DeepDTI: High-fidelity six-direction diffusion tensor imaging using deep learning

• Published in: NeuroImage (Orlando, Fla.) Vol. 219; p. 117017
• Main Authors: Tian, Qiyuan, Bilgic, Berkin, Fan, Qiuyun, Liao, Congyu, Ngamsombat, Chanon, Hu, Yuxin, Witzel, Thomas, Setsompop, Kawin, Polimeni, Jonathan R., Huang, Susie Y.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.10.2020; Elsevier Limited; Elsevier
• Subjects: Brain - diagnostic imaging; Brain research; Connectome; Convolutional neural network; Data redundancy; Deep Learning; Denoising; Diffusion tensor imaging; Diffusion Tensor Imaging - methods; Diffusion tractography; Humans; Image Processing, Computer-Assisted - methods; Magnetic resonance imaging; Methods; Nerve Net - diagnostic imaging; Neural networks; Neural Networks, Computer; Neuroimaging; Residual learning; Substantia alba; Tract-specific analysis; Deep learning; Diffusion tractography; Tract-specific analysis; Convolutional neural network; Residual learning; Data redundancy; Diffusion tensor imaging; Denoising
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2020.117017

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. •A new processing framework for DTI using data-driven supervised deep learning.•DeepDTI minimizes the data requirement of DTI to one b=0 and six DWI volumes.•The DeepDTI framework maps both scalar and orientational DTI metrics.•Enables DTI-based tractography and tract-specific analysis using a 30-60 second scan.•Comparable to fully-sampled DTI scan and better than benchmark denoising algorithm.