Human Brain Mapping最新文献

{"title":"Correction to “Decoding the Spatiotemporal Dynamics of Neural Response Similarity in Auditory Processing: A Multivariate Analysis Based on OPM-MEG”","authors":"","doi":"10.1002/hbm.70228","DOIUrl":"https://doi.org/10.1002/hbm.70228","url":null,"abstract":"<p>Liu, C., Y. Ma, X. Liang, M. Xiang, H. Wu, and X. Ning. 2025. “Decoding the Spatiotemporal Dynamics of Neural Response Similarity in Auditory Processing: A Multivariate Analysis Based on OPM-MEG.” <i>Human Brain Mapping</i> 46, no. 4: e70175. https://doi.org/10.1002/hbm.70175.</p><p>One of the corresponding author's name was inadvertently misspelled as “Xiaoling Ning”. It should be corrected to “Xiaolin Ning”.</p><p>The online version of the article has been corrected accordingly.</p><p>We apologize for this error.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 7","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70228","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143919565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping Brain Lesions to Conduction Delays: The Next Step for Personalized Brain Models in Multiple Sclerosis","authors":"C. Mazzara,&nbsp;A. Ziaeemehr,&nbsp;E. Troisi Lopez,&nbsp;L. Cipriano,&nbsp;M. Angiolelli,&nbsp;M. Sparaco,&nbsp;M. Quarantelli,&nbsp;C. Granata,&nbsp;G. Sorrentino,&nbsp;M. Hashemi,&nbsp;V. Jirsa,&nbsp;P. Sorrentino","doi":"10.1002/hbm.70219","DOIUrl":"https://doi.org/10.1002/hbm.70219","url":null,"abstract":"<p>Multiple sclerosis (MS) is a clinically heterogeneous, multifactorial autoimmune disorder affecting the central nervous system. Structural damage to the myelin sheath, resulting in the consequent slowing of the conduction velocities, is a key pathophysiological mechanism. In fact, the conduction velocities are closely related to the degree of myelination, with thicker myelin sheaths associated to higher conduction velocities. However, how the intensity of the structural lesions of the myelin translates to slowing of nerve conduction delays is not known. In this work, we use large-scale brain models and Bayesian model inversion to estimate how myelin lesions translate to longer conduction delays across the damaged tracts. A cohort of 38 subjects (20 healthy and 18 with MS) underwent MEG recordings during an eyes-closed resting-state condition, along with MRI acquisitions and detailed white matter tractography analysis. We observed that MS patients consistently showed decreased power within the alpha frequency band (8–13 Hz) as compared to the healthy group. We also derived a lesion matrix indicating the percentage of lesions for each tract in every patient. Using large-scale brain modeling, the neural activity of each region was represented as a Stuart-Landau oscillator operating in a regime showing damped oscillations, and the regions were coupled according to subject-specific connectomes. We propose a linear formulation to the relationship between the conduction delays and the amount of structural damage in each white matter tract. Dependent upon the parameter <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>γ</mi>\u0000 </mrow>\u0000 <annotation>$$ upgamma $$</annotation>\u0000 </semantics></math>, this function translates lesions into edge-specific conduction delays (leading to shifts in the power spectra). Using deep neural density estimators, we found that the estimation of <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>γ</mi>\u0000 </mrow>\u0000 <annotation>$$ upgamma $$</annotation>\u0000 </semantics></math> showed a strong correlation with the alpha peak in MEG recordings. The most probable inferred <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>γ</mi>\u0000 </mrow>\u0000 <annotation>$$ upgamma $$</annotation>\u0000 </semantics></math> for each subject is inversely proportional to the observed peaks, while power peaks themselves do not correlate with total lesion volume. Furthermore, the estimated parameters were predictive (cross-sectionally) of individual clinical disability. This study represents the initial exploration showcasing the location-specific impact of myelin lesions on conduction delays, thereby enhancing the customization of models for individuals with multiple sclerosis.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 7","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70219","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143901097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Layer-Dependent Effect of Aβ-Pathology on Cortical Microstructure With Ex Vivo Human Brain Diffusion MRI at 7 Tesla","authors":"Zhiyong Zhao,&nbsp;Zuozhen Cao,&nbsp;Qinfeng Zhu,&nbsp;Haoan Xu,&nbsp;Sihui Li,&nbsp;Liangying Zhu,&nbsp;Guojun Xu,&nbsp;Keqing Zhu,&nbsp;Jing Zhang,&nbsp;Dan Wu","doi":"10.1002/hbm.70222","DOIUrl":"https://doi.org/10.1002/hbm.70222","url":null,"abstract":"<p>The laminar-specific distributions of Aβ and Tau deposition in the neocortex of Alzheimer's disease (AD) have been established. However, direct evidence about the effect of AD pathology on cortical microstructure is lacking in human studies. We performed high-resolution T2-weighted and diffusion-weighted MRI (dMRI) on 15 ex vivo whole-hemisphere specimens, including eight cases with low AD neuropathologic change, three cases with primary age-related tauopathy (PART), and four healthy controls (HCs). Using the diffusion tensor model, we evaluated microstructure patterns in six layers of gray matter cortex and performed MRI-histology correlation analysis across cortical layers. Aβ-positive cases exhibited higher diffusivity than Aβ-negative cases (PART and HC) in selected cortical regions, particularly in the inferior frontal cortex. Both Aβ/Tau depositions and dMRI-based microstructural markers demonstrated distinct cortical layer-dependent and region-specific patterns. A significant positive correlation was observed between increased diffusivity and Aβ burden across six cortical layers but not with Tau burden. Furthermore, the mean diffusivity in layer V of the inferior frontal cortex significantly increased with the Amyloid stage. Our findings demonstrate a layer-dependent effect of Aβ pathology on cortical microstructure of the human brain, which may be used to serve as a marker of low AD neuropathologic change.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 7","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70222","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Asymmetric Modulation of Brain Connectivity by Anodal Transcranial Direct Current Stimulation in Healthy Individuals: A Single-Blind, Randomized Sham-Controlled Trial","authors":"Tiffany Carther-Krone,&nbsp;Zachary A. McAllister,&nbsp;Eun Hyung Choi,&nbsp;Lawrence Ryner,&nbsp;Ji Hyun Ko","doi":"10.1002/hbm.70218","DOIUrl":"https://doi.org/10.1002/hbm.70218","url":null,"abstract":"<p>Transcranial direct current stimulation (tDCS) applied to the dorsolateral prefrontal cortex (DLPFC) has shown asymmetric behavioral effects, though the underlying neurophysiological mechanisms remain unclear. In this preliminary study with 34 healthy individuals, tDCS was applied to either the left or right DLPFC or a sham group. Behavioral and neurophysiological changes were examined by the Stroop test and resting-state fMRI, respectively, which were measured before and after a 15-min tDCS session. Seed-to-voxel connectivity analysis with seeds placed under the tDCS target regions (F3 and F4) showed no significant changes, but voxel-to-voxel whole-brain intrinsic connectivity (IC) analysis revealed significant 3 × 2 interaction effects (stimulation site × time) in the right DLPFC (18 mm off from the F4). Post hoc analysis showed that only the right DLPFC stimulation led to an increase in IC from pre- to post-stimulation. Consistent with this finding, right DLPFC stimulation improved Stroop task performance measured by increased interference score, which represents better inhibition of irrelevant information. These findings provide further insights into the hemispheric difference of tDCS effects and its underlying neurophysiological mechanisms. However, the small sample size limits the generalizability of the results and necessitates further research with a larger cohort for confirmation.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 7","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70218","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143897025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Metric Approach for the Comparison of Denoising Techniques for Resting-State fMRI","authors":"Federica Goffi,&nbsp;Anna Maria Bianchi,&nbsp;Giandomenico Schiena,&nbsp;Paolo Brambilla,&nbsp;Eleonora Maggioni","doi":"10.1002/hbm.70080","DOIUrl":"https://doi.org/10.1002/hbm.70080","url":null,"abstract":"<p>Despite the increasing use of resting-state functional magnetic resonance imaging (rs-fMRI) data for studying the spontaneous functional interactions within the brain, the achievement of robust results is often hampered by insufficient data quality and by poor knowledge of the most effective denoising methods. The present study aims to define an appropriate denoising strategy for rs-fMRI data by proposing a robust framework for the quantitative and comprehensive comparison of the performance of multiple pipelines made available by the newly proposed HALFpipe software. This will ultimately contribute to standardizing rs-fMRI preprocessing and denoising steps. Fifty-three participants took part in the study by undergoing a rs-fMRI session. Synthetic rs-fMRI data from one subject were also generated. Nine different denoising pipelines were applied in parallel to the minimally preprocessed fMRI data. The comparison was conducted by computing previously proposed and novel metrics that quantify the degree of artifact removal, signal enhancement, and resting-state network identifiability. A summary performance index, accounting for both noise removal and information preservation, was proposed. The results confirm the performance heterogeneity of different denoising pipelines across the different quality metrics. In both real and synthetic data, the summary performance index favored the denoising strategy including the regression of mean signals from white matter and cerebrospinal fluid brain areas and global signal. This pipeline resulted in the best compromise between artifact removal and preservation of the information on resting-state networks. Our study provided useful methodological tools and key information on the effectiveness of multiple denoising strategies for rs-fMRI data. Besides providing a robust comparison approach that could be adapted to other fMRI studies, a suitable denoising pipeline for rs-fMRI data was identified, which could be used to improve the reproducibility of rs-fMRI findings.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 7","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70080","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Oscillations of the Wandering Mind: Neural Evidence for Distinct Exploration/Exploitation Strategies in Younger and Older Adults","authors":"Catherine N. Moran,&nbsp;David P. McGovern,&nbsp;Mike Melnychuk,&nbsp;Alan F. Smeaton,&nbsp;Paul M. Dockree","doi":"10.1002/hbm.70174","DOIUrl":"https://doi.org/10.1002/hbm.70174","url":null,"abstract":"<p>This study traced the neurophysiological signals of fluctuating attention and task-related processing to ascertain the mechanistic basis of transient strategic shifts between competing task focus and mind-wandering, as expressed by the ‘exploitation/exploration’ framework, and explored how they are differentially affected with age. Thirty-four younger (16 female, mean age 22 years) and 34 healthy older (20 female, mean age 71 years) adults performed the Gradual Contrast Change Detection task; monitoring a continuously presented flickering annulus for intermittent gradual contrast reductions and responding to experience sampling probes to discriminate the nature of their thoughts at discrete moments. Electroencephalography and pupillometry were concurrently recorded during target- and probe-related intervals. Older adults tracked the downward stimulus trajectory with greater sensory integrity (reduced target SSVEP amplitude) and demonstrated earlier initiation of evidence accumulation (earlier onset CPP), attenuated variability in the attentional signal (posterior alpha) and more robust phasic pupillary responses to the target, suggesting steadier attentional engagement with age. Younger adults only exhibited intermittent sensory encoding, indexed by greater variability in the sensory (SSVEP) and attentional (alpha) signals before mind-wandering relative to focused states. Attentional variability was accompanied by disrupted behavioural performance and reduced task-related neural processing, independent of age group. Together, this elucidates distinct performance strategies employed by both groups. Older adults suspended mind-wandering and implemented an exploitative oscillation strategy to circumvent their reduced cognitive resources and allay potential behavioural costs. Conversely, younger adults exhibited greater exploration through mind-wandering, utilising their greater cognitive resources to flexibly alternate between competing goal-directed and mind-wandering strategies, with limited costs.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 6","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70174","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143877797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping Contributions of the Anterior Temporal Semantic Hub to the Processing of Abstract and Concrete Verbs","authors":"Emiko J. Muraki,&nbsp;Penny M. Pexman,&nbsp;Richard J. Binney","doi":"10.1002/hbm.70210","DOIUrl":"https://doi.org/10.1002/hbm.70210","url":null,"abstract":"<p>Multiple representation theories of semantic processing propose that word meaning is supported by simulated sensorimotor experience in modality-specific neural regions, as well as in cognitive systems that involve processing of linguistic, emotional, and introspective information. According to the hub-and-spoke model of semantic memory, activity from these distributed cortical areas feeds into a primary semantic hub located in the ventral anterior temporal lobe (vATL). In the present pre-registered study, we examined whether different types of abstract verbs (mental, emotional and nonembodied) and concrete (embodied) verbs all engage the vATL, and also whether they differentially recruit a broader set of distributed neurocognitive systems (consistent with multiple representation theories). Finally, we investigated whether there is information about different verb types distributed across the broader ATL region, consistent with a Graded Semantic Hub Hypothesis. We collected data from 30 participants who completed a syntactic classification task (is it a verb? Yes or no) and a numerical judgment task which served as an active but less semantic baseline task. Whole brain univariate analyses revealed consistent BOLD signal throughout the canonical semantic network, including the left inferior frontal gyrus, left middle temporal gyrus, and the vATL. All types of abstract verbs engaged the vATL except for mental state verbs. Finally, a multivariate pattern analysis revealed clusters within the ATL that were differentially engaged when processing each type of abstract verb. Our findings extend previous research and suggest that the hub-and-spoke hypothesis and the graded semantic hub hypothesis provide a neurobiologically constrained model of semantics that can account for abstract verb representation and processing.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 6","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70210","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI Distance Measures as a Predictor of Subsequent Clinical Status During the Preclinical Phase of Alzheimer's Disease and Related Disorders","authors":"Xinyi Zhang,&nbsp;Brian S. Caffo,&nbsp;Anja Soldan,&nbsp;Corinne Pettigrew,&nbsp;Erus Guray,&nbsp;Christos Davatzikos,&nbsp;John C. Morris,&nbsp;Tammie L. S. Benzinger,&nbsp;Sterling C. Johnson,&nbsp;Colin L. Masters,&nbsp;Jurgen Fripp,&nbsp;Susan M. Resnick,&nbsp;Murat Bilgel,&nbsp;Walter A. Kukull,&nbsp;Marilyn S. Albert,&nbsp;Zheyu Wang","doi":"10.1002/hbm.70205","DOIUrl":"https://doi.org/10.1002/hbm.70205","url":null,"abstract":"<p>Brain atrophy over time, as measured by magnetic resonance imaging (MRI), has been shown to predict subsequent cognitive impairment among individuals who were cognitively normal when first evaluated, indicating that subtle brain atrophy associated with Alzheimer's disease (AD) may begin years before clinical symptoms appear. Traditionally, atrophy has been quantified by differences in brain volume or thickness over a specified timeframe. Research indicates that the rate of atrophy varies across different brain regions, which themselves exhibit complex spatial and hierarchical organizations. These characteristics collectively emphasize the need for diverse summary measures that can effectively capture the multidimensional nature of degeneration. In this study, we explore the use of distance measurements to quantify brain volumetric changes using processed MRI data from the Preclinical Alzheimer's Disease Consortium (PAC). We conducted a series of analyses to predict future diagnostic status by modeling MRI trajectories for participants who were cognitively normal at baseline and either remained cognitively normal or progressed to mild cognitive impairment (MCI) over time, with adjustments for age, sex, education, and APOE genotype. We consider multiple distance measures and brain regions through a two-step approach. First, we build base models by fitting individual mixed-effect models for each distance metric and brain region pairing, using follow-up diagnosis (normal vs. MCI) as the outcome and volumetric changes from the baseline, as summarized by a given distance measure, as predictors. The second step aggregates these individual region-distance base models to derive an overall estimate of diagnostic status. Our analyses showed that the distance measures approach consistently outperformed the traditional direct volumetric approach in terms of predictive accuracy, both in individual base models and the aggregated models. This work highlights the potential advantage of using distance measures over the traditional direct volumetric approach to capture the multidimensional aspects of atrophy in the development of AD and related disorders.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 6","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70205","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sensitivity of Quantitative Susceptibility Mapping for Clinical Research in Deep Gray Matter","authors":"Fahad Salman,&nbsp;Abhisri Ramesh,&nbsp;Thomas Jochmann,&nbsp;Mirjam Prayer,&nbsp;Ademola Adegbemigun,&nbsp;Jack A. Reeves,&nbsp;Gregory E. Wilding,&nbsp;Junghun Cho,&nbsp;Dejan Jakimovski,&nbsp;Niels Bergsland,&nbsp;Michael G. Dwyer,&nbsp;Robert Zivadinov,&nbsp;Ferdinand Schweser","doi":"10.1002/hbm.70187","DOIUrl":"https://doi.org/10.1002/hbm.70187","url":null,"abstract":"<p>Quantitative susceptibility mapping (QSM) is an advanced MRI technique for assessing iron, calcium, and myelin tissue levels based on magnetic susceptibility. QSM consists of multiple processing steps, with various choices for each step. While QSM is increasingly applied in neurodegenerative disease research, its reproducibility and sensitivity in detecting susceptibility changes across groups or over time, which underpin the interpretation of clinical outcomes, have not been thoroughly quantified. This study aimed to evaluate how choices in background field removal (BFR), dipole inversion algorithms, and anatomical referencing impact the detection of changes in deep gray matter susceptibility. We used aging-related changes in brain iron, established in earlier foundational studies, as a surrogate model to test the sensitivity and reproducibility of 378 different QSM pipelines toward the detection of longitudinal susceptibility changes in a clinical setting. We used 10-year follow-up data and scan-rescan data of healthy adults scanned at 3T. Our results demonstrated high variability in the sensitivity of QSM pipelines toward detecting susceptibility changes. While most pipelines detected the same over-time changes, the choice of the BFR algorithm and the referencing strategy influenced reproducibility error and sensitivity substantially. Notably, pipelines using RESHARP with AMP-PE, HEIDI, or LSQR inversion showed the highest overall sensitivity. The findings suggest a strong impact of algorithmic choices in QSM processing on the ability to detect physiological changes in the brain. Careful consideration should be given to the pipeline configuration for reliable clinical outcomes.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 6","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70187","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"WMH-DualTasker: A Weakly Supervised Deep Learning Model for Automated White Matter Hyperintensities Segmentation and Visual Rating Prediction","authors":"Yilei Wu,&nbsp;Zijian Dong,&nbsp;Hongwei Bran Li,&nbsp;Yao Feng Chong,&nbsp;Fang Ji,&nbsp;Joanna Su Xian Chong,&nbsp;Nathanael Ren Jie Tang,&nbsp;Saima Hilal,&nbsp;Huazhu Fu,&nbsp;Christopher Li-Hsian Chen,&nbsp;Juan Helen Zhou,&nbsp;Alzheimer's Disease Neuroimaging Initiative","doi":"10.1002/hbm.70212","DOIUrl":"https://doi.org/10.1002/hbm.70212","url":null,"abstract":"<p>White matter hyperintensities (WMH) are neuroimaging markers linked to an elevated risk of cognitive decline. WMH severity is typically assessed via visual rating scales and through volumetric segmentation. While visual rating scales are commonly used in clinical practice, they offer limited descriptive power. In contrast, supervised volumetric segmentation requires manually annotated masks, which are labor-intensive and challenging to scale for large studies. Therefore, our goal was to develop an automated deep-learning model that can provide accurate and holistic quantification of WMH severity with minimal supervision. We developed WMH-DualTasker, a deep learning model that simultaneously performs voxel-wise segmentation and visual rating score prediction. The model employs self-supervised learning with transformation-invariant consistency constraints, using WMH visual ratings (ARWMC scale, range 0–30) from clinical settings as the sole supervisory signal. Additionally, we assessed its clinical utility by applying it to identify individuals with mild cognitive impairment (MCI) and to predict dementia conversion. The volumetric quantification performance of WMH-DualTasker was either superior to or on par with existing supervised methods, as demonstrated on the MICCAI-WMH dataset (<i>N</i> = 60, Dice = 0.602) and the SINGER dataset (<i>N</i> = 64, Dice = 0.608). Furthermore, the model exhibited strong agreement with clinical visual rating scales on an external dataset (SINGER, MAE = 1.880, <i>K</i> = 0.77). Importantly, WMH severity metrics derived from WMH-DualTasker improved predictive performance beyond conventional clinical features for MCI classification (AUC = 0.718, <i>p</i> &lt; 0.001) and MCI conversion prediction (AUC = 0.652, <i>p</i> &lt; 0.001) using the ADNI dataset. WMH-DualTasker substantially reduces the reliance on labor-intensive manual annotations, facilitating more efficient and scalable quantification of WMH severity in large-scale population studies. This innovative approach has the potential to advance preventive and precision medicine by enhancing the assessment and management of vascular cognitive impairment associated with WMH.</p>","PeriodicalId":13019,"journal":{"name":"Human Brain Mapping","volume":"46 6","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hbm.70212","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}