School of Electrical Engineering, Faculty of Engineering, Tel Aviv University, Tel Aviv, Israel.
Department of Anatomy and Anthropology, Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
J Magn Reson Imaging. 2021 Oct;54(4):1066-1076. doi: 10.1002/jmri.27654. Epub 2021 Apr 24.
Current registration methods for diffusion-MRI (dMRI) data mostly focus on white matter (WM) areas. Recently, dMRI has been employed for the characterization of gray matter (GM) microstructure, emphasizing the need for registration methods that consider all tissue types.
To develop a dMRI registration method based on GM, WM, and cerebrospinal fluid (CSF) tissue probability maps (TPMs).
Retrospective longitudinal study.
Thirty-two healthy participants were scanned twice (legacy data), divided into a training-set (n = 16) and a test-set (n = 16), and 35 randomly-selected participants from the Human Connectome Project.
FIELD STRENGTH/SEQUENCE: 3.0T, diffusion-weighted spin-echo echo-planar sequence; T1-weighted spoiled gradient-recalled echo (SPGR) sequence.
A joint segmentation-registration approach was implemented: Diffusion tensor imaging (DTI) maps were classified into TPMs using machine-learning approaches. The resulting GM, WM, and CSF probability maps were employed as features for image alignment. Validation was performed on the test dataset and the HCP dataset. Registration performance was compared with current mainstream registration tools.
Classifiers used for segmentation were evaluated using leave-one-out cross-validation and scored using Dice-index. Registration success was evaluated by voxel-wise variance, normalized cross-correlation of registered DTI maps, intra- and inter-subject similarity of the registered TPMs, and region-based intra-subject similarity using an anatomical atlas. One-way ANOVAs were performed to compare between our method and other registration tools.
The proposed method outperformed mainstream registration tools as indicated by lower voxel-wise variance of registered DTI maps (SD decrease of 10%) and higher similarity between registered TPMs within and across participants, for all tissue types (Dice increase of 0.1-0.2; P < 0.05).
A joint segmentation-registration approach based on diffusion-driven TPMs provides a more accurate registration of dMRI data, outperforming other registration tools. Our method offers a "translation" of diffusion data into structural information in the form of TPMs, allowing to directly align diffusion and structural images.
1 Technical Efficacy Stage: 1.
目前扩散磁共振成像（dMRI）数据的注册方法主要集中在白质（WM）区域。最近，dMRI 已被用于灰质（GM）微观结构的特征描述，这强调了需要考虑所有组织类型的注册方法。
开发一种基于 GM、WM 和脑脊液（CSF）组织概率图（TPM）的 dMRI 注册方法。
回顾性纵向研究。
32 名健康参与者进行了两次扫描（遗留数据），分为训练集（n=16）和测试集（n=16），以及来自人类连接组计划的 35 名随机参与者。
磁场强度/序列：3.0T，扩散加权自旋回波回波平面序列；T1 加权扰动脉冲梯度回波（SPGR）序列。
采用联合分割-配准方法：使用机器学习方法将扩散张量成像（DTI）图分类为 TPM。生成的 GM、WM 和 CSF 概率图被用作图像对齐的特征。在测试数据集和 HCP 数据集上进行了验证。将注册性能与当前主流注册工具进行了比较。
用于分割的分类器使用留一交叉验证进行评估，并使用 Dice 指数进行评分。通过体素方差、注册 DTI 图的归一化互相关、注册 TPM 在个体内和个体间的相似性以及使用解剖图谱的基于区域的个体内相似性来评估注册成功。使用单向方差分析比较我们的方法和其他注册工具之间的差异。
如注册 DTI 图的体素方差较低（SD 降低 10%）以及注册 TPM 在个体内和个体间的相似性更高（所有组织类型的 Dice 增加 0.1-0.2；P<0.05）所示，所提出的方法优于主流注册工具。
基于扩散驱动的 TPM 的联合分割-配准方法提供了更准确的 dMRI 数据注册，优于其他注册工具。我们的方法以 TPM 的形式提供了扩散数据到结构信息的“转换”，允许直接对齐扩散和结构图像。
1 技术功效阶段：1。
