Attention improvement to transcranial alternating current stimulation at gamma frequency over the right frontoparietal network: a preliminary report.

Applying transcranial alternating current stimulation (tACS) at 40 Hz to the frontal and parietal regions, either unilaterally (left or right) or bilaterally, can improve cognitive dysfunctions. This study aimed to explore the influence of tACS at gamma frequency over right fronto-parietal (FP) region on attention. The analysis is based on retrospective data from a clinical intervention. We administered test of variables of attention (TOVA; visual mode) to 44 participants with various neuropsychiatric diagnoses before and after 12 sessions of tACS treatment. Alternating currents at 2.0 mA were delivered to the electrode positions F4 and P4, following the 10-20 EEG convention, for 20 mins in each session. We observed significant improvement across 3 indices of the TOVA, including reduction of variability in reaction time (p = 0.0002), increase in d-Prime (separability of targets and non-targets; p = 0.0157), and decrease in commission error rate (p = 0.0116). The mean RT and omission error rate largely remained unchanged. Artificial injection of tACS at 40 Hz over right FP network may improve attention function, especially in the domains of consistency in performance, target/non-target discrimination, and inhibitory control.

Comparative analysis of electroencephalogram (EEG) data gathered from the frontal region with other brain regions affected by attention deficit hyperactivity disorder (ADHD) through multiresolution analysis and machine learning techniques.

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by repeated patterns of hyperactivity, impulsivity, and inattention that limit daily functioning and development. Electroencephalography (EEG) anomalies correspond to changes in brain connection and activity. The authors propose utilizing empirical mode decomposition (EMD) and discrete wavelet transform (DWT) for feature extraction and machine learning (ML) algorithms to categorize ADHD and control subjects. For this study, the authors considered freely accessible ADHD data obtained from the IEEE data site. Studies have demonstrated a range of EEG anomalies in ADHD patients, such as variations in power spectra, coherence patterns, and event-related potentials (ERPs). Some of the studies claimed that the brain's prefrontal cortex and frontal regions collaborate in intricate networks, and disorders in either of them exacerbate the symptoms of ADHD. , Based on the research that claimed the brain's prefrontal cortex and frontal regions collaborate in intricate networks, and disorders in either of them exacerbate the symptoms of ADHD, the proposed study examines the optimal position of EEG electrode for identifying ADHD and in addition to monitoring accuracy on frontal/ prefrontal and other regions of brain our study also investigates the position groupings that have the highest effect on accurateness in identification of ADHD. The results demonstrate that the dataset classified with AdaBoost provided values for accuracy, precision, specificity, sensitivity, and F1-score as 1.00, 0.70, 0.70, 0.75, and 0.71, respectively, whereas using random forest (RF) it is 0.98, 0.64, 0.60, 0.81, and 0.71, respectively, in detecting ADHD. After detailed analysis, it is observed that the most accurate results included all electrodes. The authors believe the processes can detect various neurodevelopmental problems in children utilizing EEG signals.

Multimodal brain tumor segmentation and classification from MRI scans based on optimized DeepLabV3+ and interpreted networks information fusion empowered with explainable AI.

Explainable artificial intelligence (XAI) aims to offer machine learning (ML) methods that enable people to comprehend, properly trust, and create more explainable models. In medical imaging, XAI has been adopted to interpret deep learning black box models to demonstrate the trustworthiness of machine decisions and predictions. In this work, we proposed a deep learning and explainable AI-based framework for segmenting and classifying brain tumors. The proposed framework consists of two parts. The first part, encoder-decoder-based DeepLabv3+ architecture, is implemented with Bayesian Optimization (BO) based hyperparameter initialization. The different scales are performed, and features are extracted through the Atrous Spatial Pyramid Pooling (ASPP) technique. The extracted features are passed to the output layer for tumor segmentation. In the second part of the proposed framework, two customized models have been proposed named Inverted Residual Bottleneck 96 layers (IRB-96) and Inverted Residual Bottleneck Self-Attention (IRB-Self). Both models are trained on the selected brain tumor datasets and extracted features from the global average pooling and self-attention layers. Features are fused using a serial approach, and classification is performed. The BO-based hyperparameters optimization of the neural network classifiers is performed and the classification results have been optimized. An XAI method named LIME is implemented to check the interpretability of the proposed models. The experimental process of the proposed framework was performed on the Figshare dataset, and an average segmentation accuracy of 92.68 % and classification accuracy of 95.42 % were obtained, respectively. Compared with state-of-the-art techniques, the proposed framework shows improved accuracy.

Analog Spiking U-Net integrating CBAM&ViT for medical image segmentation.

SNNs are gaining popularity in AI research as a low-power alternative in deep learning due to their sparse properties and biological interpretability. Using SNNs for dense prediction tasks is becoming an important research area. In this paper, we firstly proposed a novel modification on the conventional Spiking U-Net architecture by adjusting the firing positions of neurons. The modified network model, named Analog Spiking U-Net (AS U-Net), is capable of incorporating the Convolutional Block Attention Module (CBAM) into the domain of SNNs. This is the first successful implementation of CBAM in SNNs, which has the potential to improve SNN model's segmentation performance while decreasing information loss. Then, the proposed AS U-Net (with CBAM&ViT) is trained by direct encoding on a comprehensive dataset obtained by merging several diabetic retinal vessel segmentation datasets. Based on the experimental results, the provided SNN model achieves the highest segmentation accuracy in retinal vessel segmentation for diabetes mellitus, surpassing other SNN-based models and most ANN-based related models. In addition, under the same structure, our model demonstrates comparable performance to the ANN model. And then, the novel model achieves state-of-the-art(SOTA) results in comparative experiments when both accuracy and energy consumption are considered (Fig. 1). At the same time, the ablative analysis of CBAM further confirms its feasibility and effectiveness in SNNs, which means that a novel approach could be provided for subsequent deployment and hardware chip application. In the end, we conduct extensive generalization experiments on the same type of segmentation task (ISBI and ISIC), the more complex multi-segmentation task (Synapse), and a series of image generation tasks (MNIST, Day2night, Maps, Facades) in order to visually demonstrate the generality of the proposed method.

Subclinical attention-deficit hyperactivity disorder symptoms and unhealthy lifestyle behaviours.

BACKGROUND: Literature emphasises the importance of identifying and intervening in the adoption of unhealthy lifestyle behaviours (ULBs) during adolescence at an early stage, to mitigate their long-term detrimental effects. Among the possible associated factors contributing to ULBs, attention-deficit hyperactivity disorder (ADHD) has been shown to play an important role. However, little is known about ADHD subclinical manifestations. AIMS: The present study aimed to bridge the gap in the literature and shed light on the relationship between subclinical ADHD and early adoption of ULBs during adolescence. Through a clinimetric approach, prevalence of ULBs, severity of ADHD symptoms and psychosocial factors (i.e. allostatic overload, abnormal illness behaviour, quality of life, psychological well-being) were investigated among adolescents. The associations between different degrees of ADHD, ULBs and psychosocial factors were also explored. METHOD: This multicentre cross-sectional study involved 440 adolescents (54.5% females; mean age 14.21 years) from six upper secondary schools. Participants completed self-report questionnaires on sociodemographic characteristics, ULBs, ADHD symptoms and psychosocial factors. RESULTS: The most common ULBs were energy drinks/alcohol consumption and problematic smartphone use. Of the sample, 22% showed subclinical ADHD and 20.2% showed clinical ADHD. The subclinical ADHD group showed several ULBs (i.e. altered mindful eating, impaired quality of sleep, problematic technology use) and psychosocial factors, akin to those of ADHD group and different from peers without ADHD symptoms. CONCLUSIONS: Since subclinical ADHD manifestation is associated with ULBs, similarly to clinical ADHD, identifying subthreshold symptoms during adolescence is crucial, as it could improve health-related outcomes in adulthood across different domains.

CoNglyPred: Accurate Prediction of N-Linked Glycosylation Sites Using ESM-2 and Structural Features With Graph Network and Co-Attention.

N-Linked glycosylation is crucial for various biological processes such as protein folding, immune response, and cellular transport. Traditional experimental methods for determining N-linked glycosylation sites entail substantial time and labor investment, which has led to the development of computational approaches as a more efficient alternative. However, due to the limited availability of 3D structural data, existing prediction methods often struggle to fully utilize structural information and fall short in integrating sequence and structural information effectively. Motivated by the progress of protein pretrained language models (pLMs) and the breakthrough in protein structure prediction, we introduced a high-accuracy model called CoNglyPred. Having compared various pLMs, we opt for the large-scale pLM ESM-2 to extract sequence embeddings, thus mitigating certain limitations associated with manual feature extraction. Meanwhile, our approach employs a graph transformer network to process the 3D protein structures predicted by AlphaFold2. The final graph output and ESM-2 embedding are intricately integrated through a co-attention mechanism. Among a series of comprehensive experiments on the independent test dataset, CoNglyPred outperforms state-of-the-art models and demonstrates exceptional performance in case study. In addition, we are the first to report the uncertainty of N-linked glycosylation predictors using expected calibration error and expected uncertainty calibration error.

The neurodivergent perinatal experience - A systematic literature review on autism and attention deficit hyperactivity disorder.

BACKGROUND: Neurodivergent individuals often face unique challenges during the perinatal period, which can significantly impact their experiences of pregnancy, childbirth, and early parenting. Despite growing awareness of neurodiversity, there remains a gap in perinatal care that fully addresses the lived experiences and needs of those with neurodivergent conditions such as Autism (ASD) and Attention-Deficit/Hyperactivity Disorder (ADHD). OBJECTIVE: To compile and analyse recent literature on the perinatal experiences of neurodivergent parturients. To provide an overview of current knowledge, identify prevalent challenges, and suggest opportunities for improving perinatal services. Additionally, we aim to highlight research gaps that guide future studies and enhance care quality for neurodivergent individuals during the perinatal period. METHODS: The Systematic Reviews methodological process was utilised to search relevant scientific databases to gather current research articles on neurodivergent perinatal experiences. Eleven studies met the inclusion criteria and were appraised using a rigorous quality checklist. Thematic analysis identified recurring themes across the selected papers. RESULTS: Three major themes emerged: Care provider support, Perinatal mental health needs, and Resilience and growth of neurodivergent parturients. These themes highlight significant differences in perinatal experiences between neurodivergent and neurotypical individuals, underscoring the need for tailored care approaches. CONCLUSION: The findings reveal that current perinatal care practices do not adequately address the specific challenges faced by perinatal neurodivergent individuals. There is a critical need for perinatal care systems to integrate neurodiversity-affirming practices. Future research should consider intersectionality to include marginalised and underrepresented neurodivergent voices.

The effect of dual training on the hazard response and attention allocation of novice drivers when driving with advanced driver assistance system.

To ensure traffic safety when driving with an advanced driving assistance system (ADAS), drivers are still required to take over control of the vehicle in case of emergency. Drivers' takeover performance jointly relies on their capability to anticipate the potential hazards in traffic scenarios and an appropriate understanding of ADAS capabilities. However, previous research mostly focused on strengthening drivers' understanding of ADAS capabilities but ignored drivers' hazard perception capabilities when using ADAS - the latter is especially weak among novice drivers. This study proposed and evaluated three training methods for novice drivers, i.e., ADAS training only (AD training), hazard perception training only (HP training), and AD+HP training. Their effectiveness on drivers' attention allocation strategies and responses to hazardous scenarios when handling hazardous scenarios with different levels of complexity were evaluated among 32 novice drivers in a driving simulator study. Results show that the proposed AD+HP training outperformed AD training and HP training in terms of attention allocation strategies (i.e., wider distribution of attention) and responses in hazardous scenarios (i.e., quicker and more attention to cues of importance and larger minimum time gap). However, the effectiveness of all kinds of training was weakened in more complex scenarios. Findings from this study provide insights into driver training in the context of driving automation.

Federated learning via multi-attention guided UNet for thyroid nodule segmentation of ultrasound images.

Accurate segmentation of thyroid nodules is essential for early screening and diagnosis, but it can be challenging due to the nodules' varying sizes and positions. To address this issue, we propose a multi-attention guided UNet (MAUNet) for thyroid nodule segmentation. We use a multi-scale cross attention (MSCA) module for initial image feature extraction. By integrating interactions between features at different scales, the impact of thyroid nodule shape and size on the segmentation results has been reduced. Additionally, we incorporate a dual attention (DA) module into the skip-connection step of the UNet network, which promotes information exchange and fusion between the encoder and decoder. To test the model's robustness and effectiveness, we conduct the extensive experiments on multi-center ultrasound images provided by 17 local hospitals. The model is trained using the federal learning mechanism to ensure privacy protection. The experimental results show that the Dice scores of the model on the data sets from the three centers are 0.908, 0.912 and 0.887, respectively. Compared to existing methods, our method demonstrates higher generalization ability on multi-center datasets and achieves better segmentation results.

SpaGRA: graph augmentation facilitates domain identification for spatially resolved transcriptomics.

Recent advances in spatially resolved transcriptomics (SRT) have provided new opportunities for characterizing spatial structures of various tissues. Graph-based geometric deep learning have gained widespread adoption for spatial domain identification tasks. Currently, most methods define adjacency relation between cells or spots by their spatial distance in SRT data, which overlooks key biological interactions like gene expression similarities, and leads to inaccuracies in spatial domain identification. To tackle this challenge, we propose a novel method, SpaGRA (https://github.com/sunxue-yy/SpaGRA), for automatic multi-relationship construction based on graph augmentation. SpaGRA uses spatial distance as prior knowledge and dynamically adjusts edge weights with multi-head graph attention networks (GATs). This helps SpaGRA to uncover diverse node relationships and enhance message passing in geometric contrastive learning. Additionally, SpaGRA uses these multi-view relationships to construct negative samples, addressing sampling bias posed by random selection. Experimental results show that SpaGRA demonstrates superior domain identification performance on multiple datasets generated from different protocols. Using SpaGRA, we analyzed the functional regions in the mouse hypothalamus, identified key genes related to heart development in mouse embryos, and observed cancer-associated fibroblasts enveloping cancer cells in the latest Visium HD data. Overall, SpaGRA can effectively characterize spatial structures across diverse SRT datasets.

MLSNet: a deep learning model for predicting transcription factor binding sites.

Accurate prediction of transcription factor binding sites (TFBSs) is essential for understanding gene regulation mechanisms and the etiology of diseases. Despite numerous advances in deep learning for predicting TFBSs, their performance can still be enhanced. In this study, we propose MLSNet, a novel deep learning architecture designed specifically to predict TFBSs. MLSNet innovatively integrates multisize convolutional fusion with long short-term memory (LSTM) networks to effectively capture DNA-sparse higher-order sequence features. Further, MLSNet incorporates super token attention and Bi-LSTM to systematically extract and integrate higher-order DNA shape features. Experimental results on 165 ChIP-seq (chromatin immunoprecipitation followed by sequencing) datasets indicate that MLSNet consistently outperforms several state-of-the-art algorithms in the prediction of TFBSs. Specifically, MLSNet reports average metrics: 0.8306 for ACC, 0.8992 for AUROC, and 0.9035 for AUPRC, surpassing the second-best methods by 1.82%, 1.68%, and 1.54%, respectively. This research delineates the effectiveness of combining multi-size convolutional layers with LSTM and DNA shape-based features in enhancing predictive accuracy. Moreover, this study comprehensively assesses the variability in model performance across different cell lines and transcription factors. The source code of MLSNet is available at https://github.com/minghaidea/MLSNet.

The Impact of Social Media on Otolaryngology Literature: Analyzing the Correlation Between Altmetrics and Citation Count.

Objective: The altmetric attention score (AAS) is an alternative metric that tracks article sharing via online platforms, reflecting an article's online attention trend. The objective of this study was to analyze the impact of social media on Otolaryngology-Head and Neck Surgery (OHNS) literature and analyze the correlation between AAS and citation count. Study Design and Setting: A retrospective review of otolaryngology journal article citation data and Altmetric attention score. Methods: The top 10 OHNS journals with highest impact factors were identified using the Journal Citation Reports (JCR). The number of citations in 2018 and 2019 were extracted from JCR and AAS was extracted from the altmetrics website. The primary outcome of this study was to establish whether a correlation between AAS and citation count exists, and whether AAS could serve as a valid alternative metric to assess the quality of individual articles. Results: By analyzing data from 3729 articles, a weak statistically significant positive correlation was identified between AAS and citation count (r = 0.18, P < .001), and between number of citations and Twitter activity (r = 0.18, P < .001). In addition, a statistically significant strong correlation was seen between Twitter activity and AAS (r = 0.79, P < .001). Conclusion: The current results clearly illustrate a weak correlation between AAS and citations and between Twitter activity and citations. Due to various limitations, the use of AAS should be limited to serve as a complementary metric to the current gold standard rather than an alternative metric.

Postural supporting cervical traction workstation to improve resting state brain activity in digital device users: EEG study.

Objective: This study aimed to determine the effect of postural support workstation on inducing effective brain activity during rest. Methods: Thirty-five healthy digital overusers were recruited as participants. We conducted two interventions of head weight support traction (ST) and conventional traction (CT) strength on all participants in random order. Participants' arousal levels and psychological comfort were assessed. In addition, changes in brain activity caused by traction were confirmed by measuring changes in resting state brain activity using an electroencephalogram (EEG). Results: Under the ST condition, psychological comfort improved while alert levels were maintained. In addition the resting brain activity of EEG was characterized by strong focused attention and relaxed activity, as evidenced by increased alpha waves throughout the brain. By contrast, in the CT condition, no significant improvement in comfort was observed. Furthermore, high-frequency brain activity, such as beta 3 and gamma waves, was observed across the entire brain regions. Conclusion: In this study, the ST workstation was shown to effectively improve resting attention and psychological comfort in individuals who excessively use digital devices by inducing resting state alpha activity without stimulating high-frequency brain waves, while maintaining an upright posture with appropriate traction.

Someone just posted on Instagram: Conspicuous consumption, anticipated engagement, and trait mindfulness.

The practice of "flexing," showing off one's wealth and status, gradually penetrates daily life on various social media platforms, most notably Instagram. We investigated the extent to which exposure to conspicuous consumption by a stranger stimulated the viewers' materialistic aspiration and whether this effect could be mediated by anticipated engagement and moderated by trait mindfulness. A large number of Instagram users in Indonesia (N = 2,296, 75.30% female; Mage = 31.14 years old, SDage = 7.09) completed the trait mindfulness scale, randomly received a single Instagram photo showcasing luxury material vs. experiential purchase, provided an estimate of the intensity of love and comment from other viewers (i.e., anticipated engagement), and filled out the materialistic aspiration scale. Participants exposed to material purchase reported higher aspiration than those exposed to experiential purchase, but lower anticipated engagements also reduced materialistic aspiration. Participants with higher trait mindfulness were better at distinguishing the effects of conspicuous consumption on anticipated engagement and materialistic aspiration. These findings indicate that the viewers' anticipation of collective attention could reverse the impact of exposure to conspicuous consumption and the potential of trait mindfulness as an anti-mimetic quality for situational materialism.

MobileNet-V2: An Enhanced Skin Disease Classification by Attention and Multi-Scale Features.

The increasing prevalence of skin diseases necessitates accurate and efficient diagnostic tools. This research introduces a novel skin disease classification model leveraging advanced deep learning techniques. The proposed architecture combines the MobileNet-V2 backbone, Squeeze-and-Excitation (SE) blocks, Atrous Spatial Pyramid Pooling (ASPP), and a Channel Attention Mechanism. The model was trained on four diverse datasets such as PH2 dataset, Skin Cancer MNIST: HAM10000 dataset, DermNet. dataset, and Skin Cancer ISIC dataset. Data preprocessing techniques, including image resizing, and normalization, played a crucial role in optimizing model performance. In this paper, the MobileNet-V2 backbone is implemented to extract hierarchical features from the preprocessed dermoscopic images. The multi-scale contextual information is fused by the ASPP model for generating a feature map. The attention mechanisms contributed significantly, enhancing the extraction ability of inter-channel relationships and multi-scale contextual information for enhancing the discriminative power of the features. Finally, the output feature map is converted into probability distribution through the softmax function. The proposed model outperformed several baseline models, including traditional machine learning approaches, emphasizing its superiority in skin disease classification with 98.6% overall accuracy. Its competitive performance with state-of-the-art methods positions it as a valuable tool for assisting dermatologists in early classification. The study also identified limitations and suggested avenues for future research, emphasizing the model's potential for practical implementation in the field of dermatology.

Revolutionizing tomato disease detection in complex environments.

In the current agricultural landscape, a significant portion of tomato plants suffer from leaf diseases, posing a major challenge to manual detection due to the task's extensive scope. Existing detection algorithms struggle to balance speed with accuracy, especially when identifying small-scale leaf diseases across diverse settings. Addressing this need, this study presents FCHF-DETR (Faster-Cascaded-attention-High-feature-fusion-Focaler Detection-Transformer), an innovative, high-precision, and lightweight detection algorithm based on RT-DETR-R18 (Real-Time-Detection-Transformer-ResNet18). The algorithm was developed using a carefully curated dataset of 3147 RGB images, showcasing tomato leaf diseases across a range of scenes and resolutions. FasterNet replaces ResNet18 in the algorithm's backbone network, aimed at reducing the model's size and improving memory efficiency. Additionally, replacing the conventional AIFI (Attention-based Intra-scale Feature Interaction) module with Cascaded Group Attention and the original CCFM (CNN-based Cross-scale Feature-fusion Module) module with HSFPN (High-Level Screening-feature Fusion Pyramid Networks) in the Efficient Hybrid Encoder significantly enhanced detection accuracy without greatly affecting efficiency. To tackle the challenge of identifying challenging samples, the Focaler-CIoU loss function was incorporated, refining the model's performance throughout the dataset. Empirical results show that FCHF-DETR achieved 96.4% Precision, 96.7% Recall, 89.1% mAP (Mean Average Precision) 50-95 and 97.2% mAP50 on the test set, with a reduction of 9.2G in FLOPs (floating point of operations) and 3.6M in parameters. These findings clearly demonstrate that the proposed method improves detection accuracy and reduces computational complexity, addressing the dual challenges of precision and efficiency in tomato leaf disease detection.

Deep learning approaches for assessing pediatric sleep apnea severity through SpO2 signals.

Pediatric Sleep Apnea-Hypopnea (SAH) presents a significant health challenge, particularly in diagnostic contexts, where conventional Polysomnography (PSG) testing, although effective, can be distressing for children. Addressing this, our research proposes a less invasive method to assess pediatric SAH severity by analyzing blood oxygen saturation (SpO2) signals. We adopted two advanced deep learning architectures, namely ResNet-based and attention-augmented hybrid CNN-BiGRU models, to process SpO2 signals in a one-dimensional (1D) format for Apnea-Hypopnea Index (AHI) estimation in pediatric subjects. Employing the CHAT dataset, which includes 844 SpO2 signals, the data was partitioned into training (60%), testing (30%), and validation (10%) sets. A predefined validation subset was randomly selected to ensure the models' robustness via a threefold cross-validation approach. Comparative analysis revealed that while the ResNet model attained an average accuracy of 72.9% across four SAH severity categories with a kappa score of 0.57, the CNN-BiGRU-Attention model demonstrated superior performance, achieving an average accuracy of 75.95% and a kappa score of 0.63. This distinction underscores our method's efficacy in both estimating AHI and categorizing SAH severity levels with notable precision. Further, to evaluate diagnostic capabilities, the models were benchmarked against common AHI thresholds (1, 5, and 10 events/hour) in each test fold, affirming their effectiveness in identifying pediatric SAH. This study marks a significant advance in the field, offering a non-invasive, child-friendly alternative for pediatric SAH diagnosis. Although challenges persist in accurately estimating AHI, particularly in severe cases, our findings represent a critical stride towards improving diagnostic processes in pediatric SAH.

Brain tumor detection and classification in MRI using hybrid ViT and GRU model with explainable AI in Southern Bangladesh.

Brain tumor, a leading cause of uncontrolled cell growth in the central nervous system, presents substantial challenges in medical diagnosis and treatment. Early and accurate detection is essential for effective intervention. This study aims to enhance the detection and classification of brain tumors in Magnetic Resonance Imaging (MRI) scans using an innovative framework combining Vision Transformer (ViT) and Gated Recurrent Unit (GRU) models. We utilized primary MRI data from Bangabandhu Sheikh Mujib Medical College Hospital (BSMMCH) in Faridpur, Bangladesh. Our hybrid ViT-GRU model extracts essential features via ViT and identifies relationships between these features using GRU, addressing class imbalance and outperforming existing diagnostic methods. We extensively processed the dataset, and then trained the model using various optimizers (SGD, Adam, AdamW) and evaluated through rigorous 10-fold cross-validation. Additionally, we incorporated Explainable Artificial Intelligence (XAI) techniques-Attention Map, SHAP, and LIME-to enhance the interpretability of the model's predictions. For the primary dataset BrTMHD-2023, the ViT-GRU model achieved precision, recall, and F1-score metrics of 97%. The highest accuracies obtained with SGD, Adam, and AdamW optimizers were 81.66%, 96.56%, and 98.97%, respectively. Our model outperformed existing Transfer Learning models by 1.26%, as validated through comparative analysis and cross-validation. The proposed model also shows excellent performances with another Brain Tumor Kaggle Dataset outperforming the existing research done on the same dataset with 96.08% accuracy. The proposed ViT-GRU framework significantly improves the detection and classification of brain tumors in MRI scans. The integration of XAI techniques enhances the model's transparency and reliability, fostering trust among clinicians and facilitating clinical application. Future work will expand the dataset and apply findings to real-time diagnostic devices, advancing the field.

Cognitive health outcomes of fundamental motor skill applications in children through cooperative learning method.

BACKGROUND: Previous research has suggests that cooperative learning methods and the development of fundamental motor skills support children's cognitive development, and further studies covering various aspects are recommended. In this study, as an alternative to traditional physical education classes including fundamental motor skill activities, we investigated the impact of cooperative learning methods incorporating these skills on children's visual-motor integration and selective attention. METHODS: A total of 60 boy children in the 10-11 age range were included in the study. Groups; classical method (10.95 ± 0.58age), and cooperative learning group (10.91 ± 0.42age). The study spanned a total of 24 physical education class hours. While the classical method group continued to attend physical education lessons with an FMS-based prepared program for 8 weeks, cooperative learning group participated in an FMS-based program prepared according to the cooperative learning method (40min/3days/8weeks).At the beginning and end of the study, children underwent the Bender-Gestalt test and the d2 test of attention. RESULTS: Within-group pre-post test comparisons revealed improvement in visual-motor integration and selective attention for both the classical method and cooperative learning groups. In between-group post-test comparisons, the cooperative learning group demonstrated greater improvement in visual-motor integration and selective attention parameters compared to the classical method. CONCLUSION: The results support increasing the inclusion of fundamental motor skill activities in physical education classes and advocating for the use of cooperative learning methods in these classes. Enhancements in visual-motor integration and selective attention may contribute to children forming quality relationships, enjoying activities, learning stress management, and developing as a group.