PA compared to those with disrupted sleep. Additionally, they demonstrated more efficient lipid utilization during PA, characterized by reduced diacylglycerol levels, which could enhance insulin sensitivity and lower the risk of type 2 diabetes. In contrast, fasting participants with disrupted sleep patterns experienced metabolic stress, marked by significant depletion of polyunsaturated fatty acids (PUFAs), monounsaturated fatty acids (MUFAs), and plasmalogens in response to PA. These changes were associated with increased inflammation and oxidative stress, potentially leading to metabolic dysregulation.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1542016"},"PeriodicalIF":3.2,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11891360/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143596734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gut microbiome differences in individuals with PTSD compared to trauma-exposed controls: a systematic review.","authors":"Chantelle Winder, Ami Lodhia, Melissa Basso, Kathrin Cohen Kadosh","doi":"10.3389/fnins.2025.1540180","DOIUrl":"10.3389/fnins.2025.1540180","url":null,"abstract":"<p><p>Post-traumatic stress disorder (PTSD) is a common mental health disorder that can occur following exposure to a traumatic event, and is characterized by symptoms including intrusive memories, dissociation, and nightmares. PTSD poses significant suffering on the individual and can reduce quality of life substantially, however, its mechanisms are not fully understood. It has also been associated with gut abnormalities, such as with irritable bowel syndrome, indicating possible involvement of the gut microbiome and gut-brain axis. Whereas previous research has implicated the gut microbiome and microbiome gut-brain axis in various mental health disorders, the relationship between gut microbiome function and PTSD is unclear. Specifically, little is known about whether specific gut microbiome compositions can increase the risk of developing PTSD, or, vice versa, act as a protective factor for the individual. This systematic review aims to synthesize the literature looking at gut microbiome differences between individuals with PTSD and trauma-exposed controls (TEC) while exploring potential risk and resilience factors for development of the disorder. Three studies met the inclusion criteria, and results showed that all studies found differences in gut microbial taxa between PTSD and TEC groups yet varied in their taxonomic level and type. One study found a significant difference in diversity between groups, reporting lower diversity in PTSD, and two studies found certain taxa to be correlated with PTSD symptom severity: <i>Mitsuokella</i>, <i>Odoribacter</i>, <i>Catenibacterium</i> and <i>Olsenella</i> genera, and <i>Actinobacteria</i>, <i>Lentisphaerae</i> and <i>Verrucomicrobia</i> phyla. This review has important implications for potential novel treatments for PTSD which target the gut microbiome, for example psychobiotic dietary interventions such as prebiotics and probiotics. It also informs our understanding of potential risk and resilience factors for the disorder, such as certain gut microbiome compositions being potentially protective or increasing susceptibility. More research is needed, as currently sample sizes are small and confounding variables (e.g., diet) are not always controlled for. <b>Systematic review registration:</b> The protocol was registered on PROSPERO, registration number: CRD42024530033.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1540180"},"PeriodicalIF":3.2,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11891237/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143596733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multiscale fusion enhanced spiking neural network for invasive BCI neural signal decoding.","authors":"Yu Song, Liyuan Han, Tielin Zhang, Bo Xu","doi":"10.3389/fnins.2025.1551656","DOIUrl":"10.3389/fnins.2025.1551656","url":null,"abstract":"<p><p>Brain-computer interfaces (BCIs) are an advanced fusion of neuroscience and artificial intelligence, requiring stable and long-term decoding of neural signals. Spiking Neural Networks (SNNs), with their neuronal dynamics and spike-based signal processing, are inherently well-suited for this task. This paper presents a novel approach utilizing a Multiscale Fusion enhanced Spiking Neural Network (MFSNN). The MFSNN emulates the parallel processing and multiscale feature fusion seen in human visual perception to enable real-time, efficient, and energy-conserving neural signal decoding. Initially, the MFSNN employs temporal convolutional networks and channel attention mechanisms to extract spatiotemporal features from raw data. It then enhances decoding performance by integrating these features through skip connections. Additionally, the MFSNN improves generalizability and robustness in cross-day signal decoding through mini-batch supervised generalization learning. In two benchmark invasive BCI paradigms, including the single-hand grasp-and-touch and center-and-out reach tasks, the MFSNN surpasses traditional artificial neural network methods, such as MLP and GRU, in both accuracy and computational efficiency. Moreover, the MFSNN's multiscale feature fusion framework is well-suited for the implementation on neuromorphic chips, offering an energy-efficient solution for online decoding of invasive BCI signals.</p>","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"19 ","pages":"1551656"},"PeriodicalIF":3.2,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11885244/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143585507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}