Arterial spin labeling (ASL) perfusion MRI stands as the sole non-invasive method to quantify regional cerebral blood flow (CBF), a crucial physiological parameter. However, ASL MRI typically suffers from a relatively low signal-to-noise ratio. In this study, we introduce a novel ASL denoising approach termed Multi-coil Unified Sparsity regularization using Inter-slice Correlation (MUSIC). While MRI, including ASL data, is routinely captured using multi-channel coils, existing denoising techniques are tailored for coil-combined data, overlooking inherent multi-channel correlations. MUSIC capitalizes on the fact that multi-channel images are primarily distinguished by coil sensitivity weighting and random noise, resulting in an intrinsic low-rank structure within the stacked multi-channel data matrix. This low rankness can be further enhanced by grouping highly correlated slices. Our approach involves adapting regularization to each slice individually, forming potentially low-rank matrices by stacking vectorized slices selected from different channels based on their Euclidean distance from the current slice under processing. Matrix rank is then approximated using the logarithm-determinant of the covariance matrix. Importantly, MUSIC operates directly on complex data, eliminating the need for separating magnitude and phase or dividing real and imaginary data, thereby minimizing information loss. The degree of low-rank regularization is controlled by the estimated noise level, achieving a balance between noise reduction and texture preservation. Experimental validation on real-world imaging data demonstrates the efficacy of MUSIC in significantly enhancing ASL perfusion quality. By effectively suppressing noise while retaining essential textural information, MUSIC holds promise for improving the utility and accuracy of ASL perfusion MRI, thus advancing neuroimaging research and clinical diagnoses.

Online adaptation is a promising technique for achieving calibration-free recognition in user-friendly brain-computer interfaces (BCIs) but remains underexplored for steady-state visual evoked potential (SSVEP) recognition. In our previous work on online multi-stimulus canonical correlation analysis (OMSCCA), we introduced a state-of-the-art scheme for the online adaptation of SSVEP spatial filters. Despite its effectiveness, this approach can not be directly extended to other advanced spatial filtering methods, thereby seriously limiting the broader development of calibration-free algorithms. To address this limitation, we propose a unified online adaptation frame work for correlation analysis (CA)-based spatial filtering methods, encompassing both spatial filter computation and utilization. Specifically, we extend the least-squares (LS) unified framework originally designed for full calibration with large amounts of training data to the online adaptation scenario without any pre-calibration, thereby enabling continuous updates of spatial filters. Moreover, to sufficiently utilize spatial filters, we introduce a cross-stimulus transfer method for online adaptation of the common impulse response and generation of user-specific templates for all stimuli using limited online unlabeled data. Finally, leveraging the proposed unified framework, we adapt three advanced spatial filtering methods from their calibration based counter parts to online adaptation paradigms and validate their performance through simulation studies. Our results demonstrate the framework's effectiveness in promoting the development ofzero-calibration SSVEP-based BCIs. Compared to the OMSCCA, the proposed online adaptation methods canimprove the recognition performance by more than 12%. This work provides a generalizable approach for transforming existing calibration-based methods into adaptive, user-friendly solutions for practical BCI applications.

Steady-state visual evoked potential-based brain-computer interfaces (SSVEP-BCIs) hold significant promise for enabling high-speed human-computer interaction in real-world scenarios. However, existing frequency-domain decoding methods treat frequency spectrum features (the real and imaginary spectrum features) as a single feature without considering their unique spatial and spectral characteristics, resulting in insufficient generalizable features and limited classification accuracy in cross-subject scenarios. To address this issue, we propose a Dual-Branch Attention-Based Frequency Domain Network (DB-AFDNet) to independently decode real and imaginary spectral components, aiming to acquire more discriminative and generalizable features for cross-subject applications. Specifically, we construct inter-branch attention similarity constraints to encourage the two branches to have similar attention properties, promoting to learn the consensus characteristics in the dual branches. Furthermore, we propose intra-branch orthogonality constraints to explore branch-specific discriminative features to learn generalizable features. Experimental studies on two public datasets, the Benchmark and Beta datasets, demonstrate that DB-AFDNet outperforms state-of-the-art methods in cross-subject classification, achieving a relative improvement of 1.36$\%$ and 1.45$\%$, respectively.

BackgroundAlzheimer's disease (AD) involves progressive cognitive decline associated with disrupted coordination and information exchange across brain regions. Cross-entropy can characterize inter-regional information flow, but its role in AD remains unexplored.ObjectiveTo evaluate cross-regional brain entropy (CRBEN) derived from resting-state fMRI in normal controls (NC), mild cognitive impairment (MCI), and AD, and to assess its potential as a biomarker of disease progression.MethodsResting-state fMRI data from 40 NC, 38 MCI, and 40 AD participants from ADNI 2/3 were preprocessed using SPM12 and FSL, including motion correction (FD < 0.5 mm). Mean time series were extracted from 300 regions of the seven-network Schaefer atlas. For each subject, a 300 × 300 CRBEN matrix was computed and decomposed using BrainSpace to obtain functional gradients, aligned via Procrustes analysis. Group differences were tested with two-sample t-tests controlling for age, sex, and education (Bonferroni-corrected, α = 0.05). Machine-learning classifiers were trained using gradient and demographic features, with robustness assessed by 1000 bootstrap resamples.ResultsCompared with NC, MCI showed reduced gradients in somatomotor, ventral-attention, and default-mode networks. AD showed further reductions versus MCI in somatomotor and default-mode networks, and versus NC in frontoparietal-control and default-mode networks (p < 0.05, corrected). Logistic regression achieved the highest accuracy (∼90%). Gradient flattening was prominent in temporal and occipital cortices, indicating reduced hierarchical organization.ConclusionsCRBEN gradients demonstrate progressive loss of network complexity across the AD continuum and may provide sensitive biomarkers of functional disintegration.

PURPOSE:To develop a slice-wise blurring-free and densely sampled TE-resolved multiple-TE (mTE) ASL sequence (TASL) for measuring blood-brain barrier (BBB) water exchange time. METHODS:A 3D TSE spiral-readout pCASL sequence was modified to enable TE-resolved acquisition. Signals at mTEs from a single kz partition were acquired within a single shot, and the acquisition was repeated until all required kz partitions were covered. In vivo experiments were conducted on healthy volunteers using both a conventional pCASL sequence and the proposed TASL sequence. Signal intensity modulation, perfusion SNR, and quantitative parameters including cerebral blood flow (CBF), arterial transit time (ATT), intravoxel transit time (ITT), and water exchange time (T exch) were evaluated. Test-retest scans were conducted to assess reproducibility. RESULTS:Compared with the conventional mTE acquisition, TASL eliminates T 2 decay-induced slice-wise intensity modulation and blurring, yielding higher whole-brain perfusion SNR across all TEs and PLDs. Estimates of CBF and ATT showed negligible differences between the two methods (both < 1%), whereas mean T exch and ITT values were 18.2% and 9.05% higher, respectively, with TASL. Bland-Altman analysis showed minimal bias, with 95% of differences within the limits of agreement (mean±1.96 SD). The inter-session ICC and wsCV of CBF, ATT, T exch, and ITT in gray matter are 0.86% and 8.38%, 0.96% and 1.98%, 0.93% and 4.04%, and 0.95% and 4.32%, respectively. CONCLUSION:TASL eliminates signal intensity modulation and blurring artifacts while providing densely sampled TE for parametric fitting. It may be a valuable tool for accurate and reliable quantification of cerebral perfusion and BBB permeability.

Background:Major depressive disorder (MDD) in adolescents and young adults is increasingly prevalent, yet accurate diagnosis remains challenging due to the limitations of conventional neuroimaging metrics. Traditional resting-state functional magnetic resonance imaging (rs-fMRI) measures such as amplitude of low-frequency fluctuations (ALFF), regional homogeneity (ReHo), and functional connectivity density (FCD) primarily capture static aspects of brain activity and may overlook critical neural dynamics. Brain entropy (BEN), which quantifies temporal irregularity in rs-fMRI signals, may offer a complementary approach to better characterize neural alterations in MDD. Methods:We analyzed multimodal rs-fMRI data from 204 individuals aged 12-24 years (119 with MDD and 85 healthy controls). BEN was computed alongside ALFF, ReHo, and FCD to extract region-wise features across the brain. A support vector machine with recursive feature elimination (SVM-RFE) was used to classify MDD and healthy controls based on various feature combinations. Classification performance was evaluated using repeated cross-validation and permutation testing. Additionally, partial Spearman correlations were performed between selected brain features and clinical measures including depression severity, childhood trauma, sleep quality, and cognitive control. Results:Models incorporating BEN consistently outperformed those using traditional rs-fMRI features alone. The combination of BEN, ALFF, and FCD achieved the highest classification accuracy (AUC = 0.877, permutation test P < 0.001). The most frequently selected brain regions contributing to MDD classification included the putamen, paracentral lobule, cuneus, middle frontal gyrus, and rectus. BEN features also showed preliminary correlations with clinical variables such as childhood trauma and sleep quality, suggesting functional relevance. Conclusions:This study demonstrates that BEN provides complementary diagnostic information to traditional rs-fMRI features in classifying adolescent and young adult MDD. BEN-related alterations in brain activity may reflect underlying neurobiological disruptions and show potential as a functional neuroimaging biomarker for depression during a critical stage of brain development.

Magnetic resonance fingerprinting (MRF) estimates tissue parameters by matching an acquired MR signal time course to entries in a Bloch- or EPG-simulated dictionary. However, no study has yet proven the uniqueness of the matching results. In two earlier studies by exhaustive objective mapping I showed that for two widely used MRF sequences the normalized-correlation objective exhibits a single dominant peak at the true T1/T2 values and decreases smoothly away from that peak. These empirical properties motivated the fast MRF-ZOOM search algorithm even without using a pre-generated signal dictionary, but their theoretical basis has remained incomplete. The purpose of this work is to develop a mathematical framework for the MRF matching objective under normalized-correlation matching.

Arterial spin labeled (ASL) perfusion MRI is the only non-invasive and non-radioactive technique for measuring regional tissue perfusion. Perfusion signal in ASL MRI is derived from the difference between the spin labeled image and the spin untagged control image. Limited by the T1 decay of arterial blood, ASL MRI has an intrinsic low signal-to-noise-ratio. Solving this problem is challenging because the ground truth is often unknown, and it is difficult to preserve textures when suppressing heavy noise. In this paper we propose an unsupervised Locally Adaptive regularization with Collaborative data Selection (LACS) scheme, which exploits the high affinity between the paired label and control (L/C) images to select highly correlated contents to form the low-rank matrices. The low-rank regularization applied to such matrices could be better adapted to local structures compared with slice-level global models and more robust against noise compared with voxel-level local models. Further, we used the log-determinant of covariant matrices as the non-convex surrogate of the low-rank penalty instead of the widely used convex surrogates. We demonstrated that the adopted surrogate essentially exploits near-optimal sparsity in the underlying principal component analysis (PCA) domain without explicit training. Apparently, LACS does not rely on any ground-truth training data. When tested on a real-world ASL MRI dataset, LACS significantly improved the quality of ASL perfusion maps using just one pair of L/C images, compared with the standard pipeline that requires multiple L/C pairs. The proposed scheme could set a new benchmark for ASL MRI denoising.

The interaction of the brain's decision-making and feedback stages is crucial for guiding human behavior. Previous studies mainly focused on the interaction immediately after the feedback, resulting in a limited understanding of brain communication dynamics during the interaction process. This study examined the communication dynamics of the brain network during decision- feedback interaction under various feedback conditions by employing a newly developed activation network approach to reveal its underlying neural mechanism. Thirty participants completed a decision- feedback task that involved a sequence of cue-induced predictions with highly predictable, somewhat predictable, and unpredictable feedback conditions. We constructed the activation network for all experimental stages using source-level EEG data in the alpha band. Notably, the brain exhibited the highest communication efficiency ($p < 0.05$) in receiving and integrating feedback with decision-making information during the feedback stage. Furthermore, the network-behavior correlations indicated that the brain tends to evaluate unexpected feedback under highly predictable conditions and expected feedback under unpredictable conditions, suggesting distinct neural strategies of the decision- feedback interaction process. Finally, we decoded the optimization process of decision- feedback interaction across the entire task. Although network correlations between the decision and feedback stages decreased over time (high predictable: $r = -0.447$, $p = 0.001$; unpredictable: $r = -0.305$, $p = 0.032$), classification accuracy significantly improved ($r = -0.448$, $p = 0.010$, best accuracy: 86.667%) under the highly predictable condition, corresponding with enhanced prediction behavior. These results indicate the optimization process of the cognitive resources allocation that supports more efficient interaction and improved predictive performance. Our findings advance the understanding of the mechanisms of decision- feedback interaction.

Abstract Machine learning (ML)- and artificial intelligence (AI)-based aging clocks are increasingly used to quantify physiological and molecular aging from omics and medical imaging data as distinct from chronological age. Here, we characterize a fundamental but underappreciated statistical limitation of commonly used ML/AI regression models for continuous outcomes: systematic prediction bias and its propagation to downstream association estimates. This issue becomes more challenging when the true outcome, biological age, is latent and therefore unobserved during ML/AI model training. We demonstrate that systematic prediction bias can distort and, in some cases, even reverse downstream association analyses that use aging clocks as ML/AI-predicted outcomes to assess their associations with exposures or clinical factors. For example, it can produce spurious associations suggesting that older predicted brain age is linked to better cognitive performance, or that older epigenetic age is associated with better kidney function. To address this problem, we introduce a principled and broadly applicable ML/AI regression framework based on constrained optimization, yielding better calibrated aging-clock estimates and valid downstream inference.

Rumination, characterized by repetitive and self-referential thinking, is closely linked to depression and a broad range of psychiatric disorders. However, previous research has predominantly relied on task activation or network-level approaches, leaving critical gaps in our understanding of local brain activity dynamics during ruminative states. To address this, we employed brain entropy (BEN), a novel functional magnetic resonance imaging (fMRI)-based neuroimaging measure, to quantify the temporal irregularity and complexity of local brain activity during rumination. We analyzed a publicly available dataset comprising 41 healthy adults who completed identical fMRI tasks across three MRI scanners. Each scanning session included four conditions: resting state, sad memory, rumination, and distraction. Voxel-wise BEN analyses were conducted to examine condition-related differences, with brain regions showing consistent patterns across all three scanners at p < 0.05 considered statistically significant. Our findings revealed distinct neural signatures associated with different cognitive states. Compared to sad memory, rumination was associated with decreased BEN in the visual cortex (VC), whereas distraction was associated with decreased BEN in the posterior cingulate cortex/precuneus (PCC/PCu). Furthermore, rumination exhibited significantly increased BEN in the PCC/PCu relative to distraction. These results suggest that rumination is characterized by heightened temporal irregularity in regions supporting internal self-referential processing, accompanied by reduced engagement with external environmental information. The present study demonstrates the utility of BEN in elucidating the neural mechanisms of rumination, providing novel insights into how cognitive states are reflected in local brain activity patterns. These findings carry implications for both theoretical frameworks of ruminative cognition and the development of neuroimaging biomarkers for clinical applications in depression and related disorders.

Recently, conventional domain adaptation (DA) methods have demonstrated promising performance in cross-subject classification in electroencephalogram (EEG)-based brain-computer interfaces (BCIs). However, these methods require direct access to labeled source subject data, potentially compromising biometric privacy. Source-free domain adaptation (SFDA) addresses this issue by leveraging pre-trained source models with prototype-based pseudo-labeling, thereby eliminating the need for source data access. Nevertheless, current SFDA methods rely on oversimplified representations that fail to adequately capture EEG dynamics, resulting in two critical drawbacks: (1) oversimplified representations, using single centroids, fail to adequately capture complex neural manifolds, leading to intra-class collapse; (2) inadequate feature discrimination leads to error propagation in pseudo-labeling. To overcome these challenges, we propose the Adaptive Class-wise Multicentric Prototype-based SFDA (ACMP-SFDA) framework, which improves performance in new subjects while safeguarding personal privacy. Specifically, ACMP-SFDA dynamically constructs multiple prototypes per class to capture non-stationary EEG dynamics. Besides, we integrate semantic contrastive learning to improve inter-class discriminability while preserving the intrinsic structure of intra-class neural manifolds. Extensive experiments conducted across two BCI paradigms (motor imagery and affective BCI) demonstrate that ACMP-SFDA outperforms state-of-the-art methods, achieving 1.36$\%$, 1.96$\%$, and 1.94$\%$ accuracy improvements on MI2014001, MI2015001, and SEED, respectively, in cross-subject tasks.

Mild traumatic brain injury (mTBI) is associated with persistent physical, cognitive, and emotional symptoms, yet the functional brain changes that accompany recovery remain incompletely understood. This longitudinal study investigated brain entropy (BEN), a resting-state measure of irregularity or complexity of spontaneous BOLD activity derived from resting-state functional magnetic resonance imaging (rs-fMRI), during the first year following mTBI. Data of rs-fMRI were acquired from 48 patients with mTBI at the acute (< 14 days), 6-month, and 12-month post-injury visits, and 34 healthy controls (HCs). BEN was quantified using sample entropy. Patients with mTBI also underwent behavioral assessments evaluating quality of life and cognitive function. Behavioral assessments demonstrated progressive improvements in patient-reported quality of life and objective cognitive performance. Cross-sectional analyses revealed dynamic, time-dependent alterations in BEN. Compared with HCs, patients with mTBI exhibited higher BEN in precuneus, temporal, occipital, and sensorimotor regions during the acute and 6-month stages, whereas lower BEN was observed in sensorimotor, occipital, and frontoparietal regions at the 12-month follow-up. Longitudinal analyses demonstrated progressive regional reductions in BEN over time. Several associations between longitudinal changes in regional BEN and cognitive performance were nominally significant, particularly in the precuneus, but none survived multiple comparison corrections. These findings indicate that mTBI recovery is accompanied by dynamic, regionally specific changes in resting state BOLD irregularity. BEN may therefore provide a promising imaging biomarker for tracking the evolving neural dynamics underlying recovery following mTBI.

INTRODUCTION:Cerebral perfusion is implicated in Alzheimer's disease (AD), but its development in AD and mild cognitive impairment (MCI) is not well characterized. METHODS:We constructed a normative model using > 12,000 arterial spin labeling MRI scans and applied generalized additive models for location, scale, and shape (GAMLSS). Individual deviation z scores were derived by normative model, and outlier regions (z ≤ 2.3) were quantified as the total negative proportion (TNP) of extreme hypoperfusion. These metrics were then related to other AD biomarkers through linear modeling. RESULTS:Compared to cognitively normal controls, AD showed higher TNP and greater longitudinal increases (p = 0.003), indicating progressive hypoperfusion. Progressive MCI exhibited greater perfusion decline than stable MCI (p = 0.01). Perfusion changes correlated with cognition, brain volume, amyloid, and apolipoprotein E status (all p < 0.05). DISCUSSION:Normative modeling revealed inter-individual heterogeneity in cerebral perfusion trajectories, underscoring its potential relevance for AD development.

ObjectiveThis study aimed to develop and validate a machine learning model integrating multimodal electroencephalography-functional magnetic resonance imaging (EEG-fMRI) features with clinical biomarkers for predicting post-stroke epilepsy (PSE) risk, thus providing a quantitative tool for early identification of high-risk patients.MethodsA total of 365 acute stroke patients admitted to our hospital from January 2021 to June 2024 were retrospectively enrolled and randomly divided into training (n = 256) and validation (n = 109) sets in a 7:3 ratio. Demographic data, EEG parameters, multimodal MRI indices, and serum biomarkers were collected. In the training set, univariate analysis was first performed to screen relevant factors, followed by LASSO regression for variable selection. Multivariate logistic regression was ultimately used to identify independent risk factors. Based on key predictors, random forest (RF), support vector machine (SVM), and gradient boosting (GB) models were constructed using Python. Model performance was evaluated and optimized via the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). A nomogram was developed for risk visualization, and SHapley Additive exPlanations (SHAP) values were employed for interpretability analysis to quantify the direction and magnitude of feature contributions.ResultsNo significant differences in baseline characteristics were observed between the training and validation sets (P > 0.05), confirming data comparability. Univariate and multivariate logistic regression showed that epileptiform discharge frequency (EDF), background EEG delta wave ratio (BEDWR), stroke lesion volume (SLV), National Institutes of Health Stroke Scale (NIHSS) score, and serum neuron-specific enolase (NSE) levels were independent risk factors for PSE (all P < 0.05). Among the models, RF demonstrated superior predictive performance, with AUCs of 0.892 (training set) and 0.731 (validation set). Interpretability analysis showed that the nomogram enabled individualized risk calculation. SHAP values confirmed EDF (highest mean SHAP value), NIHSS score, and lesion volume as the top three positively contributing features (higher values correlated with increased PSE risk), aligning with regression results and validating clinical rationality.ConclusionAn RF model integrating multimodal data was successfully developed to effectively predict PSE risk. EDF, NIHSS score, SLV, BEDWR, and serum NSE were identified as core predictive indicators.

Arterial spin labeling (ASL) perfusion MRI allows direct quantification of regional cerebral blood flow (CBF) without exogenous contrast, enabling noninvasive measurements that can be repeated without constraints imposed by contrast injection. ASL is increasingly acquired in research studies and clinical MRI protocols. Building on successes in structural imaging, recent efforts have implemented deep learning based methods to improve image quality, enable automated quality control, and derive robust quantitative and predictive biomarkers with ASL derived CBF. However, progress has been limited by variable image quality, substantial inter-site, vendor and protocol differences, and limited availability of labeled datasets needed to train models that generalize across cohorts. To address these challenges, we introduce ICHOR, a self supervised pre-training approach for ASL CBF maps that learns transferable representations using 3D masked autoencoders. ICHOR is pretrained via masked image modeling using a Vision Transformer backbone and can be used as a general-purpose encoder for downstream ASL tasks. For pre-training, we curated one of the largest ASL datasets to date, comprising 11,405 ASL CBF scans from 14 studies spanning multiple sites and acquisition protocols. We evaluated the pre-trained ICHOR encoder on three downstream diagnostic classification tasks and one ASL CBF map quality prediction regression task. Across all evaluations, ICHOR outperformed existing neuroimaging self-supervised pre-training methods adapted to ASL. Pre-trained weights and code will be made publicly available.

The brain entropy (BEN) reflects the randomness of brain activity and is inversely related to its temporal coherence. In recent years, BEN has been found to be associated with a number of neurocognitive, biological, and sociodemographic variables such as fluid intelligence, age, sex, and education. However, evidence regarding the potential relationship between BEN and brain structure is still lacking. In this study, we use resting-state fMRI (rsfMRI) data to estimate BEN and investigate its associations with three structural brain metrics: gray matter volume (GMV), surface area (SA), and cortical thickness (CT). We performed separate analyses on BEN maps derived from four distinct rsfMRI runs, and used a voxelwise as well as a regions-of-interest (ROIs) approach. Our findings consistently showed that lower BEN was related to increased GMV and SA in the lateral frontal and temporal lobes, inferior parietal lobules, and precuneus. We hypothesize that lower BEN and higher SA might reflect higher brain reserve as well as increased information processing capacity.

Oxytocin (OT), a neuropeptide known for its role in social behavior, has unclear neural mechanisms when administered intranasally, especially across different ages. Brain entropy (BEN), a metric of neural irregularity, shows promise for revealing OT’s neurophysiological effects. This study examined whether BEN could detect neural changes induced by intranasal OT and how these effects are modulated by age.In a randomized, double-blind, placebo-controlled trial, young adults (YA) and older adults (OA) were assigned to receive intranasal OT or placebo (PL). Using fMRI-based BEN mapping, we identified a significant age-dependent effect in the left temporoparietal junction (TPJ), where OT increased BEN in YA but decreased it in OA. Further analyses showed OT also elevated the fractional amplitude of low-frequency fluctuations (fALFF) in the same region, particularly in YA. Additionally, OT enhanced functional connectivity within the left TPJ and between the left and right TPJ in both age groups.These results establish BEN as a sensitive biomarker capable of capturing age-specific OT effects, providing information beyond traditional measures of oscillatory power and temporal synchronization. The findings suggest that the timing of post-administration brain state changes under OT may vary with age, potentially due to differences in OT receptor density.

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios.