Harmonizing 1.5T/3T Diffusion Weighted MRI through Development of Deep Learning Stabilized Microarchitecture Estimators.
Harmonizing 1.5T/3T Diffusion Weighted MRI through Development of Deep Learning Stabilized Microarchitecture Estimators.
复制标题
通过开发深度学习稳定微架构估计器来协调 1.5T/3T 扩散加权 MRI。
DOI：
10.1117/12.2512902
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Ro
中科院分区：
文献类型：
--
作者：
Nath,Vishwesh;Remedios,Samuel;Parvathaneni,Prasanna;Hansen,ColinB;Bayrak,RozaG;Bermudez,Camilo;Blaber,JustinA;Schilling,KurtG;Janve,VaibhavA;Gao,Yurui;Huo,Yuankai;Lyu,Ilwoo;Williams,Owen;Resnick,Susan;Beason-Held,Lori;Ro
扩散加权磁共振成像（DW-MRI）被解释为一种对毫米级组织微结构敏感的定量方法。然而，敏化取决于采集序列（例如扩散时间、梯度强度等）并且容易受到成像伪影的影响。因此，跨场强（包括不同的扫描仪、硬件性能和序列设计考虑因素）定量 DW-MRI 生物标志物的比较是一个具有挑战性的研究领域。我们提出了一种使用 DW-MRI 估计微观结构的新方法，该方法对 1.5T 和 3T 成像之间的扫描仪差异具有鲁棒性。我们建议使用零空间深度网络 (NSDN) 架构将 DW-MRI 信号建模为纤维取向分布 (FOD) 来表示组织微观结构。 NSDN 方法与组织学观察到的微观结构（在先前获得的离体松鼠猴数据集上）和扫描-重新扫描数据一致。这项工作的贡献在于，我们结合了相同的双网络（IDN），通过扫描-重新扫描数据最大限度地减少扫描仪效应的影响。简而言之，我们的估计器是在两个数据集上进行训练的。首先，通过相应的 DW-MRI 和共聚焦组织学（512 个独立体素）获取三只松鼠猴的组织学数据集。其次，从巴尔的摩纵向衰老研究中确定了 37 名对照受试者（67-95 岁），他们曾在 1.5T 和 3T 扫描仪（b 值为 700 s/mm2，体素分辨率为 2.2mm，30-32 梯度体积）上进行扫描，平均间隔为 4 年（标准偏差 1.3 年）。图像配准后，我们使用 17 名受试者的配对白质 (WM) 体素和 440 个组织学体素进行训练，并使用 20 名受试者和 72 个组织学体素进行测试。我们将所提出的估计器与超分辨率约束球形反卷积（CSD）和先前提出的回归深度神经网络（DNN）进行比较。 NSDN 在角度相关系数 (ACC) 0.81 对 0.28 和 0.46、均方误差 (MSE) 0.001 对 0.003 和 0.03、一般分数各向异性 (GFA) 0.05 对 0.05 和 0.09 方面优于 CSD 和 DNN。需要使用同步成像进行进一步验证和评估，但 NSDN 是以一致且独立于设备的方式构建对微架构的理解的有前途的途径。
Diffusion weighted magnetic resonance imaging (DW-MRI) is interpreted as a quantitative method that is sensitive to tissue microarchitecture at a millimeter scale. However, the sensitization is dependent on acquisition sequences (e.g., diffusion time, gradient strength, etc.) and susceptible to imaging artifacts. Hence, comparison of quantitative DW-MRI biomarkers across field strengths (including different scanners, hardware performance, and sequence design considerations) is a challenging area of research. We propose a novel method to estimate microstructure using DW-MRI that is robust to scanner difference between 1.5T and 3T imaging. We propose to use a null space deep network (NSDN) architecture to model DW-MRI signal as fiber orientation distributions (FOD) to represent tissue microstructure. The NSDN approach is consistent with histologically observed microstructure (on previously acquired ex vivo squirrel monkey dataset) and scan-rescan data. The contribution of this work is that we incorporate identical dual networks (IDN) to minimize the influence of scanner effects via scan-rescan data. Briefly, our estimator is trained on two datasets. First, a histology dataset was acquired on three squirrel monkeys with corresponding DW-MRI and confocal histology (512 independent voxels). Second, 37 control subjects from the Baltimore Longitudinal Study of Aging (67-95 y/o) were identified who had been scanned at 1.5T and 3T scanners (b-value of 700 s/mm2, voxel resolution at 2.2mm, 30-32 gradient volumes) with an average interval of 4 years (standard deviation 1.3 years). After image registration, we used paired white matter (WM) voxels for 17 subjects and 440 histology voxels for training and 20 subjects and 72 histology voxels for testing. We compare the proposed estimator with super-resolved constrained spherical deconvolution (CSD) and a previously presented regression deep neural network (DNN). NSDN outperformed CSD and DNN in angular correlation coefficient (ACC) 0.81 versus 0.28 and 0.46, mean squared error (MSE) 0.001 versus 0.003 and 0.03, and general fractional anisotropy (GFA) 0.05 versus 0.05 and 0.09. Further validation and evaluation with contemporaneous imaging are necessary, but the NSDN is promising avenue for building understanding of microarchitecture in a consistent and device-independent manner.