.png){kind=icon}
返回
DDTracking: A Diffusion Model-Based Deep Generative Framework with Local-Global Spatiotemporal Modeling for Diffusion MRI Tractography
.png){kind=icon}
PRE
AI
DOI：10.1016/j.media.2026.103967.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• Reformulates dMRI tractography as a conditional denoising diffusion process, the first application of diffusion models for fiber tracking. • A conditional diffusion model module fuses local spatial and global temporal features for fine-scale, long-range generative orientation prediction. • Outperforms model-based and deep learning baselines in accuracy and computational efficiency on synthetic and in vivo datasets. • Exhibits strong generalizability across diverse scanners, protocols, age groups, and clinical conditions.
期刊
IF:
11.8
论文数:
3.8K
被引数:
2.4W
机构
引用论文
Recognition of white matter bundles using local and global streamline-based registration and clustering.png)
NeuroImage
OAAI
NeuroImageIF0
OAAI分享收藏Anatomical accuracy of brain connections derived from diffusion MRI tractography is inherently limited从扩散MRI追踪成像得出的大脑连接的解剖学准确性固有地受到限制OAAI
OAAI分享收藏Quantitative mapping of the brain’s structural connectivity using diffusion MRI tractography: A reviewNeuroImageOAAI
NeuroImageIF0
OAAI分享收藏Multi-tissue constrained spherical deconvolution for improved analysis of multi-shell diffusion MRI data多组织约束球面反卷积改进多壳扩散MRI数据分析NeuroImage
NeuroImageIF0
PREAI
分享收藏
查看更多内容