NeuroImage最新文献

{"title":"From neural activity to behavioral engagement: temporal dynamics as their “common currency” during music","authors":"Noah Chuipka ,&nbsp;Tom Smy ,&nbsp;Georg Northoff","doi":"10.1016/j.neuroimage.2025.121209","DOIUrl":"10.1016/j.neuroimage.2025.121209","url":null,"abstract":"<div><div>The human cortex is highly dynamic as manifest in its vast ongoing temporal repertoire. Similarly, human behavior is also variable over time with, for instance, fluctuating response times. How the brain's ongoing dynamics relates to the fluctuating dynamics of behavior such as emotions remains yet unclear, though. We measure median frequency (MF) in a dynamic way (D-MF) to investigate the dynamics in both electroencephalography (EEG) neural activity and the subjects’ continuous behavioral assessment of their perceived emotional engagement changes during five different music pieces. Our main findings are: (i) significant differences in the frequency dynamics, e.g., D-MF, of the subjects’ behavioral engagement ratings between the five music pieces, (ii) significant differences in the, e.g., D-MF, of the music pieces’ EEG-based neural activity, and (iii) there is a unidirectional relationship from neural to behavioral during the five music pieces as measured through correlation and Granger causality between their respective D-MF's. Together, we demonstrate that neural dynamics relates to behavioral dynamics through the shared fluctuations in their dynamics. This highlights the key role of dynamics in connecting neural and behavioral activity as their “common currency.”</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"312 ","pages":"Article 121209"},"PeriodicalIF":4.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantifying axonal features of human superficial white matter from three-dimensional multibeam serial electron microscopy data assisted by deep learning","authors":"Qiyuan Tian ,&nbsp;Chanon Ngamsombat ,&nbsp;Hong-Hsi Lee ,&nbsp;Daniel R. Berger ,&nbsp;Yuelong Wu ,&nbsp;Qiuyun Fan ,&nbsp;Berkin Bilgic ,&nbsp;Ziyu Li ,&nbsp;Dmitry S. Novikov ,&nbsp;Els Fieremans ,&nbsp;Bruce R. Rosen ,&nbsp;Jeff W. Lichtman ,&nbsp;Susie Y. Huang","doi":"10.1016/j.neuroimage.2025.121212","DOIUrl":"10.1016/j.neuroimage.2025.121212","url":null,"abstract":"<div><div>Short-range association fibers located in the superficial white matter play an important role in mediating higher-order cognitive function in humans. Detailed morphological characterization of short-range association fibers at the microscopic level promises to yield important insights into the axonal features driving cortico-cortical connectivity in the human brain yet has been difficult to achieve to date due to the challenges of imaging at nanometer-scale resolution over large tissue volumes. This work presents results from multi-beam scanning electron microscopy (EM) data acquired at 4 × 4 × 33 nm³ resolution in a volume of human superficial white matter measuring 200 × 200 × 112 μm³, leveraging automated analysis methods. Myelin and myelinated axons were automatically segmented using deep convolutional neural networks (CNNs), assisted by transfer learning and dropout regularization techniques. A total of 128,285 myelinated axons were segmented, of which 70,321 and 2102 were longer than 10 and 100 μm, respectively. Marked local variations in diameter (i.e., beading) and direction (i.e., undulation) were observed along the length of individual axons. Myelinated axons longer than 10 μm had inner diameters around 0.5 µm, outer diameters around 1 µm, and g-ratios around 0.5. This work fills a gap in knowledge of axonal morphometry in the superficial white matter and provides a large 3D human EM dataset and accurate segmentation results for a variety of future studies in different fields.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"313 ","pages":"Article 121212"},"PeriodicalIF":4.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-Frequency repetitive transcranial magnetic stimulation enhances white matter integrity in a rat model of ischemic stroke: A diffusion tensor imaging study using tract-based spatial statistics","authors":"Jiemei Chen ,&nbsp;Chao Li ,&nbsp;Jiena Hong ,&nbsp;Fei Zhao ,&nbsp;Jiantao Zhang ,&nbsp;Man Yang ,&nbsp;Shengxiang Liang ,&nbsp;Hongmei Wen","doi":"10.1016/j.neuroimage.2025.121204","DOIUrl":"10.1016/j.neuroimage.2025.121204","url":null,"abstract":"<div><div>Ischemic stroke leads to white matter damage and neurological deficits. Previous studies have revealed that high-frequency repetitive transcranial magnetic stimulation (HF-rTMS) has beneficial effects on white matter reorganization and neurological recovery after stroke. However, the characteristics of poststroke white matter repair after treatment with HF-rTMS remain unclear. Therefore, this study used diffusion tensor imaging (DTI) to investigate the impact of HF-rTMS on white matter integrity following middle cerebral artery occlusion (MCAO) in a rat model. The modified neurological severity score (mNSS) and T2-weighted imaging data were used to assess neurological function and infarct size. We used a tract-based spatial statistics (TBSS) approach to analyze changes in fractional anisotropy (FA) across various white matter tracts. Furthermore, we performed Luxol fast blue (LFB) staining and transmission electron microscopy (TEM) to detect white matter and myelin damage. The results revealed that compared with the tMCAO group, the tMCAO+rTMS group presented a significant decrease in infarct size and the mNSS, as well as significantly greater FA values, mostly in the left external capsule, left internal capsule, left optic tract, left deep cerebral white matter, left stria terminalis and right external capsule. The LFB staining and electron microscopy results are consistent with the DTI results. These findings suggest that HF-rTMS contributes to the recovery of white matter integrity and neurological function. This study underscores the importance of HF-rTMS as a noninvasive intervention for enhancing poststroke neurological recovery by improving white matter integrity.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"311 ","pages":"Article 121204"},"PeriodicalIF":4.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IT: An interpretable transformer model for Alzheimer's disease prediction based on PET/MR images","authors":"Zhaomin Yao ,&nbsp;Weiming Xie ,&nbsp;Jiaming Chen ,&nbsp;Ying Zhan ,&nbsp;Xiaodan Wu ,&nbsp;Yingxin Dai ,&nbsp;Yusong Pei ,&nbsp;Zhiguo Wang ,&nbsp;Guoxu Zhang","doi":"10.1016/j.neuroimage.2025.121210","DOIUrl":"10.1016/j.neuroimage.2025.121210","url":null,"abstract":"<div><div>Alzheimer's disease (AD) represents a significant challenge due to its progressive neurodegenerative impact, particularly within an aging global demographic. This underscores the critical need for developing sophisticated diagnostic tools for its early detection and precise monitoring. Within this realm, PET/MR imaging stands out as a potent dual-modality approach that transforms sensor data into detailed perceptual mappings, thereby enriching our grasp of brain pathophysiology. To capitalize on the strengths of PET/MR imaging in diagnosing AD, we have introduced a novel deep learning framework named \"IT\", which is inspired by the Transformer architecture. This innovative model adeptly captures both local and global characteristics within the imaging data, refining these features through advanced feature engineering techniques to achieve a synergistic integration. The efficiency of our model is underscored by robust experimental validation, wherein it delivers superior performance on a host of evaluative benchmarks, all while maintaining low demands on computational resources. Furthermore, the features we extracted resonate with established medical theories regarding feature distribution and usage efficiency, enhancing the clinical relevance of our findings. These insights significantly bolster the arsenal of tools available for AD diagnostics and contribute to the broader narrative of deciphering brain functionality through state-of-the-art imaging modalities.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"311 ","pages":"Article 121210"},"PeriodicalIF":4.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Blending into naturalistic scenes: Cortical regions serving visual search are more strongly activated in congruent contexts","authors":"Ilenia Salsano ,&nbsp;Nathan M. Petro ,&nbsp;Giorgia Picci ,&nbsp;Aubrie J. Petts ,&nbsp;Ryan J. Glesinger ,&nbsp;Lucy K. Horne ,&nbsp;Anna T. Coutant ,&nbsp;Grace C. Ende ,&nbsp;Jason A. John ,&nbsp;Danielle L. Rice ,&nbsp;Grant M. Garrison ,&nbsp;Kennedy A. Kress ,&nbsp;Valerio Santangelo ,&nbsp;Moreno I. Coco ,&nbsp;Tony W. Wilson","doi":"10.1016/j.neuroimage.2025.121214","DOIUrl":"10.1016/j.neuroimage.2025.121214","url":null,"abstract":"<div><div>Visual attention allows us to navigate complex environments by selecting behaviorally relevant stimuli while suppressing distractors, through a dynamic balance between top-down and bottom-up mechanisms. Extensive attention research has examined the object-context relationship. Some studies have shown that incongruent object-context associations are processed faster, likely due to semantic mismatch-related attentional capture, while others have suggested that schema-driven facilitation may enhance object recognition when the object and context are congruent. Beyond the conflicting findings, translation of this work to real world contexts has been difficult due to the use of non-ecological scenes and stimuli when investigating the object-context congruency relationship. To address this, we employed a goal-directed visual search task and naturalistic indoor scenes during functional MRI (fMRI). Seventy-one healthy adults searched for a target object, either congruent or incongruent within the scene context, following a word cue. We collected accuracy and response time behavioral data, and all fMRI data were processed following standard pipelines, with statistical maps thresholded at <em>p</em> &lt; .05 following multiple comparisons correction. Our results indicated faster response times for incongruent relative to congruent trials, likely reflecting the so-called pop-out effect of schema violations in the incongruent condition. Our neural results indicated that congruent elicited greater activation than incongruent trials in the dorsal frontoparietal attention network and the precuneus, likely reflecting sustained top-down attentional control to locate the targets that blend more seamlessly into the context. These findings highlight the flexible interplay between top-down and bottom-up mechanisms in real-world visual search, emphasizing the dominance of schema-guided top-down processes in congruent contexts and rapid attention capture in incongruent contexts.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"311 ","pages":"Article 121214"},"PeriodicalIF":4.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NaDyNet: A toolbox for dynamic network analysis of naturalistic stimuli","authors":"Junjie Yang ,&nbsp;Zhe Hu ,&nbsp;Junjing Li ,&nbsp;Xiaolin Guo ,&nbsp;Xiaowei Gao ,&nbsp;Jiaxuan Liu ,&nbsp;Yaling Wang ,&nbsp;Zhiheng Qu ,&nbsp;Wanchun Li ,&nbsp;Zhongqi Li ,&nbsp;Wanjing Li ,&nbsp;Yien Huang ,&nbsp;Jiali Chen ,&nbsp;Hao Wen ,&nbsp;Binke Yuan","doi":"10.1016/j.neuroimage.2025.121203","DOIUrl":"10.1016/j.neuroimage.2025.121203","url":null,"abstract":"<div><div>Experiments with naturalistic stimuli (e.g., listening to stories or watching movies) are emerging paradigms in brain function research. The content of naturalistic stimuli is rich and continuous. The fMRI signals of naturalistic stimuli are complex and include different components. A major challenge is isolate the stimuli-induced signals while simultaneously tracking the brain's responses to these stimuli in real-time. To this end, we have developed a user-friendly graphical interface toolbox called NaDyNet (Naturalistic Dynamic Network Toolbox), which integrates existing dynamic brain network analysis methods and their improved versions. The main features of NaDyNet are: 1) extracting signals of interest from naturalistic fMRI signals; 2) incorporating six commonly used dynamic analysis methods and three static analysis methods; 3) improved versions of these dynamic methods by adopting inter-subject analysis to eliminate the effects of non-interest signals; 4) performing K-means clustering analysis to identify temporally reoccurring states along with their temporal and spatial attributes; 5) Visualization of spatiotemporal results. We then introduced the rationale for incorporating inter-subject analysis to improve existing dynamic brain network analysis methods and presented examples by analyzing naturalistic fMRI data. We hope that this toolbox will promote the development of naturalistic neuroscience. The toolbox is available at <span><span>https://github.com/yuanbinke/Naturalistic-Dynamic-Network-Toolbox</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"311 ","pages":"Article 121203"},"PeriodicalIF":4.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electroencephalography estimates brain age in infants with high precision: Leveraging advanced machine learning in healthcare","authors":"Saeideh Davoudi ,&nbsp;Gabriela Lopez Arango ,&nbsp;Florence Deguire ,&nbsp;Inga Sophie Knoth ,&nbsp;Fanny Thebault-Dagher ,&nbsp;Rebecca Reh ,&nbsp;Laurel Trainor ,&nbsp;Janet Werker ,&nbsp;Sarah Lippé","doi":"10.1016/j.neuroimage.2025.121200","DOIUrl":"10.1016/j.neuroimage.2025.121200","url":null,"abstract":"<div><div>Changes in the pace of neurodevelopment are key indicators of atypical maturation during early life. Unfortunately, reliable prognostic tools rely on assessments of cognitive and behavioral skills that develop towards the second year of life and after. Early assessment of brain maturation using electroencephalography (EEG) is crucial for clinical intervention and care planning. We developed a reliable methodology using conventional machine learning (ML) and novel deep learning (DL) networks to efficiently quantify the difference between chronological and biological age, so-called brain age gap (BAG) as a marker of accelerated/decelerated biological brain development. In this cross-sectional study, EEG from 219 typically-developing infants aged from three to 14-months was used. For DL networks, the input samples were increased to 2628 recordings. We further validated the BAG tool in a population at clinical risk with abnormal brain growth (macrocephaly) to capture deviation from normal aging. Our results indicate that DL networks outperform conventional ML models, capturing complex non-monotonic EEG characteristics and predicting the biological age with a mean absolute error of only one month (MAE = 1 month, 95 %CI:0.88–1.15, r = 0.82, 95 %CI:0.78–0.85). Additionally, the developing brain follows a trajectory characterized by increased non-linearity and complexity in which alpha rhythm plays an important role. BAG could detect group-level maturational delays between typically-developing and macrocephaly <span><math><mrow><mo>(</mo><mrow><mi>p</mi><mi>v</mi><mi>a</mi><mi>l</mi><mi>u</mi><mi>e</mi><mo>=</mo><mn>0.009</mn></mrow><mo>)</mo></mrow></math></span>. In macrocephaly, BAG negatively correlated with the general adaptive composite of the ABAS-II (<span><math><mrow><mi>p</mi><mi>v</mi><mi>a</mi><mi>l</mi><mi>u</mi><mi>e</mi><mo>=</mo><mn>0.04</mn></mrow></math></span>) at 18-months and the information processing speed scale of the WPSSI-IV at age four (<span><math><mrow><mi>p</mi><mi>v</mi><mi>a</mi><mi>l</mi><mi>u</mi><mi>e</mi><mo>=</mo><mn>0.006</mn></mrow></math></span>). The EEG-based BAG score offers a reliable non-invasive measure of brain maturation, with significant advantages and implications for developmental neuroscience and clinical practice.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"312 ","pages":"Article 121200"},"PeriodicalIF":4.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143833142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Brain-based gene expression and corresponding behavioural relevance of risk genes for broad antisocial behaviour","authors":"Jaroslav Rokicki ,&nbsp;Megan L. Campbell ,&nbsp;Dennis van der Meer ,&nbsp;Alina I. Sartorius ,&nbsp;Natalia Tesli ,&nbsp;Piotr Jahołkowski ,&nbsp;Alexey Shadrin ,&nbsp;Ole Andreassen ,&nbsp;Lars T. Westlye ,&nbsp;Daniel S. Quintana ,&nbsp;Unn K. Haukvik","doi":"10.1016/j.neuroimage.2025.121198","DOIUrl":"10.1016/j.neuroimage.2025.121198","url":null,"abstract":"<div><div>Antisocial behaviour (ASB) involves persistent irresponsible, delinquent activities violating rights and safety of others. A meta-analysis of genome-wide association studies revealed significant genetic associations with ASB, yet their brain expression patterns and behavioural relevance remain unclear. Our investigation of fifteen genes associated with ASB examined their biological role and distribution across tissues, integrating post-mortem brain sample data from the Allen-Human-Brain Atlas and the Genotype-Tissue Expression project. We found that these genes were differentially expressed in the brain, particularly in regions like the cerebellum, putamen, and caudate, and were notably downregulated in the pancreas. Single cell type expression analysis revealed that ASB-associated genes had strong correlations with ductal and endothelial cells in the pancreas, indicating a possible metabolic influence on ASB. Certain genes like <em>NTN1, SMAD5, NCAM2</em>, and <em>CDC42EP3</em> displayed specificity for cognitive terms including chronic pain, heart rate, and aphasia. These expression patterns aligned with neurocognitive domains related to thinking, and learning, distress, motor skills, as determined by fMRI analysis. This study connects specific brain gene expression with potential genetic and metabolic factors in ASB, offering novel insights into its biological basis and possible interdisciplinary approaches to understanding and addressing aggressive behaviours.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"311 ","pages":"Article 121198"},"PeriodicalIF":4.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterizing the distribution of neural and non-neural components in multi-echo EPI data across echo times based on tensor-ICA","authors":"Tengfei Feng ,&nbsp;Halim Ibrahim Baqapuri ,&nbsp;Jana Zweerings ,&nbsp;Huanjie Li ,&nbsp;Fengyu Cong ,&nbsp;Klaus Mathiak","doi":"10.1016/j.neuroimage.2025.121199","DOIUrl":"10.1016/j.neuroimage.2025.121199","url":null,"abstract":"<div><div>Multi-echo echo-planar imaging (ME-EPI) acquires images at multiple echo times (TEs), enabling the differentiation of BOLD and non-BOLD fluctuations through TE-dependent analysis of transverse relaxation time and initial intensity. Decomposing ME-EPI in tensor space is a promising approach to characterize the distribution of changes across TEs (TE patterns) directly and aid the classification of components by providing information from an additional domain. In this study, the tensorial extension of independent component analysis (tensor-ICA) is used to characterize the TE patterns of neural and non-neural components in ME-EPI data. With the constraints of independent spatial maps, an ME-EPI dataset was decomposed into spatial, temporal, and TE domains to understand the TE patterns of noise or signal-related independent components. Our analysis revealed three distinct groups of components based on their TE patterns. Motion-related and other non-BOLD origin components followed decreased TE patterns. While the long-TE-peak components showed a large overlay on grey matter and signal patterns, the components that peaked at short TEs reflected noise that may be related to the vascular system, respiration, or cardiac pulsation, amongst others. Accordingly, removing short-TE peak components as part of a denoising strategy significantly improved quality control metrics and revealed clearer, more interpretable activation patterns compared to non-denoised data. To our knowledge, this work is the first application of decomposing ME-EPI in a tensor way. Our findings demonstrate that tensor-ICA is efficient in decomposing ME-EPI and characterizing the neural and non-neural TE patterns aiding in classifying components which is important for denoising fMRI data.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"311 ","pages":"Article 121199"},"PeriodicalIF":4.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FetDTIAlign: A deep learning framework for affine and deformable registration of fetal brain dMRI","authors":"Bo Li,&nbsp;Qi Zeng,&nbsp;Simon K. Warfield,&nbsp;Davood Karimi","doi":"10.1016/j.neuroimage.2025.121190","DOIUrl":"10.1016/j.neuroimage.2025.121190","url":null,"abstract":"<div><div>Diffusion MRI (dMRI) offers unique insights into the microstructure of fetal brain tissue in utero. Longitudinal and cross-sectional studies of fetal dMRI have the potential to reveal subtle but crucial changes associated with normal and abnormal neurodevelopment. However, these studies depend on precise spatial alignment of data across scans and subjects, which is particularly challenging in fetal imaging due to the low data quality, rapid brain development, and limited anatomical landmarks for accurate registration. Existing registration methods, primarily developed for superior-quality adult data, are not well-suited for addressing these complexities. To bridge this gap, we introduce FetDTIAlign, a deep learning approach tailored to fetal brain dMRI, enabling accurate affine and deformable registration. FetDTIAlign integrates a novel dual-encoder architecture and iterative feature-based inference, effectively minimizing the impact of noise and low resolution to achieve accurate alignment. Additionally, it strategically employs different network configurations and domain-specific image features at each registration stage, addressing the unique challenges of affine and deformable registration, enhancing both robustness and accuracy. We validated FetDTIAlign on a dataset covering gestational ages centered between 23 and 36 weeks, encompassing 60 white matter tracts. For all age groups, FetDTIAlign consistently showed superior anatomical correspondence and the best visual alignment in both affine and deformable registration, outperforming two classical optimization-based methods and a deep learning-based pipeline. Further validation on external data from the Developing Human Connectome Project demonstrated the generalizability of our method to data collected with different acquisition protocols. Our results show the feasibility of using deep learning for fetal brain dMRI registration, providing a more accurate and reliable alternative to classical techniques. By enabling precise cross-subject and tract-specific analyses, FetDTIAlign paves the way for new discoveries in early brain development. The code is available at <span><span>https://gitlab.com/blibli/fetdtialign</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"311 ","pages":"Article 121190"},"PeriodicalIF":4.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}