Brain Informatics最新文献

{"title":"Brain dysconnectivity patterns associated with chronic back pain development.","authors":"Stephan Wunderlich, Enrico Schulz, Florian Ringel, Veit M Stoecklein, Sophia Stoecklein","doi":"10.1186/s40708-026-00328-8","DOIUrl":"10.1186/s40708-026-00328-8","url":null,"abstract":"<p><p>Chronic back pain often emerges from a transitional period of subacute pain, yet no clinically applicable biomarker exists to identify which patients are at risk for chronification. Evidence suggests that this transition is driven not only by nociceptive input but by changes in brain networks involved in valuation, emotion regulation, and learning. Here, we used resting-state functional magnetic resonance imaging (rs-fMRI) and machine learning to explore whether dysconnectivity in these networks is associated with later development of chronic back pain. We analyzed functional connectivity in 46 patients with subacute back pain and 43 healthy controls from a publicly available longitudinal cohort, classifying patients one year later as either recovered or chronified based on pain outcomes. A data-driven model identified a set of six brain regions whose patterns of dysconnectivity distinguished the two patient trajectories with an area under the curve of 0.87. These regions encompass prefrontal, temporal, and somatosensory hubs implicated in reinforcement learning, avoidance behavior, and pain catastrophizing, suggesting a potential link between dysconnectivity patterns and psychological processes implicated in pain persistence. Based on these features, we introduced an exploratory rs-fMRI-based marker for pain chronification, suggesting potential prognostic relevance that requires independent validation before clinical stratification or targeted intervention can be considered.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":"13 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13507019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148819856","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":"CAE-BrainNet: a statistically validated class-adaptive attention ensemble model for explainable brain tumor classification from MRI.","authors":"Mehedi Hasan Meraj, Mashfiquzzaman Tajbid, Mayen Uddin Mojumdar, Narayan Ranjan Chakraborty, Mohammaed Jabed Morshed Chowdhury, Kamanashis Biswas","doi":"10.1186/s40708-026-00325-x","DOIUrl":"10.1186/s40708-026-00325-x","url":null,"abstract":"<p><p>Deep learning has further accelerated progress in automated Magnetic Resonance Imaging (MRI) based classification of brain tumors, whereas prior studies have often reflected critical limitations such as narrow classification scope, insufficient Explainable Artificial Intelligence, weak statistical validation, and incomplete deployment metrics. These ultimately impede clinical trust and practical deployment. This study presents the CAE-BrainNet, a statistically validated Class-Adaptive Attention Ensemble model, which integrates representations of EfficientNetV2-M, DenseNet201, and ConvNeXt-Base dynamically, with complementary inductive biases based on different tumor morphology. Unlike uniform ensembles, a learned class-adaptive attention mechanism, parameterised by a [Formula: see text] weight matrix with a trainable temperature scalar, adaptively leverages model-specific morphological strengths, serving as the primary performance driver confirmed by ablation analysis. A hybrid optimization strategy based on grid search refinement via gradient-based optimization is also employed to estimate optimal hyperparameters. In addition, McNemar's and Cochran's Q tests were conducted, proving that the accuracy gains are statistically significant and not stochastic in nature. Experimental results show that the proposed CAE-BrainNet achieves 99.39% accuracy on a challenging four-class benchmark, with clinically critical 99.89% specificity in the identification of healthy tissue. To overcome the limitations of narrow scope and generalizability, zero-shot transfer assessment on the independent BRISC2025 dataset yields 98.10% accuracy, statistically validated against all base models, confirming cross-dataset robustness without retraining. Quantitative explainability via Grad-CAM, AWCLF, and IoU spatial agreement, combined with formal hypothesis testing and publicly accessible deployment at https://huggingface.co/spaces/Meraj-21/Brain-Tumor-Classification-Using-Grad-CAM , makes CAE-BrainNet a rigorous, transparent, and clinically deployable benchmark for brain tumor classification.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":"13 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13534405/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148875573","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":"Investigating functional brain networks in multiple sclerosis patients: a graph theory approach for evaluating working memory impairment.","authors":"Sareh Yousefi, Mohammad Reza Daliri","doi":"10.1186/s40708-026-00324-y","DOIUrl":"https://doi.org/10.1186/s40708-026-00324-y","url":null,"abstract":"<p><p>This study introduces a graph theory-based machine learning framework to analyze functional brain networks in Multiple Sclerosis (MS) patients during working memory tasks. Using fMRI data from 22 participants (8 MS patients/14 controls) performing a Persian n-back task, we constructed functional connectivity networks with an automated anatomical labeling atlas (116 regions). Novel methodological contributions include: a proportional thresholding approach (5-80% connectivity strength) to optimize network analysis, and extraction of six graph-theoretic features (degree, clustering coefficient, betweenness/eigenvector/page-rank/k-coreness centrality) for classification. Machine learning models (SVM, decision trees, kNN) were trained on task-specific networks (1-back, 2-back, 3-back), with leave-one-subject-out validation. The 3-back task (high cognitive load) yielded superior classification (95.5% accuracy) using SVM with degree, k-coreness, and eigenvector centrality features, outperforming traditional resting-state approaches. Key innovations include identification of the cerebellum (1-back) and orbitofrontal cortex (3-back) as novel discriminative hubs, and demonstration that task difficulty modulates network separability. Results indicate MS patients exhibit impaired high-load connectivity patterns, with the proposed framework showing potential as an auxiliary diagnostic tool. The study provides both a technical blueprint for task-based network analysis and clinically relevant insights into MS-related cognitive impairment, bridging engineering methodologies with neurological applications.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":"13 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13481945/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148799086","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":"Adaptive frequency band attention-guided CNN-BiLSTM for Spatial-Spectral-Temporal EEG emotion recognition.","authors":"Rabita Hasan, Sheikh Md Rabiul Islam","doi":"10.1186/s40708-026-00319-9","DOIUrl":"10.1186/s40708-026-00319-9","url":null,"abstract":"<p><p>Electroencephalography (EEG)-based emotion recognition has gained increasing attention in affective computing because EEG provides high temporal resolution and reflects intrinsic neural activity. However, reliable emotion recognition remains challenging due to the nonlinear, non-stationery and subject-dependent nature of EEG signals. Moreover, many existing methods insufficiently examine temporal overlap effects, treat frequency bands with equal importance, and offer limited spectral interpretability. To address these issues, this study proposes an interpretable Adaptive Frequency Band Attention (AFBA)-guided multi-band 2D CNN-BiLSTM framework for spatial-spectral-temporal EEG emotion recognition using power spectral density (PSD) features. The proposed framework decomposes EEG signals into delta, theta, alpha, beta, gamma and broadband components using Butterworth bandpass filtering. Welch-based PSD features are then extracted and arranged into structured multi-band representations. The AFBA module adaptively learns the relative contribution of each frequency band before spatial-spectral feature extraction through a 2D convolutional neural network and temporal dependency modeling using a BiLSTM network. To assess temporal continuity, 3-s EEG windows with 0 s, 1 s and 2 s overlap are evaluated. The model is tested on the DEAP dataset using leakage-aware trial-level tenfold cross-validation and further validated on SEED under protocol-aligned conditions. Results show that increased temporal overlap improves performance across bands and emotion dimensions. With 2-s overlap, the gamma band achieves 97.2% valence accuracy, 98.1% arousal accuracy and 88.9% four-class accuracy on DEAP, while reaching 94.1% three-class accuracy on SEED. Ablation and SHAP analyses further support the contribution of temporal modeling, AFBA, and high-frequency beta/gamma activity.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13507023/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537402","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":"Decoding neuronal gene expression: integrative insights from omics and AI.","authors":"Aranyak Goswami, Rushikesh R Lagad, Shakil Rafi","doi":"10.1186/s40708-026-00323-z","DOIUrl":"10.1186/s40708-026-00323-z","url":null,"abstract":"<p><p>Neuronal functional diversity and pathological vulnerability are governed by multi-layered regulatory programs. While high-throughput omics and neuroimaging provide high-resolution snapshots of these programs, bridging the gap between molecular dynamics and macro-scale brain architecture remains a significant informatics challenge. This review synthesizes the evolution of computational frameworks in neuro-omics-transitioning from descriptive co-expression modules to causal graph neural networks and cross-scale foundation models. We evaluate these methodologies within the context of Alzheimer's disease, schizophrenia, and epilepsy, identifying critical bottlenecks in data harmonization, spatial alignment, and causal interpretability.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13481912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537322","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":"Effiformer: a unified data-efficient vision transformer-CNN framework for interpretable epileptic seizure detection.","authors":"Aaranay Aadi, Divyansh Sukhija, Rishabh Shetty, Praveen Shukla, Vijaypal Singh Dhaka","doi":"10.1186/s40708-026-00320-2","DOIUrl":"10.1186/s40708-026-00320-2","url":null,"abstract":"<p><p>Epileptic seizures are short episodes of abnormal electrical activity in the brain that can cause convulsions, loss of consciousness, and other similar symptoms. Despite therapy, around 30% of patients with epilepsy continue to have seizures, emphasizing the necessity for quick and effective detection measures. Accurate seizure detection allows for prompt intervention, which dramatically improves patient safety. This study has developed EffiFormer, a hybrid Vision Transformer-CNN model for reliable seizure detection using Electroencaphelogram (EEG) spectrograms. EffiFormer combines spatial feature extraction from EfficientNet with global attention mechanisms from the Data-Efficient Image Transformer, resulting in high accuracy even with limited training data. Our four-phase pipeline processes raw EEG signals through normalization, Short-Time Fourier Transform (STFT) to create spectrograms, synthetic seizure sample generation using SMOTE, and data augmentation. This study utilized a standard 60-20-20 training-validation-testing split for effectively training our proposed architecture and validating its accuracy. Further, this study tests the technique using the CHB-MIT dataset, which is a publicly available collection of long-term scalp EEG recordings from 22 pediatric patients at Children's Hospital Boston and covers a wide spectrum of seizure and non-seizure episodes. With an average sensitivity of 99.8% and average accuracy of 99.3%, our approach offers accurate seizure detection in various scenarios. Furthermore, explainable AI (XAI) approaches emphasize EEG regions that influence the model's results, making the model's decision-making process more transparent and interpretable for potential clinical review.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13481616/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537326","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":"Hybrid self-supervised EEG emotion representation: masked reconstruction joint with mutual information bounds.","authors":"Haoyu Liu, Xinyu Li, Haiyan Zhou, Jiajin Huang","doi":"10.1186/s40708-026-00322-0","DOIUrl":"10.1186/s40708-026-00322-0","url":null,"abstract":"<p><p>EEG signals are widely used in affective computing and brain informatics for emotion recognition due to their non-invasiveness. Deep learning and self-supervised learning (SSL) are key for EEG representation learning: masked reconstruction captures structural information, while contrastive learning extracts invariant semantic features via maximizing mutual information (MI). However, existing methods lack MI upper-bound constraints, leading to difficulty balancing structural fidelity and semantic discriminability. To address this issue, we propose HybridMI-EEG, a hybrid self-supervised framework for EEG emotion recognition. Built on a Transformer encoder-decoder, it integrates masked reconstruction and MI bound optimization into a three-component synergistic architecture. Specifically, raw EEG signals are decomposed into patch embeddings; a random continuous masking strategy on the embeddings drives reconstruction via contextual information. A dual-objective loss maximizes inter-view consistency and minimizes input-latent redundancy, while learnable augmenters generate informative contrastive views to enable synergistic optimization of local structure and global semantics. Experiments on DEAP and DREAMER datasets show that HybridMI-EEG outperforms state-of-the-art baselines in accuracy and stability, providing an effective solution to enhance EEG representation learning and emotion classification performance.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13391463/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148521220","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":"EEG-DBNet: a dual-branch framework for temporal-spectral representation learning of motor imagery electroencephalography.","authors":"Youxi Qu, Xicheng Lou, Hongying Meng, Zhangyong Li, Jianlin Wang, Kunpeng Mao, Xinwei Li","doi":"10.1186/s40708-026-00321-1","DOIUrl":"10.1186/s40708-026-00321-1","url":null,"abstract":"<p><strong>Purpose: </strong>Motor imagery electroencephalography (MI-EEG) decoding remains challenging due to low signal-to-noise ratio and complex temporal-spectral characteristics. This study aims to develop a robust deep learning framework for effective EEG representation learning.</p><p><strong>Methods: </strong>We propose EEG-DBNet, a dual-branch neural network that jointly models temporal dynamics and spectral representations of EEG signals. The model integrates local and global convolutional modules to enable multi-scale feature extraction, complementing the dual-branch design for multi-dimensional temporal-spectral representation learning. To validate robustness, experiments are conducted on two public datasets as well as a self-collected MI-EEG dataset acquired under controlled laboratory conditions.</p><p><strong>Results: </strong>Experimental results show that EEG-DBNet achieves the best average performance on the two public benchmark datasets, BCI Competition IV-2a and IV-2b. On the self-collected CQUPT dataset, EEG-DBNet obtains competitive performance compared with representative baseline methods, suggesting its potential applicability to laboratory-acquired MI-EEG decoding. These results indicate that the proposed temporal-spectral dual-branch design is effective, while further validation on larger self-collected datasets is still needed.</p><p><strong>Conclusion: </strong>The proposed EEG-DBNet provides an effective solution for MI-EEG decoding with improved robustness. The inclusion of multiple datasets, particularly laboratory-acquired self-collected data, highlights its potential for practical brain-computer interface applications.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13391462/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148473324","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":"Cross-attention-guided subject-adaptive graph learning for multimodal autism classification: integrating structural and functional MRI data.","authors":"Yan Tang, Chao Yang, Yihang Xu, Hao Zhang, Hua Xie","doi":"10.1186/s40708-026-00318-w","DOIUrl":"10.1186/s40708-026-00318-w","url":null,"abstract":"<p><p>Autism spectrum disorder (ASD) is a complex neurodevelopmental condition marked by structural atypicality and abnormal functional connectivity. It remains challenging to accurately delineate an ASD-associated neural marker due to individual heterogeneity and multi-site data variability. To address these issues, we propose a cross-attention-guided subject-adaptive graph network (CAS-GNN) model that integrates structural MRI and resting-state functional connectivity data, effectively fusing complementary multimodal information. By modeling individualized brain network topologies and incorporating a site-invariant learning strategy, our approach enhances discriminability and cross-site generalization. On the ABIDE-I dataset, CAS-GNN significantly outperformed machine learning baselines and achieved an accuracy of 79.25% ± 4.71% on independent test data and an average accuracy of 78.75% ± 1.56% on five-fold cross-validation. Exploratory analyses identified key ASD-related brain regions and connections, revealing a notable right-hemisphere dominance consistent with atypical asymmetry in ASD. Our framework offers valuable neurobiological insights and provides a promising tool for interpretable and robust ASD diagnosis, accelerating biomarker discovery and development.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":"13 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13350566/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148413163","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":"Generalizable and explainable deep learning for brain MRI: a multi-cohort evaluation of 3D architectures for age and sex prediction.","authors":"Radhika Juglan, Marta Ligero, Zunamys I Carrero, Asier Rabasco Meneghetti, Tim Lenz, Leo Misera, Gregory Patrick Veldhuizen, Paul Kuntke, Hagen H Kitzler, Sven Nebelung, Daniel Truhn, Jakob Nikolas Kather","doi":"10.1186/s40708-026-00316-y","DOIUrl":"10.1186/s40708-026-00316-y","url":null,"abstract":"<p><p>Deep learning (DL) methods increasingly outperform classical approaches in brain MRI analysis, yet their generalizability across independent imaging cohorts remains insufficiently evaluated. Because age and sex are fundamental neurobiological factors influencing brain structure and disease risk, this study systematically compares three three-dimensional architectures-Simple Fully Convolutional Network (SFCN), DenseNet121, and Swin Transformer-for age and sex prediction using T1-weighted MRI from four independent cohorts: UK Biobank (UKB, n = 47,390), Dallas Lifespan Brain Study (DLBS, n = 132), Parkinson's Progression Markers Initiative (PPMI, n = 108 controls), and Information eXtraction from Images (IXI, n = 319). SFCN consistently demonstrated the most robust performance. For sex classification, it achieved an AUC of 1.00 [1.00-1.00] in the UKB internal test set and 0.85-0.91 across external cohorts. For age prediction, SFCN achieved a mean absolute error (MAE) of 2.66 years (r = 0.89) internally and 4.98-5.81 years (r = 0.55-0.70) externally. Pairwise DeLong and Wilcoxon tests with Bonferroni correction confirmed significantly better performance of SFCN compared with Swin Transformer in most cohorts (p < 0.017). No significant demographic subgroup biases were observed. Explainability analyses further showed task-specific and spatially consistent attention patterns across cohorts. These findings demonstrate that simpler convolutional architectures can generalize more reliably than more complex attention-based models in multi-cohort settings. The study highlights the importance of external validation and emphasizes potential trade-offs between model complexity, robustness, and interpretability for clinically relevant neuroimaging applications.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13342005/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148391981","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}