Diffusion tensor magnetic resonance imaging (DTI) is unsurpassed in its ability to map tissue microstructure and structural connectivity in the living human brain. Nonetheless, the angular sampling requirement for DTI leads to long scan times and poses a critical barrier to performing high-quality DTI in routine clinical practice and large-scale research studies. In this work we present a new processing framework for DTI entitled DeepDTI that minimizes the data requirement of DTI to six diffusion-weighted images (DWIs) required by conventional voxel-wise fitting methods for deriving the six unique unknowns in a diffusion tensor using data-driven supervised deep learning. DeepDTI maps the input non-diffusion-weighted (b = 0) image and six DWI volumes sampled along optimized diffusion-encoding directions, along with T1-weighted and T2-weighted image volumes, to the residuals between the input and high-quality output b = 0 image and DWI volumes using a 10-layer three-dimensional convolutional neural network (CNN). The inputs and outputs of DeepDTI are uniquely formulated, which not only enables residual learning to boost CNN performance but also enables tensor fitting of resultant high-quality DWIs to generate orientational DTI metrics for tractography. The very deep CNN used by DeepDTI leverages the redundancy in local and non-local spatial information and across diffusion-encoding directions and image contrasts in the data. The performance of DeepDTI was systematically quantified in terms of the quality of the output images, DTI metrics, DTI-based tractography and tract-specific analysis results. We demonstrate rotationally-invariant and robust estimation of DTI metrics from DeepDTI that are comparable to those obtained with two b = 0 images and 21 DWIs for the primary eigenvector derived from DTI and two b = 0 images and 26–30 DWIs for various scalar metrics derived from DTI, achieving 3.3–4.6 × acceleration, and twice as good as those of a state-of-the-art denoising algorithm at the group level. The twenty major white-matter tracts can be accurately identified from the tractography of DeepDTI results. The mean distance between the core of the major white-matter tracts identified from DeepDTI results and those from the ground-truth results using 18 b = 0 images and 90 DWIs measures around 1–1.5 mm. DeepDTI leverages domain knowledge of diffusion MRI physics and power of deep learning to render DTI, DTI-based tractography, major white-matter tracts identification and tract-specific analysis more feasible for a wider range of neuroscientific and clinical studies.

中文翻译：

---

DeepDTI：使用深度学习的高保真六向扩散张量成像

弥散张量磁共振成像 (DTI) 在绘制活人大脑中组织微观结构和结构连通性的能力方面是无与伦比的。尽管如此，DTI 的角度采样要求会导致较长的扫描时间，并成为在常规临床实践和大规模研究中执行高质量 DTI 的关键障碍。在这项工作中，我们提出了一种名为 DeepDTI 的 DTI 新处理框架，该框架将 DTI 的数据需求最小化为传统体素拟合方法所需的六个扩散加权图像 (DWI)，以使用数据导出扩散张量中的六个唯一未知数 -驱动监督深度学习。DeepDTI 映射输入的非扩散加权 (b = 0) 图像和沿优化的扩散编码方向采样的六个 DWI 体积，连同 T1 加权和 T2 加权图像体积，使用 10 层三维卷积神经网络 (CNN) 到输入和高质量输出 b = 0 图像和 DWI 体积之间的残差。DeepDTI 的输入和输出采用独特的公式，这不仅使残差学习能够提高 CNN 性能，而且还能够对生成的高质量 DWI 进行张量拟合，以生成用于牵引成像的定向 DTI 指标。DeepDTI 使用的非常深的 CNN 利用了局部和非局部空间信息中的冗余以及数据中的扩散编码方向和图像对比度。DeepDTI 的性能在输出图像的质量、DTI 指标、基于 DTI 的纤维束成像和特定于纤维束的分析结果方面进行了系统量化。我们展示了来自 DeepDTI 的 DTI 度量的旋转不变性和鲁棒性估计，与从 DTI 派生的主要特征向量的两个 b = 0 图像和 21 个 DWI 以及各种标量度量的两个 b = 0 图像和 26-30 个 DWI 获得的估计相当派生自 DTI，实现了 3.3-4.6 倍的加速度，并且在组级别上是最先进的去噪算法的两倍。从 DeepDTI 结果的纤维束成像中可以准确识别 20 个主要的白质束。从 DeepDTI 结果确定的主要白质束的核心与使用 18 b = 0 图像和 90 个 DWI 的地面实况结果确定的核心之间的平均距离约为 1-1.5 毫米。DeepDTI 利用扩散 MRI 物理学的领域知识和深度学习的力量来渲染 DTI、基于 DTI 的纤维束成像、