Attention Scores Research Articles

NMGrad: Advancing Histopathological Bladder Cancer Grading with Weakly Supervised Deep Learning.

The most prevalent form of bladder cancer is urothelial carcinoma, characterized by a high recurrence rate and substantial lifetime treatment costs for patients. Grading is a prime factor for patient risk stratification, although it suffers from inconsistencies and variations among pathologists. Moreover, absence of annotations in medical imaging renders it difficult to train deep learning models. To address these challenges, we introduce a pipeline designed for bladder cancer grading using histological slides. First, it extracts urothelium tissue tiles at different magnification levels, employing a convolutional neural network for processing for feature extraction. Then, it engages in the slide-level prediction process. It employs a nested multiple-instance learning approach with attention to predict the grade. To distinguish different levels of malignancy within specific regions of the slide, we include the origins of the tiles in our analysis. The attention scores at region level are shown to correlate with verified high-grade regions, giving some explainability to the model. Clinical evaluations demonstrate that our model consistently outperforms previous state-of-the-art methods, achieving an F1 score of 0.85.

Towards accurate diagnosis: exploring knowledge distillation and self-attention in multimodal medical image fusion

ABSTRACT Multimodal medical image fusion aims to aggregate significant information based on the characteristics of medical images from different modalities. Existing research in image fusion faces several major limitations, including a scarcity of paired data, noisy and inconsistent modalities, a lack of contextual relationships, and suboptimal feature extraction and fusion techniques. In response to these challenges, this research proposes a novel adaptive fusion approach. Our knowledge distillation (KD) model extracts informative features from multimodal medical images using various key components. A teacher network is employed to emphasise the suitability and complexity of capturing high-level abstract features. The soft labels are utilised to transfer the knowledge between the teacher network as well as the student network. During student network training, we minimise the divergence between these soft labels. To enhance the adaptive fusion of extracted features from different modalities, we apply a self-attention mechanism. Training this self-attention mechanism minimises the loss function, encouraging attention scores to capture relevant contextual relationships between features. Additionally, a cross-modal consistency module aligns the extracted features to ensure spatial consistency and meaningful fusion. Our adaptive fusion strategy effectively combines features to enhance the diagnostic value and quality of fused images. We employ generator and discriminator architectures for synthesising fused images and distinguishing between real and generated fused images. Comprehensive analysis is conducted on the basis of diverse evaluation measures. Experimental results demonstrate improved fusion outcomes with values of 0.92, 41.58, 7.25, 0.958, 0.759, 0.947, 0.90, 7.05, 0.0726, and 76 s for SSIM, PSNR, FF, VIF, UIQI, FMI, EITF, entropy, RMSE, and execution time, respectively.

Enhancing SNN-based spatio-temporal learning: A benchmark dataset and Cross-Modality Attention model

Spiking Neural Networks (SNNs), renowned for their low power consumption, brain-inspired architecture, and spatio-temporal representation capabilities, have garnered considerable attention in recent years. Similar to Artificial Neural Networks (ANNs), high-quality benchmark datasets are of great importance to the advances of SNNs. However, our analysis indicates that many prevalent neuromorphic datasets lack strong temporal correlation, preventing SNNs from fully exploiting their spatio-temporal representation capabilities. Meanwhile, the integration of event and frame modalities offers more comprehensive visual spatio-temporal information. Yet, the SNN-based cross-modality fusion remains underexplored.In this work, we present a neuromorphic dataset called DVS-SLR that can better exploit the inherent spatio-temporal properties of SNNs. Compared to existing datasets, it offers advantages in terms of higher temporal correlation, larger scale, and more varied scenarios. In addition, our neuromorphic dataset contains corresponding frame data, which can be used for developing SNN-based fusion methods. By virtue of the dual-modal feature of the dataset, we propose a Cross-Modality Attention (CMA) based fusion method. The CMA model efficiently utilizes the unique advantages of each modality, allowing for SNNs to learn both temporal and spatial attention scores from the spatio-temporal features of event and frame modalities, subsequently allocating these scores across modalities to enhance their synergy. Experimental results demonstrate that our method not only improves recognition accuracy but also ensures robustness across diverse scenarios.

Clinical Features of Typically Developing Children With and Without Prenatal Alcohol Exposure

To determine if prenatal alcohol exposure (PAE) affected physical and cognitive/behavioral outcomes in apparently typically developing, first-grade children. Three groups were compared: children with fetal alcohol spectrum disorders (FASD); children with PAE without FASD; and children without PAE. The three groups were significantly different on most physical traits and fewer neurodevelopmental traits. Two-group comparisons of exposed and unexposed, non-FASD groups were statistically different on: height, weight, head circumference (OFC), body mass index (BMI), and palpebral fissure length (PFL). Neurobehavioral outcomes were significant in three-group, but not two-group, comparisons. Few sex differences were observed; however, sex ratios indicated fewer male offspring in first grade among women who consumed 6+ drinks per occasion during pregnancy. For weight, OFC, BMI, age, rural residence, and drinking measures, mothers of exposed children without FASD were intermediaries between, and significantly different from, the other maternal groups. Adjusted for socioeconomic covariates, multivariate analysis of covariance (MANCOVA), three-group comparisons were significantly different for cognitive/behavioral variables (p<.001); however, two-group neurobehavior comparisons for children without FASD were not significant (p>.05). Physical trait MANCOVA comparisons of the non-FASD groups were significant only for weight (p<.004) when tested univariately and through stepdown analysis. Socioeconomic-adjusted trend plots were in the expected direction for nonverbal IQ, problem behaviors, attention, height, weight, OFC, vermilion, PFL, and total dysmorphology score. Even when meeting developmental norms, children with PAE exhibited trends of poorer growth and cognitive/behavioral traits than children without PAE. These findings support the notion that abstinence during pregnancy is best.

Amplifying Research: The Potential for Podcasts to Boost Radiology Journal Article Exposure.

Background Podcasts have become an increasingly popular method of communicating information in medicine, including in radiology. However, the effect of podcasts on the reach of journal articles remains unclear. Purpose To evaluate the influence of Radiology podcasts on the performance metrics, including downloads, citations, and Altmetric Attention Score (AAS), of Radiology articles. Materials and Methods This was a retrospective study. All articles published in the print version of Radiology from January 2021 to December 2022 were reviewed; editorials and case reports were excluded. Articles featured on Radiology podcasts were included in the podcast group. Articles published within the same journal issue and category were the nonpodcast group. Downloads, Google Scholar citations, Dimensions citations, and AAS metrics were recorded. The Mann-Whitney U test was used to compare medians and evaluate differences between older and more recently published articles. Results The podcast group, composed of 88 articles, exhibited significantly higher median values for downloads (PG, 4521.0; nonpodcast group, 2123.0; P < .001), Google Scholar citations (podcast group, 14.5; nonpodcast group, 10.0; P = .01), Dimensions citations (podcast group, 12.0; nonpodcast group, 9.0; P = .01), and AAS (podcast group, 43.0; nonpodcast group, 10.0; P < .001) compared with the nonpodcast group of 378 articles. Within both groups, articles published in the earlier nonpodcast group (January to June 2021) had higher downloads (podcast group, P = .08; nonpodcast group, P < .001), Google Scholar citations (podcast group and nonpodcast group, P < .001), and Dimension citations (podcast group and nonpodcast group, P < .001) than articles from the later period (July to December 2022). AAS markedly increased in recent podcast articles (P = .03), but AAS for nonpodcast articles significantly decreased over time (P = .01). Conclusion Radiology articles featured on the Radiology podcast had greater median metrics, including downloads, Google Scholar citations, Dimensions citations, and AAS, compared with nonpodcast articles, suggesting that podcasts can be an effective method of disseminating and amplifying research within the field of radiology. © RSNA, 2024 See also the editorial by Chu and Nicola in this issue.

A new hybrid deep neural network for multiple sites PM2.5 forecasting

Many studies have confirmed that fine particulate matter (PM2.5) poses significant hazards to both human health and the ecological environment. Predicting future trends in PM2.5 concentrations is crucial for preventing air pollution hazards to human health. However, current machine learning-based forecasting models often focus on specific regions or sites, resulting in poor spatial generalization performance. To address this issue, this study utilizes ERA5 meteorological reanalysis data, MERRA2 assimilated aerosol optical depth (AOD) data, and ground pollutant monitoring site data to construct a three-dimensional dataset. A novel hybrid deep neural network model (D_GAT) is proposed to simultaneously forecast the future 72h PM2.5 concentration trends for all sites in China. The D_GAT model combines the advantages of a graph attention network and a long short-term memory neural network, which can effectively aggregate spatial information between sites and simulate the spatial transport process and time series change characteristics of pollutant particles. Moreover, the proposed calculation method for attention scores quantified based on the actual pollutant propagation characteristics, combined with the upper atmosphere pollution transport process represented by AOD, can better express the pollution contributions of different neighboring sites to the predicted central site. Experimental results show that, compared to four other baseline models, the novel model achieves an average R2 of 0.732 for all sites in 72-h prediction, which is the highest among the five models, and the prediction accuracy of 72h is also in the forefront compared with the current similar research. The RMSE and MAE are 14.63 μg/m3 and 9.49 μg/m3, respectively, which are 2–4 μg/m3 lower than the other four baseline models, indicating that it has higher reliability and can achieve the goal of timely prediction and early warning. Overall, the new model is an effective tool for multiple sites generalization forecasting.

Quality-driven deep feature representation learning and its industrial application to soft sensors

Establishing effective soft sensors relies on feature representation that is capable of capturing critical information. Stacked AutoEncoder (SAE) is able to capture the intricate structures of data characterized by high dimensionality and strong non-linearity by extracting abstract features layer by layer, making it widely used. However, the pretraining process of SAE is unsupervised, which means the features extracted cannot leverage label information to provide more actionable insights for downstream tasks. To extract more valuable feature representation, a new quality-driven dynamic weighted SAE (QD-SAE) is proposed in this paper. By incorporating supervised information dominated by the quality variable into the learned features during the pretraining of the SAE and weighting the abstract features layer by layer, the features that are beneficial to the prediction task are thus focused. In QD-SAE, the supervised information is computed by an improved attention score. In the initial state of the supervised fine-tuning process, the weighted features compose the hidden layers of the entire network. Finally, a benchmark function case and a real complex industrial process case are used to verify the effectiveness and advantages of QD-SAE. The experimental analyses demonstrate that the soft sensor constructed by the QD-SAE can predict the output variable with high accuracy and outperforms the conventional neural networks.

Which orthodontic articles are accessed online the most? Exploring article usage metrics along with citations and altmetrics.

To investigate the current state of article usage metrics in orthodontics. Out of all orthodontic journals listed in Journal Citation Reports 2022, the European Journal of Orthodontics and The Angle Orthodontist fulfilled the inclusion criteria. All journal issues published in 2021 were scrutinized for original research articles and systematic reviews/meta-analyses, and the following features were collected: article type, subject, title, number of words and authors, Altmetric Attention Score (AAS), X (formerly Twitter) posts, and Mendeley reads. Article citations, number of publications, and h-index of the last authors were retrieved from Web of Science (WoS). 181 articles were considered eligible. The median number of views and downloads of included articles was 1296 (range: 355-10,233) and 793 (range: 167-3629). Page views, downloads, and total views were significantly correlated with WoS citations (rho > 0.345; P < .001). There was no correlation between usage metrics, AAS, X posts, and Mendeley reads. Number of downloads were significantly higher in studies dealing with new technologies, and where the last author had 1-40 publications or an h-index of 0-30. Page views, downloads, and total views were positively correlated with WoS citations and, therefore, may serve as an early estimate of future citations. Significant variations in article downloads may be expected in relation to article subject, scientific productivity, and impact of the last authors.

Citation and Altmetric Attention Score of Top 100 Highly Cited Articles in Health Information Management Journals: A Correlation Study

Citation and Altmetric Attention Score of Top 100 Highly Cited Articles in Health Information Management Journals: A Correlation Study

Resting-State Brain Function Alteration in Colorectal Cancer Patients.

To investigate the abnormal pattern of altered functional activity in the brain and the neuroimaging mechanisms underlying the cognitive impairment of patients with colorectal cancer (CRC) via resting-state functional magnetic resonance imaging (rs-fMRI). CRC patients (n = 56) and healthy controls (HCs) (n = 50) were studied. The participants underwent rs-fMRI scans and the Montreal Cognitive Assessment (MoCA). The amplitude of low-frequency fluctuations (ALFF), degree centrality (DC), regional homogeneity (ReHo), and MoCA scores, were calculated for participants. The scores of executives, visuospatial, memory, language and attention were lower in CRC patients. ReHo and ALFF values in the left postcentral gyrus, ReHo values in the right postcentral gyrus, ALFF and DC values in the left middle occipital gyrus, ReHo and DC values in the right lingual gyrus, DC values in the right angular gyrus and precuneus, and ALFF values in the left middle temporal gyrus decreased conspicuously in the CRC patients. CRC patients have abnormal resting state function, mainly in the brain areas involved in cognitive function. The overlapping brain regions with abnormal functional indicators are in the middle occipital gyrus, postcentral gyrus, and lingual gyrus. This study reveals the potential biological pathways involved in brain impairment and neurocognitive decline in patients with CRC.

Bibliometric Analysis of Predictors of Altmetric Attention Scores in Orthopedic Research: Investigating Online Visibility.

Altmetric Attention Score (AAS) captures online attention received by a research article in addition to traditional bibliometrics. We present a comprehensive bibliometric analysis of high AAS articles and identify predictors of AAS in orthopedics. The top 30 articles with highest AAS were selected from orthopedic journals using the Dimensions App. Multilevel mixed-effects linear regression was used to address clustering in articles from the same journal, with journals as the leveling variable. A total of 750 articles from 25 journals were included. In the final multivariable model, the funding source (none, industry, government, foundation, university, or multiple), findings (positive, negative, neutral, or not applicable), and the journal's impact factor were significant at P<.05. Predictors of AAS are similar to predictors of traditional bibliometrics. Future studies need prospective dynamic data to further elucidate the AAS. [Orthopedics. 20XX;4X(X):XXX-XXX.].

Attention-based CNN-BiLSTM for sleep state classification of spatiotemporal wide-field calcium imaging data

BackgroundWide-field calcium imaging (WFCI) with genetically encoded calcium indicators allows for spatiotemporal recordings of neuronal activity in mice. When applied to the study of sleep, WFCI data are manually scored into the sleep states of wakefulness, non-REM (NREM) and REM by use of adjunct EEG and EMG recordings. However, this process is time-consuming, invasive and often suffers from low inter- and intra-rater reliability. Therefore, an automated sleep state classification method that operates on spatiotemporal WFCI data is desired. New methodA hybrid network architecture consisting of a convolutional neural network (CNN) to extract spatial features of image frames and a bidirectional long short-term memory network (BiLSTM) with attention mechanism to identify temporal dependencies among different time points was proposed to classify WFCI data into states of wakefulness, NREM and REM sleep. ResultsSleep states were classified with an accuracy of 84 % and Cohen’s κ of 0.64. Gradient-weighted class activation maps revealed that the frontal region of the cortex carries more importance when classifying WFCI data into NREM sleep while posterior area contributes most to the identification of wakefulness. The attention scores indicated that the proposed network focuses on short- and long-range temporal dependency in a state-specific manner. Comparison with existing methodOn a held out, repeated 3-hour WFCI recording, the CNN-BiLSTM achieved a κ of 0.67, comparable to a κ of 0.65 corresponding to the human EEG/EMG-based scoring. ConclusionsThe CNN-BiLSTM effectively classifies sleep states from spatiotemporal WFCI data and will enable broader application of WFCI in sleep research.

TDCS-enhanced cognitive training improves attention and alters connectivity in control and somatomotor networks: A triple blind study

BackgroundExecutive dysfunction such as inattention or forgetfulness can lead to disruptions in a person's daily functioning and quality of life. Objective/HypothesisThis triple-blinded randomized clinical trial assessed the efficacy of bifrontal (over the forehead) transcranial direct current stimulation (tDCS) concurrent with cognitive training to improve cognitive performance in a healthy sample. MethodsFifty-eight participants were randomly assigned to one of three stimulation conditions (2 mA left anode–right cathode, 2 mA right anode–left cathode, or sham), which was administered with cognitive training tasks 3x/week over 12 weeks with assessments at baseline, midpoint (6 weeks), and post-training (12 weeks). We assessed cognitive performance, functional connectivity, and the influence of individual differences in training advancement. ResultsForty participants completed training. We found that at midpoint and post, all groups improved significantly on overall cognitive performance. The left anode group's attention & vigilance score improved significantly at post, but the other two groups did not. Greater attention training advancement predicted attention improvement by post, most notably in the left anode group. Finally, within-network connectivity decreased in the control network and increased in the somatomotor network across all groups. ConclusionsThese results suggest that, given cognitive training, the left anode montage is more effective at improving attention than the right anode montage and sham. Future research may focus on the application of the left anode montage during cognitive training to assess its effectiveness in improving cognition in neuropsychiatric disorders.

MRSAPose: Multi-level routing sparse attention for multi-person pose estimation

Multi-person Pose Estimation (MPPE) aims to reconstruct human poses by locating and connecting keypoints of individuals in input images. The variability of human poses and the complexity of scenes make MPPE reliant on both local details and global structures, and the absence of either can lead to the generation of deformed poses. With the emergence of Transformer, the performance of MPPE has been significantly improved. However, due to self-attention computing attention scores between each pair of positions, the current Transformer-based MPPE exhibits high quadratic complexity. To address these issues, this paper proposes a novel pose estimation model, MRSAPose. MRSAPose utilizes Multi-level Routing Sparse Attention (MRSA) to dynamically select relevant regions for attention, reducing computational complexity and mitigating the impact of irrelevant regions. Furthermore, MRSAPose constructs a Transformer-CNN Parallel Interaction Block (T-CP block) through MRSA and Recursive Residual Gated Convolution (Res-gnConv), facilitating parallel learning of global and local information. By relying on multi-level routing algorithms and high-order spatial interactions conducted by recursive processing of adjacent features, T-CP block helps MRSAPose effectively alleviates the issues of occlusion and misalignment in pose estimation. On multiple challenging keypoint datasets, MRSAPose outperforms current state-of-the-art algorithms, particularly excelling in crowded and occluded scenes.

An Empirical Study on Teaching Management and Quality Feedback Based on Human Behavior Detection

In the current education field, the assessment of teaching management quality mostly relies on subjective judgment and static data, and lacks a real-time and dynamic feedback mechanism. In this study, we propose a deep learning-based human behavior analysis method, which aims to assess teaching management quality in real time by analyzing the behaviors of teachers and students in the classroom. First, in order to detect individual students in the video stream, an augmented detection framework based on YOLO v5s is introduced to process and analyze human actions and interaction patterns in the video data. Immediately after that, we design a channel residual decoupled convolutional neural network to recognize the different states of students. Teaching management quality is assessed by detecting students' classroom attention scores. By conducting experiments in different disciplines and teaching management environments to collect and train the model, the results show that the method can effectively improve the objectivity and accuracy of teaching management quality assessment.

Bibliometric top ten healthcare-related ChatGPT publications in the first ChatGPT anniversary.

Since its public release on November 30, 2022, ChatGPT has shown promising potential in diverse healthcare applications despite ethical challenges, privacy issues, and possible biases. The aim of this study was to identify and assess the most influential publications in the field of ChatGPT utility in healthcare using bibliometric analysis. The study employed an advanced search on three databases, Scopus, Web of Science, and Google Scholar, to identify ChatGPT-related records in healthcare education, research, and practice between November 27 and 30, 2023. The ranking was based on the retrieved citation count in each database. The additional alternative metrics that were evaluated included (1) Semantic Scholar highly influential citations, (2) PlumX captures, (3) PlumX mentions, (4) PlumX social media and (5) Altmetric Attention Scores (AASs). A total of 22 unique records published in 17 different scientific journals from 14 different publishers were identified in the three databases. Only two publications were in the top 10 list across the three databases. Variable publication types were identified, with the most common being editorial/commentary publications (n=8/22, 36.4%). Nine of the 22 records had corresponding authors affiliated with institutions in the United States (40.9%). The range of citation count varied per database, with the highest range identified in Google Scholar (1019-121), followed by Scopus (242-88), and Web of Science (171-23). Google Scholar citations were correlated significantly with the following metrics: Semantic Scholar highly influential citations (Spearman's correlation coefficient ρ=0.840, p<0.001), PlumX captures (ρ=0.831, p<0.001), PlumX mentions (ρ=0.609, p=0.004), and AASs (ρ=0.542, p=0.009). In conclusion, despite several acknowledged limitations, this study showed the evolving landscape of ChatGPT utility in healthcare. There is an urgent need for collaborative initiatives by all stakeholders involved to establish guidelines for ethical, transparent, and responsible use of ChatGPT in healthcare. The study revealed the correlation between citations and alternative metrics, highlighting its usefulness as a supplement to gauge the impact of publications, even in a rapidly growing research field.

Is Open Access Criminology Influential?

Open access is a hot topic throughout the sciences, including in criminology and criminal justice (CCJ), with increasing calls for accessibility of high-quality research for the public and policymakers. Yet, the question remains: How influential are open access publications? We use Altmetric data from 95 CCJ journals to examine whether the presence and level of open access corresponds with variations in three influence indicators: Altmetric Attention Scores, Twitter/X mentions, and news mentions. Results indicate that open access is positively associated with Altmetric influence, even at lower tiers of access.

RSVP-based BCI for inconspicuous targets: detection, localization, and modulation of attention

Objective.While brain-computer interface (BCI) based on rapid serial visual presentation (RSVP) is widely used in target detection, patterns of event-related potential (ERP), as well as the performance on detecting inconspicuous targets remain unknown. Moreover, participant-screening methods to excluded 'BCI-blind' users are still lacking.Approach.A RSVP paradigm was designed with targets of varied concealment, size, and location. ERPs (e.g. P300 and N2pc) and target detection accuracy were compared among these conditions. The relationship between participants' attention scores and target detection accuracy was also analyzed to test attention level as a criterion for participant screening.Main results.Statistical analysis showed that the conditions of target concealment and size significantly influenced ERP. In particular, ERP for inconspicuous targets, such as concealed and small targets, exhibited lower amplitudes and longer latencies. In consistent, the accuracy of detection in inconspicuous condition was significantly lower than that of conspicuous condition. In addition, a significant association was found between attention scores and target detection accuracy for camouflaged targets.Significance.The study was the first to address ERP features among multiple dimensions of concealment, size, and location. The conclusion provided insights into the relationship between ERP decoding and properties of targets. In addition, the association between attention scores and detection accuracy implied a promising method in screening well-behaved participants for camouflaged target detection.

A Genetic Causal Explainer for Deep Knowledge Tracing

Knowledge tracing (KT) has become an increasingly relevant problem in intelligent education services. Deep learning-based knowledge tracing (DLKT) achieves superb performance in terms of prediction accuracy, but it lacks of explainability, which makes us hard to trust or understand models. The previous work on explaining DLKT was mainly based on gradients or attention scores, which is susceptible to spurious correlations, reducing the credibility of the explanation. To address this limitation, in this paper, we propose a causal explanation method based on the genetic algorithm (GA), named Genetic Causal Explainer(GCE), which constructs a causal framework to estimate the attribution of subsequence to the predictions of DLKT models, and a genetic coding system is designed. Further, A multi-strategy initialization method inspired by domain prior knowledge is proposed, and a global empirical matrix is introduced to capture the causal correlation knowledge during the search process across instances, and guiding the mutation operators. The GCE as a post hoc explanation method can generate explanation results without affecting model training, and can be applied to analyze different DLKT models. Experimental results demonstrate the GCE perform better than other explanation methods in terms of accuracy and readability in quantitative assessments. Meanwhile, the GCE also shows good application prospects in mining educational laws and comparing KT models.

Baseline brain volume predicts home-based transcranial direct current stimulation effects on inattention in adults with attention-deficit/hyperactivity disorder

BackgroundHome-based transcranial direct current stimulation (Hb-tDCS) is a non-invasive brain stimulation technique that utilizes low-intensity electric currents delivered via scalp electrodes to modulate brain activity. It holds significant promise for addressing inattention in adults with attention-deficit/hyperactivity disorder (ADHD). However, its effectiveness varies among individuals, and predicting outcomes remains uncertain, partially due to the influence of individual differences in ADHD-related brain anatomy. MethodsWe analyzed data from a subsample, composed by twenty-nine adult patients with ADHD, of the Treatment of Inattention Symptoms in Adult Patients with ADHD (TUNED) trial. Fourteen patients underwent active anodal right cathodal left dorsolateral prefrontal cortex (DLPFC) Hb-tDCS for 4 weeks and fifteen received sham-related tDCS intervention. Inattention outcome was evaluated at both baseline and endpoint (4th week). Baseline structural measures of the DLPFC, anterior cingulate cortex (ACC) and subcortical structures, previously associated with ADHD, were quantified. Several linear mixed models, with a three-way interaction between the fixed predictors brain volume or thickness, time, and treatment were calculated. Multiple comparison corrections were applied using the Benjamini-Hochberg method. ResultsBaseline volume of the left DLPFC regions middle frontal gyrus (t (25) = 3.33, p-adjusted = 0.045, Cohen's d = 1.33, 95% CI = [0.45, 2.19]), inferior frontal gyrus (orbital part) (t (25) = 3.10, p-adjusted = 0.045, Cohen's d = 1.24, 95% CI = [0.37, 2.08]), and of the left ACC supragenual (t (25) = 3.15, p-adjusted = 0.045, Cohen's d = 1.26, 95% CI = [0.39, 2.11]) presented significant association with the inattentive score improvement only in the active tDCS group. More specifically, the smaller these regions were, the more the symptoms improved following anodal right cathodal left DLPFC Hb-tDCS. ConclusionHb-tDCS was associated with greater improvement in brain areas related to attention regulation. Brain MRI can be potentially used to predict clinical response to tDCS in ADHD adults.