DTI引导的体素球谐函数回归用于单壳层到多壳层dMRI合成
DTI-Guided Volumetric Spherical Harmonics Regression for Single-to-Multi-Shell dMRI Synthesis
浏览论文内容
中文总结 AI 辅助
提出DTI-SHNet框架，利用DTI参数图引导3D U-Net在球谐系数域进行体素回归，实现单壳层到多壳层dMRI合成，并通过信号一致性正则化提升保真度，在UK Biobank和Cam-CAN数据上验证了优越性能。
中文摘要 AI 辅助
多壳层扩散磁共振成像（dMRI）比单壳层扫描能够实现更具表现力的微结构建模，但其较长的采集时间阻碍了在大规模队列和时间受限的临床环境中的部署。从单壳层输入合成未观测的壳层本质上是病态问题，并且由于协议不匹配（源和目标梯度方向集可能不对齐）而进一步复杂化。我们提出了DTI-SHNet，一种单壳层到多壳层合成框架，它在实对称球谐函数（SH）系数域中操作，并执行空间感知的体素回归。给定一个源壳层，我们估计扩散张量成像（DTI），并使用方向无关的参数图以及脑掩膜作为条件先验，引导3D U-Net回归器从源壳层到目标壳层的SH系数。为了将系数精度与信号保真度耦合，我们引入了一种信号一致性正则化，该正则化从预测系数在随机采样的规范方向上重建信号，并在信号域中强制一致性。在UK Biobank和Cam-CAN数据上进行的b=1000到b=2000 dMRI合成实验表明，DTI-SHNet与先进方法相比实现了具有竞争力的视觉质量，同时更好地保留了下游扩散测量指标。我们的代码可在以下网址获取：https://this https URL。
英文摘要
Multi-shell diffusion MRI (dMRI) unlocks more expressive microstructural modeling than single-shell scans, yet its longer acquisition time hinders deployment in large-scale cohorts and time-constrained clinical settings. Synthesizing an unobserved shell from a single-shell input is fundamentally ill-posed and further complicated by protocol mismatch, where source and target gradient direction sets may not align. We propose DTI-SHNet, a single-to-multi-shell synthesis framework that operates in the real symmetric spherical harmonics (SH) coefficient domain and performs spatially aware volumetric regression. Given a source shell, we estimate diffusion tensor imaging (DTI) and use direction-agnostic parametric maps along with a brain mask as conditioning priors to guide a 3D U-Net regressor from source-shell to target-shell SH coefficients. To couple coefficient accuracy with signal fidelity, we introduce a signal consistency regularization that reconstructs signals on randomly sampled canonical directions from predicted coefficients and enforces agreement in the signal domain. Experiments on UK Biobank and Cam-CAN data for b=1000 to b=2000 dMRI synthesis show that DTI-SHNet achieves competitive visual quality compared to advanced methods, while better preserving downstream diffusion measures. Our code is available at https://github.com/xiaovhua/dti-shnet.
发表机构
- Juntendo University（顺天堂大学）
- RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能研究中心）
- Tokyo University of Agriculture and Technology（东京农工大学）
机构由 AI 辅助整理，请以论文原文为准。
