Search Results (1,783)

Background: Previous work from our group demonstrated an association between immunohistochemical detection of Human cytomegalovirus (HCMV) late antigen and poor event-free survival (EFS) in pediatric medulloblastoma. Whole-genome sequencing (WGS) further identified increased abundance of HCMV-aligned reads at the UL88 locus, particularly in Group 3 tumors, a molecular subgroup associated with aggressive clinical behavior and poor prognosis. Methods: We performed an integrated multi-omics analysis of pediatric medulloblastoma using WGS (n = 39) and RNA sequencing (RNA-seq; n = 28) datasets. RNA-seq data were filtered using stringent alignment criteria (MAPQ ≥ 20) and compared with fetal brain (n = 12), adult brain (n = 12), and HCMV-infected cell culture controls (n = 3). Only high-confidence uniquely aligned reads were retained to reduce nonspecific and multi-mapped viral alignments. Sequencing reads were aligned to the HCMV Merlin reference genome (NC_006273.2) using a standardized analytical pipeline. A subset of 28 cases with matched tumor WGS, tumor RNA-seq, and germline WGS data was used for integrated multi-omics analyses. Orthogonal validation analyses were performed in Group 3 tumors using independent genomic and transcriptomic approaches. Exploratory survival analyses were conducted in a combined cohort (n = 84) integrating genomic and immunohistochemical datasets. Results: Recurrent low-level HCMV-aligned molecular signals were identified across medulloblastoma datasets. Reads aligning to UL76, UL88, and UL99 were the most consistently detected HCMV-associated late-gene signals across RNA-seq and WGS datasets. A composite HCMV late-gene signature (UL76–UL88–UL99) showed higher levels in Group 3 tumors than in other molecular subgroups (p < 0.05 in WGS analyses). Orthogonal analyses demonstrated concordant low-level HCMV-associated genomic and transcriptomic signals enriched in tumors with MYC-associated activation and chromosome 17 imbalance. In the combined cohort (n = 84), elevated HCMV-associated signal assessed by immunohistochemistry and genomic profiling was associated with reduced EFS (median 55 vs. 147 months; log-rank p < 0.001). The subgroup classified as HCMV-high Group 3 demonstrated the strongest association with adverse outcome in exploratory multivariable analyses (HR = 6.43, p = 0.002). Conclusions: This study identifies recurrent low-level HCMV-associated genomic and transcriptomic signals across pediatric medulloblastoma datasets, with preferential enrichment in biologically aggressive Group 3 tumors. Although the extremely low abundance of viral-aligned reads precludes definitive evidence of productive viral infection, the reproducible detection of HCMV-associated molecular signatures across independent sequencing platforms supports further investigation into a potential oncomodulatory association in pediatric medulloblastoma. Additional validation using optimized viral detection methodologies, independent cohorts, and mechanistic studies will be necessary to clarify the biological and clinical significance of these findings. Full article

Early diagnosis of post-traumatic epilepsy (PTE) is crucial for timely intervention. However, it is hampered by the lack of reliable biomarkers. In this review, we provide a comprehensive summary of current advances in PTE biomarker research, drawing primarily on evidence from human cohort studies, with selective support from experimental animal models where mechanistic insights are required. We cover (i) neuroimaging, including CT, MRI, and EEG/qEEG, which reveal structural and functional alterations associated with epileptogenesis; (ii) molecular biomarkers, including RNAs, proteins, metabolites, and extracellular vesicle (EV)-derived molecules that reflect neuroinflammation, blood–brain barrier (BBB) dysfunction, neuronal injury, and synaptic remodeling; and (iii) artificial intelligence (AI)-assisted approaches, which integrate multimodal datasets to identify complex predictive patterns. While individual modalities offer valuable but incomplete prognostic information, AI-driven analytics hold the greatest promise for early predictive power by combining multimodal data. Future progress will depend on the integration of high-resolution imaging, multi-omics profiling, and rigorous validation to deliver clinically actionable biomarker panels and ultimately reduce the burden of PTE. Full article

Background/Objectives: Brain magnetic resonance imaging (MRI) is an important imaging modality for assessing neurological disorders. However, automatic multi-class MRI classification remains challenging because of visual similarity between disease categories, heterogeneous pathological patterns, class imbalance, and the need for reliable confidence estimation. This study aims to develop a comprehensive and well-calibrated deep learning framework for image-level brain MRI classification across multiple neurological categories. Methods: This paper introduces a new deep learning framework, MCND-ComputeNet++, for brain MRI classification into eight image-level categories using the MCND dataset, which comprises 16,400 two-dimensional brain MRI images belonging to eight diagnostic categories: AD-MildDemented, AD-ModerateDemented, AD-VeryMildDemented, BT-glioma, BT-meningioma, BT-pituitary, MS, and Normal. The proposed model uses a single pretrained EfficientNetV2-S backbone to extract hierarchical feature maps from three intermediate stages. These multi-level features are projected into a common latent space, spatially aligned, adaptively fused through learnable gated multi-scale fusion, further refined using convolutional processing, and aggregated using spatial attention pooling before classification. The training strategy combines class-balanced focal loss with label smoothing, MixUp/CutMix regularization, exponential moving average weight smoothing, warmup cosine learning-rate scheduling, temperature scaling, and test-time augmentation to improve generalization and calibration. The framework was evaluated using accuracy, precision, recall, macro-F1, macro-AUC, macro-average precision, expected calibration error, Brier score, bootstrap confidence intervals, ablation analysis, McNemar testing, and comparisons against standard pretrained baseline models. Results: MCND-ComputeNet++ achieved mean accuracy, macro-F1, macro-AUC, and macro-average precision values of 0.9738, 0.9771, 0.9993, and 0.9971, respectively, with narrow bootstrap confidence intervals indicating stable image-level performance. These findings should be interpreted as image-level/slice-level performance on MCND, because patient-level identifiers and subject-wise splitting were not available. These results outperformed most evaluated baselines, including ResNet50, DenseNet121, EfficientNetB0, EfficientNetV2-S with a standard classifier, Swin-Tiny, and ConvNeXt-Tiny, across several discrimination and calibration metrics. Compared with ConvNeXt-Tiny, the proposed model achieved higher macro-AUC and macro-average precision, together with a lower ECE and Brier score, suggesting improved image-level discrimination and confidence reliability. Compared with the EfficientNetV2-S standard classifier, accuracy increased from 0.9308 to 0.9738, while the Brier score decreased from 0.1045 to 0.0400. Conclusions: The results suggest that MCND-ComputeNet++ is a promising image-level brain MRI classification framework for the eight MCND categories. The proposed model integrates hierarchical feature extraction, shared latent projection, gated multi-scale fusion, convolutional refinement, spatial attention pooling, and calibrated inference within a unified architecture. However, because the current evaluation was conducted at the image/slice level without available patient-level identifiers, the findings should not be interpreted as patient-level clinical diagnostic validation. Further studies using subject-wise splitting, external multi-center datasets, 3D volumetric modeling, and multimodal clinical information are required to assess generalizability and potential clinical decision-support applicability. Full article

Background: Brain-derived neurotrophic factor (BDNF) is crucial in the nociception and mechanisms underlying chronic and neuropathic pain. The evaluation of circulating BDNF in patients with multimodal analgesia has not been reported previously. We hypothesized that opioid-based multi-analgesia induces changes in BDNF values and that BDNF correlates with pain intensity in neuropathic pain. Methods: Adult patients who met low back pain (LBP) criteria and received multimodal opioid-based therapy were included. The control group included patients with LBP who did not receive any pharmacotherapy. Plasma measurements obtained with the ELISA test were analyzed. The study was registered at Clinical Trials.gov (NCT 04227223). Results: Patients with multimodal opioid-based analgesia had significantly higher BDNF values compared to the monotherapy: 3.6 ng/mL vs. 2.7 ng/mL, p = 0.01. No statistical differences were observed compared to the non-pharmacologically treated group: 3.6 ng/mL vs. 5.0 ng/mL, p = 0.75. The median BDNF values were lowest in the mild-pain group, and significant differences were observed between the severe and moderate-pain groups (p = 0.006) and the mild-pain group (p = 0.0001). BDNF was significantly higher in the neuropathic-pain group compared to the group of patients without neuropathic pain (p = 0.0005). A significant correlation was demonstrated between the BDNF and numerical rating pain score (NRS) in the neuropathic-pain component (rho = 0.6, p = 0.001). Conclusions: Multimodal opioid-based analgesia decreases plasma BDNF concentrations less than opioid monotherapy, which offers an opportunity to limit opioid-induced adverse effects. BDNF influences pain intensity and predicts neuropathic pain in multimodal opioid-based analgesia. Full article

With the development of Internet of Things (IoT) technology, fire detection systems based on multi-sensor fusion have become critical infrastructure to ensure public safety. Due to environmental noise and sensor heterogeneity, these systems often suffer from high rates of false alarms and missed detections. Although existing machine learning approaches have partially improved classification accuracy, their overall performance remains limited. Inspired by the cognitive mechanisms of the human brain, we developed an improved mind-linked continuous-coupled neural network (ML-CCNN) based on the existing continuous-coupled neural network (CCNN). We propose a parameter adaptation mechanism that modulates neural activations through a global threshold. We utilized the synthetic minority oversampling technique (SMOTE) to mitigate data imbalance and transformed sample feature vectors into matrices for training. Our model achieved an accuracy of 99.96% on our own dataset and 99.97% on the public Smoke Detection Dataset (SDD), which highlights ML-CCNN’s potential for fire detection. Full article

Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental condition. Growing evidence suggests that the gut–brain axis may contribute to its pathophysiology. However, findings regarding gut microbiota alterations in ADHD remain inconsistent. This systematic review aimed to synthesize the current evidence on the gut microbiota composition and microbial diversity in individuals with ADHD. A systematic search of PubMed, Scopus, and Web of Science was conducted up to 31 December 2025 following PRISMA guidelines, yielding 562 studies. Twenty-three studies published between 2015 and 2025 were included. Most studies reported no significant differences in alpha-diversity in ADHD and control groups. More consistently, beta-diversity analysis reported significant differences in microbial composition between ADHD and control groups. ADHD was often associated with a reduced abundance of Alistipes and butyrate producers such as Faecalibacterium and increased abundance of Roseburia and Agathobacter. Some longitudinal studies suggested that distinct early-life microbial patterns may precede the ADHD diagnosis. ADHD appears to be associated with alterations in the gut microbiota, particularly in taxa involved in short-chain fatty acid production and immune regulation. However, findings remain inconsistent due to methodological heterogeneity and potential confounding factors. Future research should prioritize longitudinal multi-omics approaches to clarify causal mechanisms and refine microbiota-targeted interventions. Full article

Brain tumor segmentation from 3D MRI presents significant challenges due to small lesion sizes, ambiguous boundaries, arbitrary spatial distributions, and heterogeneous morphological properties. To tackle these issues, this paper presents a fully automatic 3D brain tumor segmentation network that integrates morphological and anatomical information under a multi-task learning framework for whole tumor, tumor core, and enhanced tumor segmentation. We propose a multimodal feature fusion module to adaptively weight features from four MRI modalities (T1, T1ce, T2, FLAIR), enabling discriminative information integration and helping reduce modality intensity discrepancy and data imbalance. Furthermore, a ConvReXt downsampling module is introduced to preserve fine-grained semantic details by reducing information loss caused by conventional pooling. A dense parallel global attention module is also developed to capture both local details and long-range dependencies, addressing the limited receptive field of standard convolutions. Extensive experiments on the BraTS2020 dataset show that the proposed model obtains average Dice coefficients of 92.54%, 89.21%, and 86.54% for whole tumors, tumor cores, and enhanced tumors. The proposed model achieves competitive performance compared with state-of-the-art methods including nnFormer, validating that it can effectively fuse multimodal and multi-scale features and improve brain tumor segmentation accuracy. Full article

Gliomas constitute the majority of primary brain tumors, and accurate diagnosis through MRI is essential for patient management. Existing computer-aided diagnosis approaches frequently rely on tumor segmentation frameworks. In this study, a segmentation-independent framework for volumetric low-grade versus high-grade glioma (LGG/HGG) classification is proposed using a Convolutional Neural Network (CNN) designed through task-oriented Neural Architecture Search (NAS). The proposed method was evaluated on a multi-center dataset comprising 1194 patients with pre-operative MRI scans, including T1-CE and FLAIR sequences from four publicly available cohorts. NAS was conducted within a controlled search space to optimize a 3D U-Net–based backbone using Tree-structured Parzen Estimator (TPE) combined with Hyperband pruning. The optimized backbone was enhanced with residual connections and Squeeze-and-Excitation (SE) attention mechanisms to improve feature representation and training stability. Internal validation employed repeated 5-fold cross-validation across all four multi-center datasets. An external experiment used REMBRANDT as a test cohort (49 LGG, 19 HGG). The proposed model achieved 88.25% internal accuracy and 75.51% external accuracy (macro-F1: 87.37% internal, 73.77% external), outperforming benchmark 3D CNNs. Explainable Artificial Intelligence (XAI) analysis based on Grad-CAM revealed robust tumor localization without segmentation supervision, validated against available ground-truth masks. Additional experiments demonstrated the model’s generalization capacity, achieving 89.51% accuracy for IDH mutation prediction and 78.74% for multi-grade classification. Full article

Martian periglacial landforms are among the clearest surface clues for investigating ground-ice occurrence, climate evolution, and potential habitability on Mars. Utopia Planitia contains abundant ice-related landforms and is therefore well suited to regional-scale mapping of periglacial features. However, most existing identifications still rely heavily on manual interpretation, which is time-consuming and difficult to keep consistent across large image mosaics. In this paper, using Context Camera (CTX) imagery, a dataset of four representative landform types in Utopia Planitia, namely flat-floored depressions, thermal contraction cracks, scalloped depressions, and brain terrain, was built. A Multi-scale Texture-enhanced U-Net (MTU-Net) was then developed as an automated and standardized mapping solution for semantic segmentation of these landforms. The model incorporates hierarchical attention and multi-scale texture enhancement modules, enabling recognition under complex backgrounds where fine-scale landforms such as thermal contraction cracks and brain terrain exhibit only weak textural details, alongside large scale variations. On the held-out test set, MTU-Net reaches a mean intersection over union (mIoU) of 89.55%, a mean F1-score of 94.71%, and a Kappa coefficient of 91.21%, outperforming the baseline U-Net under the same evaluation protocol. The resulting regional maps show marked spatial heterogeneity in the occurrence of the four landform types across Utopia Planitia. This study provides a methodological basis for automated periglacial landform mapping in Mars. Full article

Alzheimer’s disease (AD) is a global health challenge requiring early and accurate diagnosis, yet current clinical methods struggle with early stages. Deep learning approaches for MRI-based diagnosis face persistent challenges related to image quality issues, limited model generalization, and subtle inter-class variations. To address these limitations, this paper proposes a robust, end-to-end brain MRI-based framework for multi-class classification of AD stages. Positioned within the broader research priority of artificial intelligence and intelligent healthcare technologies, the proposed methodology incorporates an attention-based ensemble of deep learning models alongside an enhanced image preprocessing that uses Real-ESRGAN to mitigate common compression and resolution degradations in 2-D MRI slices. The ensemble makes use of the superior capabilities of the Swin Transformer to capture global contextual dependencies and EfficientNet-B3/MobileNetV2 for effective multi-scale feature extraction, with feature fusion performed using a Squeeze-and-Excitation attention mechanism. The experiments were performed on a publicly available Alzheimer’s MRI dataset, resulting in classification accuracy of 94.47% and 92.28% for the two proposed frameworks. The robustness and clinical interpretability of the framework are emphasized through comprehensive metrics and qualitative analysis. This framework demonstrates promising benchmark performance on a standardized public dataset, highlighting the potential of cross-paradigm ensembles combined with super-resolution preprocessing. Full article

Steady-state visual evoked potential-based brain–computer interfaces (SSVEP-BCIs) are widely applied in non-invasive brain–computer interaction, yet traditional single-frequency coding suffers from scarce frequency resources and degraded accuracy in multi-target tasks. The partitioned backlight mode (PB-M) supports SSVEP spatial coding, while systematic investigations on its inherent backlight crosstalk are still lacking. This study develops a PB-M-based SSVEP-BCI system to explore crosstalk mechanisms. Each participant completed 90 valid trials with 18 stimuli and five repetitions each. The results verify inter-partition crosstalk, which can reduce recognition accuracy under narrow frequency intervals and non-isolated layouts, and gaze position can modulate non-target SSVEP responses. Classification accuracy was calculated by valid correct trial ratios, and the information transfer rate (ITR) was computed using standard BCI formulas, yielding 87.50% accuracy and 48.75 bits/min ITR. Full exhaustive classification testing across all 18 stimulus targets was not implemented, where core classification validation was performed on partially selected targets. The proposed frequency reuse strategy shows promising potential to improve SSVEP-BCI performance based on empirical experimental data, providing valid references for multi-target BCI design. Full article

Introduction: Three-dimensional deep learning offers promise for automated accurate brain tumor segmentation and survival prediction but requires robust validation across multiple MRI modalities to be effectively implemented in clinical practice. Methods: This study presents a comprehensive 3D deep learning framework using 369 cases from the BraTS2020 dataset. A 3D U-Net architecture was developed for tumor segmentation utilizing combined imaging data and optimized for computational efficiency and memory. The final 3D U-Net model segmentations were used to build machine learning 6-month and 12-month survival classifiers. Segmentation models were evaluated using multiple metrics, including the Dice Similarity Coefficient, Hausdorff Distance, and Cohen’s d. The classification models were evaluated using AUC-ROC and balanced accuracy. Results: Segmentation achieved a modest, but promising, performance across 30 epochs and with 295 training patients, achieving the best mean validation Dice = 0.8388 and a final-epoch mean Dice of 0.8263. Survival classification with a hybrid clinical and imaging logistic regression showed promising results, with 12-month prediction achieving AUC = 0.746 and 69% accuracy. The top contributing features for the 12-month prediction classifier were extent of resection, T1 contrast-enhanced tumor median, and FLAIR tumor median. Conclusions: This comprehensive framework demonstrates that a multi-modal approach provides meaningful performance gains, while segmentation-derived features show a promising ability to enable survival prediction. Full article

Background: Rare neurological diseases are challenging to diagnose from brain MRI because of their low prevalence, heterogeneous imaging patterns, and limited annotated datasets. Deep learning may support image-level recognition, but results from curated datasets without complete patient-level identifiers require cautious interpretation. Objectives: This study proposes RareNeuroXNet, a frequency-aware multi-branch attention framework for image-level classification of rare neurological diseases from brain MRI. The objective was to assess whether combining global anatomical, local fine-grained, and frequency-domain representations improves benchmark performance, calibration, and interpretability. Methods: RareNeuroXNet uses three complementary branches: a global branch for whole-image representation, a local branch for regional feature extraction, and an FFT magnitude-based frequency branch. Features are refined using CBAM attention, fused, and classified through a fully connected head. The model was evaluated on a balanced curated dataset with five rare neurological disease classes using five-fold cross-validation, ablation analysis, calibration metrics, internal baseline comparison, paired testing against DenseNet121 local-only, and Grad-CAM visualization. MCND was also used as a complementary cross-dataset neurological MRI benchmark, not as same-task external validation. Results: RareNeuroXNet achieved strong image-level internal benchmark performance, with accuracy of $0.9924\pm 0.0061$, macro F1-score of $0.9924\pm 0.0061$, macro AUROC of $0.9998\pm 0.0002$, and macro AUPR of $0.9992\pm 0.0007$. Calibration was favorable, with ECE of $0.0052\pm 0.0029$ and NLL of $0.0276\pm 0.0159$. Ablation results showed that the local branch was the dominant contributor, while FFT and CBAM provided supportive refinement. Compared with DenseNet121 local-only, RareNeuroXNet showed modest classification gains and clearer calibration improvements. Conclusions: RareNeuroXNet demonstrated strong controlled image-level benchmark performance with high discrimination, stable cross-validation behavior, favorable calibration, and Grad-CAM interpretability. However, possible correlated slices, duplicate images, or subject overlap cannot be excluded. Future work should use patient-level, same-task, multi-center external validation and 3D multimodal MRI analysis. Full article

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder for which early and accurate diagnosis remains a critical challenge. In this work, we propose a Multi-ROI Multimodal 3D Vision Transformer for AD classification that integrates structural MRI data with clinical and volumetric biomarkers within a unified attention-based framework. The proposed approach leverages anatomically guided multi-region-of-interest (ROI) decomposition to focus on disease-relevant brain structures, including the hippocampus, entorhinal cortex, fornix, and major cortical lobes. Each ROI is encoded using 3D tubelet embeddings, while clinical and volumetric features are transformed into feature-wise tokens, enabling seamless multimodal fusion through self-attention mechanisms. A hemisphere-aware selection strategy is introduced to identify the most discriminative ROI representations, enhancing both performance and interpretability. The model is evaluated on a merged multi-cohort dataset combining ADNI, AIBL, and OASIS using a 7-fold cross-validation protocol. Experimental results demonstrate that the proposed method achieves high classification performance, reaching an accuracy of 97.62% and an AUC of 0.9940, outperforming single-modality and whole-brain baselines. Furthermore, attention-based analysis provides interpretable insights into the relative importance of clinical and neuroanatomical features, revealing consistency with established AD biomarkers. These findings highlight the effectiveness of multimodal integration and ROI-based representation for robust and explainable AD classification. Full article

Background/Objectives: Brain tumor analysis using magnetic resonance imaging (MRI) remains a challenging task due to tumor heterogeneity, complex anatomical structures, and reliance on expert interpretation. Although deep learning approaches have shown promising results in medical image analysis, many existing studies focus on either tumor classification or segmentation independently, limiting their applicability in comprehensive automated brain tumor analysis workflows. This study proposes an integrated dual-task deep learning framework for automated brain tumor classification and segmentation using MRI scans. The framework aims to provide complementary diagnostic support by combining tumor-type prediction and tumor boundary delineation within an integrated workflow. Methods: The proposed framework utilizes EfficientNet-based convolutional neural networks for multi-class brain tumor classification and U-Net++ architectures with EfficientNet encoders for tumor segmentation. Experiments were conducted using the BRISC2025 dataset, consisting primarily of 6000 T1-weighted 2D MRI slices collected from axial, coronal, and sagittal planes. Standard preprocessing, augmentation, transfer learning, and selective fine-tuning strategies were applied. Multiple architectures were systematically evaluated using evaluation metrics. Results: EfficientNet-B1 achieved a classification accuracy of 99.70% with near-perfect precision, recall, and F1-scores across glioma, meningioma, pituitary tumor, and no-tumor classes. For segmentation, U-Net++ with an EfficientNet-B1 encoder achieved a Dice score of 0.9055, an IoU score of 0.8442, and an HD95 value of 12.21 pixels on the held-out test set. The proposed framework demonstrated robust performance in detecting small and low-contrast tumor regions while maintaining strong generalization performance across diverse MRI samples. Conclusions: The proposed integrated framework demonstrated strong performance in both brain tumor classification and segmentation tasks, effectively detecting small and low-contrast tumor regions while maintaining good generalization across diverse MRI samples. These findings suggest that the framework may serve as a reliable decision-support tool for automated brain tumor analysis in clinical practice. Full article