Single-shell NODDI using dictionary-learner-estimated isotropic volume fraction
Single-shell NODDI using dictionary-learner-estimated isotropic volume fraction
复制标题
DOI：
10.1002/nbm.4628
复制
发表时间：
2021-10-12
影响因子：
2.9
通讯作者：
Uddin, Md Nasir
中科院分区：
文献类型：
--
作者：
Faiyaz, Abrar;Doyley, Marvin;Uddin, Md Nasir
神经突取向弥散和密度成像（NODDI）能够从多壳层扩散MRI数据评估细胞内、细胞外和游离水信号。这是一个有见地的方法来表征脑组织的微观结构。NODDI参数的单壳重建在以前的研究中由于拟合失败而受到阻碍，特别是对于神经突密度指数（NDI）。在这里，我们研究了使用各向同性体积分数（f（ISO））作为先验，使用单壳层数据创建鲁棒NODDI参数图的可能性。先验估计独立的NODDI模型约束，使用字典学习方法。首先，我们使用随机稀疏基于字典的网络（DictNet），该网络使用从体内和模拟扩散MRI数据中获得的数据进行训练，以预测f（ISO）。在单壳情况下，将平均扩散率和无扩散加权（S-0）的原始T-2信号纳入f（ISO）估计的词典中。然后，使用NODDI框架与已知的f（ISO）来估计NDI和取向分散指数（ODI）。在模拟中，使用我们的模型估计的f（ISO）与其他f（ISO）估计进行了比较。此外，使用合成数据模拟和在3 T扫描仪上收集的人体数据（高质量HCP和临床数据集），我们比较了基于字典的学习先验NODDI（DLpN）与原始NODDI在单壳和多壳数据中的性能。我们的研究结果表明，单壳层方案的DLpN衍生NDI和ODI参数与原始多壳层NODDI相当，B = 2000 s/mm（2）的方案表现最好（白色和灰质中的误差类似于5%）。这可能允许NODDI通过DictNet f（ISO）训练对两个受试者进行多壳扫描来评估单壳数据的研究。
Neurite orientation dispersion and density imaging (NODDI) enables the assessment of intracellular, extracellular, and free water signals from multi-shell diffusion MRI data. It is an insightful approach to characterize brain tissue microstructure. Single-shell reconstruction for NODDI parameters has been discouraged in previous studies caused by failure when fitting, especially for the neurite density index (NDI). Here, we investigated the possibility of creating robust NODDI parameter maps with single-shell data, using the isotropic volume fraction (f(ISO)) as a prior. Prior estimation was made independent of the NODDI model constraint using a dictionary learning approach. First, we used a stochastic sparse dictionary-based network (DictNet), which is trained with data obtained from in vivo and simulated diffusion MRI data, to predict f(ISO). In single-shell cases, the mean diffusivity and raw T-2 signal with no diffusion weighting (S-0) was incorporated in the dictionary for the f(ISO) estimation. Then, the NODDI framework was used with the known f(ISO) to estimate the NDI and orientation dispersion index (ODI). The f(ISO) estimated using our model was compared with other f(ISO) estimators in the simulation. Further, using both synthetic data simulation and human data collected on a 3 T scanner (both high-quality HCP and clinical dataset), we compared the performance of our dictionary-based learning prior NODDI (DLpN) with the original NODDI for both single-shell and multi-shell data. Our results suggest that DLpN-derived NDI and ODI parameters for single-shell protocols are comparable with original multi-shell NODDI, and the protocol with b = 2000 s/mm(2) performs the best (error similar to 5% in white and gray matter). This may allow NODDI evaluation of studies on single-shell data by multi-shell scanning of two subjects for DictNet f(ISO) training.