Journal of Neuroscience Methods最新文献

{"title":"Cross-species evaluation of commercial primary antibodies by Western blotting for immunohistochemical protein detection in mouse, rat, and human brain tissue.","authors":"Tila Medenica, Ema Bokulić, Anton Mažuranić, Slavica Martinović, Miloš Judaš, Goran Sedmak","doi":"10.1016/j.jneumeth.2026.110939","DOIUrl":"https://doi.org/10.1016/j.jneumeth.2026.110939","url":null,"abstract":"<p><strong>Background: </strong>Commercial antibodies show variable specificity and performance, limiting reproducibility of immunohistochemical studies. We systematically evaluated antibodies used to detect brain proteins across species.</p><p><strong>New method: </strong>Established Western blotting (WB) and immunofluorescence (IF) validation approaches were applied systematically and in parallel to mouse, rat, and human brain tissue. The distinctive scope of the study was the comparative evaluation of 23 antibodies targeting 17 proteins, with WB results interpreted in the context of expected molecular weights, isoforms, post-translational modifications, and published evidence concerning each target. Antibody performance was further compared with publicly available validation information, and logistic regression was used to assess whether antibody citation count and manufacturer-provided validation information predicted successful experimental validation.</p><p><strong>Results: </strong>Ten antibodies (43%) showed supportive WB results, and eight (35%) were validated by both WB and IF. Several antibodies produced unexplained or non-specific bands, while others showed speciesdependent performance. Validated antibodies displayed appropriate neuroanatomical and subcellular staining patterns. Antibody citation count was moderately associated with successful validation, whereas manufacturer-provided validation information did not improve predictive performance.</p><p><strong>Comparison with existing methods: </strong>The overall validation rate was comparable to previously published antibody validation studies and Human Protein Atlas results. The present study extends existing work through its broader antibody panel, parallel cross-species evaluation, detailed target-protein assessment, and quantitative analysis of antibody metadata.</p><p><strong>Conclusions: </strong>Commercial antibodies require independent validation before use in cross-species immunohistochemical studies. Our results provide a practical resource for antibody selection and highlight limitations of manufacturer claims and citation counts as indicators of antibody performance.</p>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":" ","pages":"110939"},"PeriodicalIF":2.5,"publicationDate":"2026-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149245098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Baseline Adjustment and Normalisation in Neurite Outgrowth Assays: A Simulation-Based Comparison of Analytical Methods.","authors":"Kyle Hewitt, Xu-Feng Huang","doi":"10.1016/j.jneumeth.2026.110940","DOIUrl":"https://doi.org/10.1016/j.jneumeth.2026.110940","url":null,"abstract":"<p><strong>Background: </strong>When baseline neurite lengths differ between experimental groups, analytical methods may detect, miss or overstate treatment effects. We assessed how commonly used methods recover a baseline-adjusted treatment effect.</p><p><strong>New method: </strong>We developed a simulation framework comparing endpoint comparison, change score, percentage change, percent-of-control normalisation and ANCOVA. A known 8 μm treatment effect was simulated under varying baseline imbalances and baseline-growth relationships, with additional analyses of sample size and baseline measurement error.</p><p><strong>Results: </strong>In the worked example, endpoint comparison and percent-of-control normalisation did not recover the true adjusted effect, whereas change score overestimated it by 55%. Across 20 parameter combinations, ANCOVA maintained nominal Type I error (3.8-5.8%) and remained essentially unbiased (mean absolute bias: 0.02 μm) when baseline was measured without error. Small-sample analyses showed that systematic bias persisted while error rates varied with sample size. Substantial baseline measurement error reduced ANCOVA's bias advantage and could inflate its Type I error.</p><p><strong>Comparison with existing methods: </strong>Endpoint and percent-of-control approaches estimate unadjusted endpoint differences. Change scores can be distorted when baseline predicts subsequent growth, while percentage change additionally introduces denominator-related distortion when baselines differ. ANCOVA directly estimates the treatment effect at a common baseline under its standard assumptions.</p><p><strong>Conclusions: </strong>When the target is a baseline-adjusted effect and baseline is measured reliably, ANCOVA provides the most appropriate analysis under the conditions examined. Baseline values, the target estimand and assumption checks should be reported explicitly.</p>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":" ","pages":"110940"},"PeriodicalIF":2.5,"publicationDate":"2026-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149245149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-Modal Masked Connectome Transformer for multimodal EEG-fMRI learning in ADHD diagnosis.","authors":"Jiujiang Guo, Monan Wang, Xiaojing Guo","doi":"10.1016/j.jneumeth.2026.110922","DOIUrl":"https://doi.org/10.1016/j.jneumeth.2026.110922","url":null,"abstract":"<p><strong>Background: </strong>Attention Deficit Hyperactivity Disorder (ADHD) is associated with distributed alterations in large-scale brain systems, making reliable diagnosis from neuroimaging data challenging. EEG-derived and fMRI-derived static functional-connectivity profiles summarize patterns of electrophysiological coupling and hemodynamic covariation, respectively, but their heterogeneous signal mechanisms make direct multimodal alignment difficult.</p><p><strong>New method: </strong>We propose a Cross-Modal Masked Connectome Transformer (CM-MCT) for EEG-fMRI based ADHD diagnosis. Instead of imposing direct correspondence between individual connections, CM-MCT treats each Desikan-Killiany 68-region cortical atlas (DK-68) region of interest (ROI) as a connectivity-profile token and learns to recover masked ROI-level connectome information within and across modalities. The model contains modality-specific Transformer encoders, cross-modal masked connectome objectives, and a bidirectional cross-attention fusion module for diagnostic prediction. Cross-fitted mask perturbations are used to characterize ROI-level model dependence, with explicit assessment of associations with nodal strength and perturbation magnitude.</p><p><strong>Results: </strong>Experiments using repeated five-by-five stratified evaluation of 210 paired HBN subjects demonstrate that the proposed method achieves 89.7% accuracy (95% confidence interval: 85.7%-93.3%) and 94.3% AUC (95% confidence interval: 91.5%-96.8%).</p><p><strong>Comparison with existing methods: </strong>Compared with the evaluated methods under matched splits, preprocessing, validation, and model-selection rules, CM-MCT shows the highest mean performance, although the AUC difference from the strongest baseline does not reach statistical significance after multiplicity correction.</p><p><strong>Conclusions: </strong>CM-MCT supports multimodal learning from the complementary network-level information provided by static EEG and fMRI connectivity profiles. Perturbation analysis yields modality-specific ROI sensitivity patterns that are modestly associated with the assessed factors. These heatmaps characterize model dependence without establishing causal involvement or identifying ADHD biomarkers.</p>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":" ","pages":"110922"},"PeriodicalIF":2.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149224293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Use of the arousal-based individual screening model for studying post-traumatic stress disorder: Findings and future directions.","authors":"Sebastiano A Torrisi, Gian Marco Leggio","doi":"10.1016/j.jneumeth.2026.110924","DOIUrl":"10.1016/j.jneumeth.2026.110924","url":null,"abstract":"<p><p>Post-traumatic stress disorder (PTSD) is a debilitating psychiatric condition arising in a subset of trauma-exposed susceptible individuals, yet the pathophysiological determinants of this individual variability remain largely unresolved. We developed the arousal-based individual screening (AIS) model with the aim of filling key gaps in the preclinical field. The AIS model identifies susceptible and resilient mice of both sexes by applying z-normalization of post-trauma changes in acoustic startle reactivity (ASR) induced by a single 24-hour restraint. Susceptible mice develop a long-lasting, multi-domain PTSD-like phenotype with behavioral abnormalities persisting for at least 75 days post-trauma. Critically, trauma susceptibility rates are sex-dependent: approximately 25-35% in males and 35-45% in females, recapitulating clinically observed sex differences in PTSD prevalence. The AIS model shows face, construct, and predictive validity, including pharmacological response to chronic paroxetine in susceptible animals. Since its establishment, we have used the AIS model to investigate three major pathophysiological dimensions of PTSD susceptibility: epigenetic regulation via brain-region-specific miRNA dysregulation; gut-brain axis dysfunctions, and sex-dependent hippocampal pathophysiological mechanisms. This review synthesizes these findings in relation to the human PTSD phenomenology, argues for the necessity of developing genuinely translational animal models that capture individual variability and sex differences as key experimental variables, and discusses the methodological and ethical considerations surrounding the use of traumatic procedures in preclinical research.</p>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":" ","pages":"110924"},"PeriodicalIF":2.5,"publicationDate":"2026-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149206975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Brain folding as a Fourier series yields a developmental clock.","authors":"Ezequiel Goldschmidt","doi":"10.1016/j.jneumeth.2026.110926","DOIUrl":"https://doi.org/10.1016/j.jneumeth.2026.110926","url":null,"abstract":"<p><p>The human fetal cortex begins as a smooth spheroid and progressively folds into a stereotypical sulcal pattern. I show that the spherical-harmonic expansion - the closed-surface generalisation of Fourier's series - reproduces this developmental sequence in reverse on the group-average atlas: truncating the fully formed cortex at low maximum harmonic degree L_max recovers a younger fetal brain; progressively higher L_max recovers the primary, secondary and tertiary folds in the order in which they emerge. From this I derive a closed-form 23-dimensional log-fractional spectral descriptor. On atlas templates (17 Harvard CRL + 16 dHCP weekly templates) it predicts gestational age at MAE 0.13 and 0.38 wk across cohorts after a single supervised linear alignment, and 1.07 and 1.51 wk without. On 28 Yale-Wayne State longitudinal pairs it advances predicted GA in every subject, without cohort matching. On 80 FeTA scans (31 neurotypical, 49 pathological) off-trajectory distance discriminates pathology at AUC 0.80, and unsupervised clustering yields three internally stable, biometrically concordant subgroups - an exploratory finding requiring external validation. Individual-scan gestational-age accuracy is not the descriptor's competitive use (MAE 2.25 wk on FeTA-NT); its individual-scan value is the shape of the residual around the normative trajectory. The framework separates two spatial-scale regimes of folding onto distinguishable spectral bands and is complementary to existing measures of fetal cortical maturation.</p>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":" ","pages":"110926"},"PeriodicalIF":2.5,"publicationDate":"2026-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149216421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A graph convolution-based dual-branch network for decoding of upper-limb motor imagery EEG signals.","authors":"S Chrisilla, R Shantha Selvakumari","doi":"10.1016/j.jneumeth.2026.110921","DOIUrl":"10.1016/j.jneumeth.2026.110921","url":null,"abstract":"<p><strong>Background: </strong>Analysing motor imagery EEG signals using conventional Euclidean feature computation is challenging due to low spatial resolution, non-stationarity, and complex inter-channel dependencies, which limit robust subject-independent generalization in brain-computer interface systems.</p><p><strong>New method: </strong>This study proposes a graph-based convolutional framework for subject-independent decoding of upper-limb motor imagery. The model integrates graph convolution with skip connections and handcrafted time-frequency features, together with parallel spatial and temporal convolutional pathways. Graph convolution captures functional connectivity between electrodes, while convolutional modules enhance spatial-temporal representation learning. Subject-independent evaluation is ensured using Stratified Group K-Fold (SGKF) and Leave-One-Subject-Out (LOSO) validation protocols.</p><p><strong>Results: </strong>The framework was evaluated on the PhysioNet, BCI IV-2a, and BCI IV-2b datasets using multiple electrode configurations. For the PhysioNet dataset, three upper-limb classes were considered, achieving SGKF accuracies of 86.42%, 91.01%, and 93.91% using 64, 21, and 5 electrodes, respectively, and LOSO accuracies of 92.25%, 95.72%, and 96.01%. On the BCI IV-2a dataset, SGKF accuracies of 86.13%, 89.01%, and 92.33% were obtained, with LOSO accuracies reaching 97.12% using five electrodes. For the BCI IV-2b dataset, accuracies of 88.60% (SGKF) and 93.35% (LOSO) were achieved using only three electrodes.</p><p><strong>Comparison with existing methods: </strong>The proposed graph-based framework demonstrates competitive performance compared to representative graph-based methods while requiring fewer trainable parameters and EEG electrodes.</p><p><strong>Conclusion: </strong>These findings demonstrate that graph-based deep learning enables accurate, subject-independent motor imagery decoding with reduced model complexity and minimal electrode usage, supporting practical and resource-efficient brain-computer interface systems.</p>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":" ","pages":"110921"},"PeriodicalIF":2.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149193911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Post-traumatic stress disorder recognition using the fNIRS dual-attention network.","authors":"He Pan, Peng Ding, Fan Wang, Yunyun Ma, Anmin Gong, Wenya Nan, Na Li, Yunfa Fu","doi":"10.1016/j.jneumeth.2026.110925","DOIUrl":"10.1016/j.jneumeth.2026.110925","url":null,"abstract":"<p><strong>Background: </strong>Post-traumatic stress disorder (PTSD) is a prevalent psychological disorder that can impair daily functioning and mental health. Current clinical assessment mainly relies on structured interviews and symptom scales, which may introduce subjectivity and inter-rater variability. Functional near-infrared spectroscopy (fNIRS) provides a noninvasive approach for measuring task-evoked hemodynamic responses and may offer objective physiological information for auxiliary PTSD recognition.</p><p><strong>New method: </strong>This study proposes an end-to-end deep learning framework, the fNIRS Dual Attention Network (FDANet), for PTSD recognition. Ten PTSD patients and ten healthy controls (HC) were recruited, and prefrontal hemodynamic signals, including oxyhemoglobin (HbO), deoxyhemoglobin (HbR), and total hemoglobin (HbT), were recorded during fear and neutral facial-expression stimuli. The three hemodynamic signals were concatenated along the channel dimension to form the model input. FDANet combines Transformer-based temporal modeling, one-dimensional temporal-channel attention, and convolutional feature extraction to learn discriminative representations from multichannel fNIRS signals.</p><p><strong>Results: </strong>The model was evaluated using subject-wise nested cross-validation with five outer folds. At the trial level, FDANet achieved an accuracy of 79.4%. At the subject level, FDANet achieved an accuracy of 95.0%.</p><p><strong>Comparison with existing methods: </strong>Compared with the evaluated traditional machine-learning and deep-learning baseline methods, FDANet achieved higher classification accuracy at both trial and subject levels.</p><p><strong>Conclusions: </strong>These findings indicate that task-evoked prefrontal fNIRS signals contain discriminative information for PTSD recognition. Given the portability and noninvasive measurement characteristics of fNIRS, FDANet may support the future development of objective auxiliary screening tools for PTSD, although further validation with larger and independent samples is required.</p>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":" ","pages":"110925"},"PeriodicalIF":2.5,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149182353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis choices can produce apparent rich-club differences: an Alzheimer's disease EEG case study.","authors":"Kai-Wayne Liu, Ryan Tian En Pang, Pholpat Durongbhan","doi":"10.1016/j.jneumeth.2026.110927","DOIUrl":"10.1016/j.jneumeth.2026.110927","url":null,"abstract":"<p><strong>Background: </strong>The weighted rich-club coefficient tests whether a network's most strongly connected nodes are preferentially interconnected. Its interpretation depends on two often-implicit choices: how the randomised comparison networks are constructed, and whether the hubs are re-identified in each comparison network or held fixed at those of the observed network. When hubs are defined by connection strength, these choices change what the coefficient tests.</p><p><strong>New method: </strong>We examined how these choices affect inference using resting-state EEG from 20 people with Alzheimer's disease and 20 controls. Holding the data fixed, we compared four analysis pipelines, crossing two ways of building the comparison networks (global weight reshuffle or strength-conditioned null) with the two hub choices, and ran a calibration study using data constructed to contain no preferential hub coupling beyond nodal strength.</p><p><strong>Results: </strong>An apparent eyes-open group difference in rich-club organisation appeared only under the pipeline combining a global weight reshuffle with re-identified hubs. Under the empirical resampling ensemble, that pipeline reported a group difference in 43% of pseudo-studies, always higher in the Alzheimer's disease group, while the other three stayed near the expected 5%.</p><p><strong>Comparison with existing methods: </strong>Unlike global weight reshuffling, strength-conditioned nulls approximately preserve nodal strengths; fixing observed hubs also retains the identity of the core being tested.</p><p><strong>Conclusions: </strong>The same data can support or dissolve an apparent rich-club difference depending on these choices. No single choice is universally correct, but reporting which were made, and why they fit the question being asked, is essential to interpreting the result.</p>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":" ","pages":"110927"},"PeriodicalIF":2.5,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149182340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An orthotopic vestibular schwannoma mouse model to study tumor-host interactions and mechanism of sensorineural hearing loss","authors":"Bailey H. Duhon ,&nbsp;Melanie Fisher ,&nbsp;Han TN. Nguyen ,&nbsp;Matthew T. Rocco ,&nbsp;Eric C. Bielefeld ,&nbsp;Yin Ren","doi":"10.1016/j.jneumeth.2026.110709","DOIUrl":"10.1016/j.jneumeth.2026.110709","url":null,"abstract":"<div><h3>Background</h3><div>Sensorineural hearing loss (SNHL) is the most common symptom of vestibular schwannoma (VS), arising from multifactorial tumor-host interactions including mechanical cochleovestibular nerve compression and ototoxic tumor secretion, yet underlying mechanisms remain incompletely defined. This study establishes an anatomically precise mouse model and investigates the role of blood-labyrinth barrier (BLB) disruption in VS-associated SNHL.</div></div><div><h3>New method</h3><div>Adapting neuro-otologic surgical techniques, a petrosectomy with lateral semicircular canal fenestration was used to implant mouse <em>Nf2</em>^<em>-/-</em> Schwann cells and patient-derived primary VS cells into the cochleovestibular nerve within the internal auditory canal (IAC). Tumor growth was assessed by MRI and bioluminescence, while auditory and vestibular functions were evaluated by auditory brainstem response and behavioral assays. Immunofluorescence of inflammatory, matrix-remodeling, and tight junction markers were performed in the tumor, brainstem and cochlea.</div></div><div><h3>Results</h3><div>VS allografts progressed from the IAC to the cerebellopontine angle, exhibiting mixed Antoni A/B architecture. Auditory and vestibular function was preserved postoperatively and progressively declined with tumor growth. Macrophage/microglia activation was observed in the tumor, brainstem and cochleovestibular nerve. Matrix metalloprotease-9 (MMP-9) and high mobility group box 1 (HMGB1) overexpression in the tumor and ipsilateral cochlea was associated with evidence of BLB disruption, characterized by tight junction downregulation and significant vascular disorganization in the stria vascularis.</div></div><div><h3>Comparison with existing methods</h3><div>Existing animal models either require months to develop or fail to recapitulate native VS progression and hearing decline.</div></div><div><h3>Conclusion</h3><div>This novel mouse model recapitulates native VS progression within the IAC and offers a powerful platform to investigate mechanisms underlying VS-associated SNHL.</div></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"430 ","pages":"Article 110709"},"PeriodicalIF":2.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing brain–computer interface performance through source-level attention mechanism: An EEG motor imagery study","authors":"Jia-He Lim,&nbsp;Po-Chih Kuo","doi":"10.1016/j.jneumeth.2025.110666","DOIUrl":"10.1016/j.jneumeth.2025.110666","url":null,"abstract":"<div><h3>Background:</h3><div>Brain–computer interfaces (BCIs) enable direct communication between humans and machines by translating brain signals into control commands. Electroencephalography (EEG) is a commonly used modality in BCI systems due to its non-invasiveness and high temporal resolution. However, EEG-based BCIs often suffer from low signal-to-noise ratios and limited spatial resolution, primarily due to the small number of recording electrodes. Although source estimation techniques can improve spatial specificity, they typically require subject-specific information such as individual brain anatomy or electrode positions, which may not always be available. This study aims to address these challenges by proposing a framework that enhances task-relevant EEG signals using an attention-guided source estimation approach based on coarse predefined brain regions.</div></div><div><h3>New method:</h3><div>We developed an attention-guided neural network that estimates source-level activity most relevant to the BCI task, without requiring subject-specific structural data. The model uses predefined regions of interest to guide attention mechanisms toward informative spatial features.</div></div><div><h3>Results:</h3><div>The framework was validated using publicly available motor imagery EEG datasets, achieving strong performance. Comparison with existing methods: Comparative analyses were conducted against baseline models using traditional EEG signals and standard feature extraction methods. This study presents an effective approach for improving EEG-based BCI performance by integrating an attention-guided source estimation network into the decoding pipeline. The method does not rely on subject-specific anatomical information, making it broadly applicable.</div></div><div><h3>Conclusion:</h3><div>By emphasizing task-relevant source activity, the framework enhances signal quality and classification accuracy, thereby advancing the potential of BCIs for precise and practical applications.</div></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"429 ","pages":"Article 110666"},"PeriodicalIF":2.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145998391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}