Search Results (1,749)

Background/Objectives: Accurate diagnosis of brain tumors is one of the most important challenges in neuro-oncology since tumor classification and volumetric segmentation inform treatment planning. Two-dimensional classification and three-dimensional segmentation deep learning models can augment radiological workflows, particularly if paired with explainable AI techniques to improve model interpretability. The objective of this research was to develop a web-based brain tumor segmentation and classification diagnosis platform. Methods: A diagnosis system was developed combining 2D tumor classification and 3D volumetric segmentation. Classification employed a fine-tuned MobileNetV2 model trained on a glioma, meningioma, pituitary tumor, and normal control dataset. Segmentation employed a SegResNet model trained on BraTS multi-channel MRI with synthetic no-tumor data. A meta-classifier MLP was used for binary tumor detection from volumetric features. Explainability was offered using XRAI maps for 2D predictions and Gaussian overlays for 3D visualizations. The platform was incorporated into a web interface for clinical use. Results: MobileNetV2 2D model recorded 98.09% classification accuracy for tumor classification. 3D SegResNet obtained Dice coefficients around 68–70% for tumor segmentations. The MLP-based tumor detection module recorded 100% detection accuracy. Explainability modules could identify the area of the tumor, and saliency and overlay maps were consistent with real pathological features in both 2D and 3D. Conclusions: Deep learning diagnosis system possesses improved brain tumor classification and segmentation with interpretable outcomes by utilizing XAI techniques. Deployment as a web tool and a user-friendly interface made it suitable for clinical usage in radiology workflows. Full article

Background: Brain health is a growing public health priority due to the high global burden of neurological and mental disorders. Promoting brain health across the lifespan supports individual and societal well-being, creativity, and productivity. Objective: To address the need for specialized education in this field, the University of Bern developed a Certificate of Advanced Studies (CAS) in Brain Health. This article outlines the program’s rationale, structure, and goals. Program Description: The one-year, 15 ECTS-credit program is primarily online and consists of four modules: (1) Introduction to Brain Health, (2) Brain Disorders, (3) Risk Factors, Protective Factors and Interventions, and (4) Brain Health Implementation. It offers a multidisciplinary, interprofessional, life-course approach, integrating theory with practice through case studies and interactive sessions. Designed for healthcare and allied professionals, the CAS equips participants with skills to promote brain health in clinical, research, and public health contexts. Given the shortage of trained professionals in Europe and globally, the program seeks to build a new generation of brain health advocates. It aims to inspire action and initiatives that support the prevention, early detection, and management of brain disorders. Conclusions: The CAS in Brain Health is an innovative educational response to a pressing global need. By fostering interdisciplinary expertise and practical skills, it enhances professional development and supports improved brain health outcomes at individual and population levels. Full article

Background: Transcranial direct current stimulation (tDCS) has emerged as a promising neuromodulatory tool for language rehabilitation in chronic aphasia. However, the effects of bi-hemispheric, multisite stimulation remain largely unexplored, especially in people with chronic and treatment-resistant language impairments. The goal of this study is to look at the effects on behavior and brain activity of an individualized language training program that combines bi-hemispheric multisite anodal tDCS with personalized language training for Albert, a patient with long-standing, treatment-resistant non-fluent aphasia. Methods: Albert, a right-handed retired physician, had transcortical motor aphasia (TCMA) subsequent to a left-hemispheric ischemic stroke occurring more than six years before the operation. Even after years of traditional treatment, his expressive and receptive language deficits remained severe and persistent despite multiple rounds of traditional therapy. He had 15 sessions of bi-hemispheric multisite anodal tDCS aimed at bilateral dorsal language streams, administered simultaneously with language training customized to address his particular phonological and syntactic deficiencies. Psycholinguistic evaluations were performed at baseline, immediately following the intervention, and at 1, 2, 3, and 6 months post-intervention. Resting-state fMRI was conducted at baseline and following the intervention to evaluate alterations in functional connectivity (FC). Results: We noted statistically significant enhancements in auditory sentence comprehension and oral reading, particularly at the 1- and 3-month follow-ups. Neuroimaging showed decreased functional connectivity (FC) in the left inferior frontal and precentral regions (dorsal stream) and in maladaptive right superior temporal regions, alongside increased FC in left superior temporal areas (ventral stream). This pattern suggests that language networks may be reorganizing in a more efficient way. There was no significant improvement in phonological processing, which may indicate reduced connectivity in the left inferior frontal areas. Conclusions: This case underscores the potential of combining individualized, network-targeted language training with bi-hemispheric multisite tDCS to enhance recovery in chronic, treatment-resistant aphasia. The convergence of behavioral gains and neuroplasticity highlights the importance of precision neuromodulation approaches. However, findings are preliminary and warrant further validation through controlled studies to establish broader efficacy and sustainability of outcomes. Full article

In this paper, we study the classification problem of short-time-window steady-state visual evoked potentials (SSVEPs) and propose a novel deep convolutional network named EEGResNet based on the idea of residual connection to further improve the classification performance. Since the frequency-domain features extracted from short-time-window signals are difficult to distinguish, the EEGResNet starts from the filter bank (FB)-based feature extraction module in the time domain. The FB designed in this paper is composed of four sixth-order Butterworth filters with different bandpass ranges, and the four bandwidths are 19–50 Hz, 14–38 Hz, 9–26 Hz, and 3–14 Hz, respectively. Then, the extracted four feature tensors with the same shape are directly aggregated together. Furthermore, the aggregated features are further learned by a six-layer convolutional neural network with residual connections. Finally, the network output is generated through an adaptive fully connected layer. To prove the effectiveness and superiority of our designed EEGResNet, necessary experiments and comparisons are conducted over two large public datasets. To further verify the application potential of the trained network, a virtual simulation of brain computer interface (BCI) based quadrotor control is presented through V-REP. Full article

The transgenic animals have been yielding invaluable insights into amyloid pathology by replicating the key features of Alzheimer’s disease (AD). However, there is no clear relationship between senile plaques and memory deficits. Instead, cognitive impairment and synaptic dysfunction are particularly linked to a rise in Aβ_1-42 oligomer level. Thus, injection of Aβ_1-42 oligomers into a specific brain region is considered an alternative approach to investigate the effects of increased soluble Aβ species without any plaques, offering higher controllability, credibility and validity compared to the transgenic model. The hippocampal CA1 (cornu ammonis 1) region is selectively affected in the early stage of AD and specific targeting of CA1 region directly links Aβ oligomer-related pathology with memory impairment in early AD. Next, the inhibitory avoidance (IA) task, a learning paradigm to assess the synaptic basis of CA1-dependent contextual learning, triggers training-dependent synaptic plasticity similar to in vitro HFS (high-frequency stimulation). Given its reliability in assessing contextual memory and synaptic plasticity, this task provides an effective framework for studying early stage AD-related memory deficit. Therefore, in this review, we will focus on why Aβ_1-42 oligomer injection is a valid in vivo model to investigate the early stage of AD and why dorsal CA1 region serves as a target area to understand the adverse effects of Aβ_1-42 oligomers on contextual learning through the IA task. Full article

Adolescence represents a critical period of neurodevelopment during which brain-derived neurotrophic factor (BDNF) plays a fundamental role in neuronal survival and synaptic plasticity. While exercise-BDNF relationships are well-documented in adults, evidence in adolescents remains limited and inconsistent. This systematic review examined the effects of exercise modalities on circulating BDNF concentrations in adolescent populations. A systematic search was conducted following PRISMA guidelines across multiple databases (FECYT, PubMed, SPORTDiscus, ProQuest Central, SCOPUS, Cochrane Library) through June 2025. Inclusion criteria comprised adolescents, exercise interventions, BDNF outcomes, and randomized controlled trial design. Methodological quality was assessed using the PEDro scale. From 130 initially identified articles, 8 randomized controlled trials were included, with 4 rated as excellent and the other 4 as good quality. Exercise modalities included aerobic, resistance, concurrent, high-intensity interval training, Taekwondo, and whole-body vibration, with durations ranging 6–24 weeks. Four studies demonstrated statistically significant BDNF increases following exercise interventions, four showed no significant changes, and one reported transient reduction. Positive outcomes occurred primarily with vigorous-intensity protocols implemented for a minimum of six weeks. Meta-analysis was not feasible due to high heterogeneity in populations, interventions, and control conditions. Moreover, variation in post-exercise sampling timing further limited comparability of BDNF results. Future research should standardize protocols and examine longer interventions to clarify exercise-BDNF relationships in adolescents. Full article

Brain–computer interface (BCI) technology holds promise for improving motor rehabilitation in stroke patients. This review explores the immediate and long-term effects of BCI training, shedding light on the potential benefits and challenges. Clinical studies have demonstrated that BCIs yield significant immediate improvements in motor functions following stroke. Patients can engage in BCI training safely, making it a viable option for rehabilitation. Evidence from single-group studies consistently supports the effectiveness of BCIs in enhancing patients’ performance. Despite these promising findings, the evidence regarding long-term effects remains less robust. Further studies are needed to determine whether BCI-induced changes are permanent or only last for short durations. While evaluating the outcomes of BCI, one must consider that different BCI training protocols may influence functional recovery. The characteristics of some of the paradigms that we discuss are motor imagery-based BCIs, movement-attempt-based BCIs, and brain-rhythm-based BCIs. Finally, we examine studies suggesting that integrating BCIs with other devices, such as those used for functional electrical stimulation, has the potential to enhance recovery outcomes. We conclude that, while BCIs offer immediate benefits for stroke rehabilitation, addressing long-term effects and optimizing clinical implementation remain critical areas for further investigation. Full article

Background and objectives: Neurosurgical intervention on the newborn’s developing brain is a risk factor for neurodevelopmental disorders (NDDs). These patients necessarily require regular, coordinated follow-up. The ventricular subgaleal shunt (VSGS) technique has been used since 2013 at Rouen University Hospital. Like any change in practice, this technique must be evaluated. In this paper, we describe the population of patients with hydrocephalus treated by VSGS, the complications associated with the procedure, and the outcome of these patients at two and six years old. Methods: This study was an observational, descriptive, retrospective, single-center study. Children included were those less than three months old with hydrocephalus treated by VSGS at Rouen University Hospital from January 2013 to December 2023. Data were anonymized and collected using EDSaN software. A descriptive analysis was performed. Results: Thirty-two patients were included in our study. Of these, 22 (69%) were born prematurely; 16 (50%) of these 22 had postnatal intraventricular hemorrhage (IVH) requiring treatment with VSGS. A total of three patients (13.6%) died within the first year of life; twenty-four patients (75%) required definitive shunting. Twenty-two patients were over 2 years old in our study. Only 10 of them acquired the ability to walk (45%). Cerebral palsy was present in 10 (45%) patients. Fifteen patients were over 6 years old; thirteen (87%) attended school, but six (40%) had special needs (the need of an assistant, or part-time schedule). In our study, only 24 patients (82%) were followed by a pediatrician trained in neurodevelopment at Rouen University Hospital, and 27 (93%) were followed by a neurosurgeon. Conclusions: This study describes all patients with hydrocephalus treated by VSGS at Rouen University Hospital between January 2013 and December 2023, as well as their complications and their neurological outcomes. The follow-up of these children at risk of NDDs is essential. Full article

The stochastic variance-reduced gradient (SVRG) theory is particularly well-suited for addressing gradient variance in deep neural network (DNN) training; however, its direct application to DNN training is hindered by adaptation challenges. To tackle this issue, the present paper proposes a series of strategies focused on adaptive alternating learning rates to effectively adapt SVRG for DNN training. Firstly, within the outer loop of SVRG, both the full gradient and the learning rate specific to DNN training are computed. For two distinct formulas used for calculating the learning rate, an alternating strategy is introduced that employs them alternately across iterations. This approach allows for simultaneous provision of diverse guidance information regarding parameter change rates and gradient change rates during DNN weight updates. Additionally, a threshold method is utilized to correct the learning rate into an appropriate range, thereby accelerating convergence. Secondly, in the inner loop of SVRG, DNN weights are updated using mini-batch average gradient along with the proposed learning rate. Concurrently, mini-batch average gradients from each iteration within the inner loop are refined and aggregated into a single gradient exhibiting reduced variance through an inertia strategy. This refined gradient is then relayed back to the outer loop to recalculate the new learning rate. The efficacy of the proposed algorithm has been validated on models including LeNet, VGG11, ResNet34, and DenseNet121 while being compared against several classic and advanced optimizers. Experimental results demonstrate that the proposed algorithm exhibits remarkable training robustness across DNN models with diverse characteristics. In terms of training convergence, the proposed algorithm demonstrates competitiveness with state-of-the-art algorithms, such as Lion, developed by the Google Brain team. Full article

Using neural networks has become the standard technique for medical diagnostics, especially in cancer detection and classification. This work evaluates the performance of Vision Transformer architectures, including Swin Transformer and MaxViT, for several datasets of magnetic resonance imaging (MRI) and computed tomography (CT) scans. We used three training sets of images with brain, lung, and kidney tumors. Each dataset included different classification labels, from brain gliomas and meningiomas to benign and malignant lung conditions and kidney anomalies such as cysts and cancers. This work aims to analyze the behavior of the neural networks in each dataset and the benefits of combining different image modalities and tumor classes. We designed several experiments by fine-tuning the models on combined and individual datasets. The results revealed that the Swin Transformer achieved the highest accuracy, with an average of 99.0% on single datasets and reaching 99.43% on the combined dataset. This research highlights the adaptability of Transformer-based models to various human organs and image modalities. The main contribution lies in evaluating multiple ViT architectures across multi-organ tumor datasets, demonstrating their generalization to multi-organ classification. Integrating these models across diverse datasets could mark a significant advance in precision medicine, paving the way for more efficient healthcare solutions. Full article

Investigating brain area functions requires advanced technologies, but meaningful insights depend on correlating neural signals with behavior. Traditional mice behavior annotation methods, including manual and semi-automated approaches, are limited by subjectivity and time constraints. To overcome these limitations, our study employs the YOLO neural network for precise mice tracking and composite RGB frames for behavioral scoring. Our model, trained on over 10,000 frames, accurately classifies sitting, running, and grooming behaviors. Additionally, we provide statistical metrics and data visualization tools. We further combined AI-powered behavior labeling to examine hippocampal neuronal activity using fluorescence microscopy. To analyze neuronal circuit dynamics, we utilized a manifold analysis approach, revealing distinct functional patterns corresponding to transgenic 5xFAD Alzheimer’s model mice. This open-source software enhances the accuracy and efficiency of behavioral and neural data interpretation, advancing neuroscience research. Full article

Alzheimer’s disease (AD) involves the accumulation of amyloid-β (Aβ) plaques, whose quantification plays a central role in understanding disease progression. Automated segmentation of Aβ deposits in histopathological micrographs enables large-scale analyses but is hindered by the high cost of detailed pixel-level annotations. Weakly supervised learning offers a promising alternative by leveraging coarse or indirect labels to reduce the annotation burden. We evaluated a weakly supervised approach to segment and analyze thioflavin-S-positive parenchymal amyloid pathology in AD and age-matched brains. Our pipeline integrates three key components, each designed to operate under weak supervision. First, robust preprocessing (including retrospective multi-image illumination correction and gradient-based background estimation) was applied to enhance image fidelity and support training, as models rely more on image features. Second, class activation maps (CAMs), generated by a compact deep classifier SqueezeNet, were used to identify, and coarsely localize amyloid-rich parenchymal regions from patch-wise image labels, serving as spatial priors for subsequent refinement without requiring dense pixel-level annotations. Third, a patch-based convolutional neural network, U-Net, was trained on synthetic data generated from micrographs based on CAM-derived pseudo-labels via an extensive object-level augmentation strategy, enabling refined whole-image semantic segmentation and generalization across diverse spatial configurations. To ensure robustness and unbiased evaluation, we assessed the segmentation performance of the entire framework using patient-wise group k-fold cross-validation, explicitly modeling generalization across unseen individuals, critical in clinical scenarios. Despite relying on weak labels, the integrated pipeline achieved strong segmentation performance with an average Dice similarity coefficient (≈0.763) and Jaccard index (≈0.639), widely accepted metrics for assessing segmentation quality in medical image analysis. The resulting segmentations were also visually coherent, demonstrating that weakly supervised segmentation is a viable alternative in histopathology, where acquiring dense annotations is prohibitively labor-intensive and time-consuming. Subsequent morphometric analyses on automatically segmented Aβ deposits revealed size-, structural complexity-, and global geometry-related differences across brain regions and cognitive status. These findings confirm that deposit architecture exhibits region-specific patterns and reflects underlying neurodegenerative processes, thereby highlighting the biological relevance and practical applicability of the proposed image-processing pipeline for morphometric analysis. Full article

Recent deep learning models, including GPT-4, have achieved remarkable performance using the back-propagation (BP) algorithm. However, the mechanism of BP is fundamentally different from how the human brain processes learning. To address this discrepancy, the Forward-Forward (FF) algorithm was introduced. Although FF enables deep learning without backward passes, it suffers from instability, dependence on artificial input construction, and limited generalizability. To overcome these challenges, we propose Local Back-Propagation (LBP), a method that integrates layer-wise unsupervised learning with standard inputs and conventional loss functions. Specifically, LBP demonstrates high training stability and competitive accuracy, significantly outperforming FF-based training methods. Moreover, LBP reduces memory usage by up to 48% compared to convolutional neural networks trained with back-propagation, making it particularly suitable for resource-constrained environments such as federated learning. These results suggest that LBP is a promising biologically inspired training method for decentralized deep learning. Full article

Background: Brain-derived neurotrophic factor (BDNF) plays a pivotal role in neuroplasticity and cognitive development. While exercise has been shown to modulate BDNF levels in adults, evidence in children remains limited and heterogeneous. Methods: A systematic review was conducted following PRISMA guidelines to examine randomized controlled trials investigating exercise effects on BDNF in children aged 5–12 years. The databases searched included FECYT, PubMed, SPORTDiscus, ProQuest Central, SCOPUS, and Cochrane Library through June 2025. Study quality was assessed using the PEDro scale. Results: Five randomized controlled trials (N = 385 participants) met inclusion criteria. Two studies (40%) demonstrated significant BDNF increases following exercise interventions. Successful interventions were characterized by neuromotor activities or martial arts programs, training frequencies ≥ 3 sessions/week, durations ≥ 12 weeks, and healthy participant populations. Methodological quality was mostly fair, with four studies rated as fair and one as good. Conclusions: Structured physical exercise may enhance BDNF levels in healthy children, with neuromotor activities and martial arts showing particular promise. However, children with overweight/obesity may require modified intervention approaches. The evidence supports the implementation of cognitively engaging physical activities in educational settings to optimize brain health during critical developmental periods, though larger standardized trials are needed to strengthen these preliminary findings. Full article

Accurate segmentation of key tumor subregions in adult gliomas from Magnetic Resonance Imaging (MRI) is of critical importance for brain tumor diagnosis, treatment planning, and prognosis. However, this task remains poorly investigated and highly challenging due to the considerable variability in shape and appearance of these areas across patients. This study proposes a novel Deep Learning architecture leveraging modality-specific encoding and attention-based refinement for the segmentation of glioma subregions, including peritumoral edema (ED), necrotic core (NCR), and enhancing tissue (ET). The model is trained and validated on the Brain Tumor Segmentation (BraTS) 2023 challenge dataset and benchmarked against a state-of-the-art transformer-based approach. Our architecture achieves promising results, with Dice scores of 0.78, 0.86, and 0.88 for NCR, ED, and ET, respectively, outperforming SegFormer3D while maintaining comparable model complexity. To ensure a comprehensive evaluation, performance was also assessed on standard composite tumor regions, i.e., tumor core (TC) and whole tumor (WT). The statistically significant improvements obtained on all regions highlight the effectiveness of integrating complementary modality-specific information and applying channel-wise feature recalibration in the proposed model. Full article