Cross-Population White Matter Atlas Creation for Concurrent Mapping of Brain Connections in Neonates and Adults with Diffusion MRI Tractography

• URL: http://arxiv.org/abs/2512.20370v1
• Date: Tue, 23 Dec 2025 13:54:11 GMT
• Title: Cross-Population White Matter Atlas Creation for Concurrent Mapping of Brain Connections in Neonates and Adults with Diffusion MRI Tractography
• Abstract summary: White matter (WM) connections between adults and neonates can be compared using diffusion MRI (dMRI)<n>Existing WM atlases are population-specific (adult or neonatal) and reside in separate spaces, preventing cross-population comparisons.<n>We propose a neonatal/adult brain atlas (NABA), a WM tractography atlas built from dMRI data of both neonates and adults.
• Score: 8.011530916936389
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Comparing white matter (WM) connections between adults and neonates using diffusion MRI (dMRI) can advance our understanding of typical brain development and potential biomarkers for neurological disorders. However, existing WM atlases are population-specific (adult or neonatal) and reside in separate spaces, preventing direct cross-population comparisons. A unified WM atlas spanning both neonates and adults is still lacking. In this study, we propose a neonatal/adult brain atlas (NABA), a WM tractography atlas built from dMRI data of both neonates and adults. NABA is constructed using a robust, data-driven fiber clustering pipeline, enabling group-wise WM atlasing across populations despite substantial anatomical variability. The atlas provides a standardized template for WM parcellation, allowing direct comparison of WM tracts between neonates and adults. Using NABA, we conduct four analyses: (1) evaluating the feasibility of joint WM mapping across populations, (2) characterizing WM development across neonatal ages relative to adults, (3) assessing sex-related differences in neonatal WM development, and (4) examining the effects of preterm birth. Our results show that NABA robustly identifies WM tracts in both populations. We observe rapid fractional anisotropy (FA) development in long-range association tracts, including the arcuate fasciculus and superior longitudinal fasciculus II, whereas intra-cerebellar tracts develop more slowly. Neonatal females exhibit faster overall FA development than males. Although preterm neonates show lower overall FA development rates, they demonstrate relatively higher FA growth in specific tracts, including the corticospinal tract, corona radiata-pontine pathway, and intracerebellar tracts. These findings demonstrate that NABA is a useful tool for investigating WM development across neonates and adults.

Related papers

• NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis [51.033331232872094]
  Neonatal respiratory diseases are a major cause of neonatal morbidity and mortality.<n>Existing Multimodal Large Language Models (MLLMs) face two key limitations in neonatal diagnosis.<n>We propose NeoRed, to the best of our knowledge, the first MLLM tailored for neonatal respiratory disease.
  arXiv  Detail & Related papers  (2026-09-03T08:24:38Z)
• Deep learning-based neurodevelopmental assessment in preterm infants [17.951227721383884]
  We propose a novel segmentation neural network, named Hierarchical Dense Attention Network.<n>Our architecture incorporates a 3D spatial-channel attention mechanism combined with an attention-guided dense upsampling strategy to enhance feature discrimination in low-contrast volumetric data.<n>Experiments demonstrate that our method achieves superior segmentation performance compared to state-of-the-art baselines, effectively tackling the challenge of isointense tissue differentiation.
  arXiv  Detail & Related papers  (2026-01-17T07:42:13Z)
• Age Sensitive Hippocampal Functional Connectivity: New Insights from 3D CNNs and Saliency Mapping [55.27843586881593]
  We develop an interpretable deep learning framework to predict brain age from hippocampal functional connectivity analysis.<n>Key hippocampal-cortical connections are mapped, particularly with the precuneus, cuneus, posterior cingulate cortex, parahippocampal cortex, left superior parietal lobule, and right superior temporal sulcus.<n>Findings provide new insights into the functional mechanisms of hippocampal aging and demonstrate the power of explainable deep learning to uncover biologically meaningful patterns in neuroimaging data.
  arXiv  Detail & Related papers  (2025-07-02T07:05:18Z)
• Explainable Brain Age Gap Prediction in Neurodegenerative Conditions using coVariance Neural Networks [94.06526659234756]
  Black-box machine learning approaches to brain age gap prediction have limited practical utility.<n>We apply the VNN-based approach to study brain age gap using cortical thickness features for various prevalent neurodegenerative conditions.<n>Our results reveal distinct anatomic patterns for brain age gap in Alzheimer's disease, frontotemporal dementia, and atypical Parkinsonian disorders.
  arXiv  Detail & Related papers  (2025-01-02T19:37:09Z)
• LoCI-DiffCom: Longitudinal Consistency-Informed Diffusion Model for 3D Infant Brain Image Completion [45.361733575664886]
  We propose LoCI-DiffCom, a novel Longitudinal Consistency-Informed Diffusion model for infant brain image Completion. Our approach can extract individualized developmental features while ensuring context-aware consistency.
  arXiv  Detail & Related papers  (2024-05-17T10:53:40Z)
• Cas-DiffCom: Cascaded diffusion model for infant longitudinal super-resolution 3D medical image completion [47.83003164569194]
  We propose a two-stage cascaded diffusion model, Cas-DiffCom, for dense and longitudinal 3D infant brain MRI completion and super-resolution. Experiment results validate that Cas-DiffCom achieves both individual consistency and high fidelity in longitudinal infant brain image completion.
  arXiv  Detail & Related papers  (2024-02-21T12:54:40Z)
• Age Prediction Performance Varies Across Deep, Superficial, and Cerebellar White Matter Connections [5.748406277713642]
  We propose a deep-learning-based age prediction model that leverages large convolutional kernels and inverted bottlenecks. Experimental results demonstrate that the proposed model achieves a mean absolute error of 2.59 years. Overall, the most predictive WM tracts are the thalamo-frontal tract from the deep WM and the intracerebellar input and Purkinje tract from the cerebellar WM.
  arXiv  Detail & Related papers  (2022-11-11T15:23:09Z)
• Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions [68.41088365582831]
  White matter parcellation classifies tractography streamlines into clusters or anatomically meaningful tracts. Most parcellation methods focus on the deep white matter (DWM), whereas fewer methods address the superficial white matter (SWM) due to its complexity. We propose a novel two-stage deep-learning-based framework, Superficial White Matter Analysis (SupWMA), that performs an efficient parcellation of 198 SWM clusters from whole-brain tractography.
  arXiv  Detail & Related papers  (2022-07-18T23:07:53Z)
• An automatic pipeline for atlas-based fetal and neonatal brain segmentation and analysis [1.3198175418055964]
  We report the creation of two new fetal atlases, and their use within the pipeline for atlas-based segmentation. The pipeline is also able to extract cortical and pial surfaces and compute features, such as curvature, thickness, sulcal depth, and local gyrification index.
  arXiv  Detail & Related papers  (2022-05-16T11:15:26Z)
• Building Brains: Subvolume Recombination for Data Augmentation in Large Vessel Occlusion Detection [56.67577446132946]
  A large training data set is required for a standard deep learning-based model to learn this strategy from data. We propose an augmentation method that generates artificial training samples by recombining vessel tree segmentations of the hemispheres from different patients. In line with the augmentation scheme, we use a 3D-DenseNet fed with task-specific input, fostering a side-by-side comparison between the hemispheres.
  arXiv  Detail & Related papers  (2022-05-05T10:31:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.