School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.
School of Biomedical Engineering, ShanghaiTech University, Shanghai, People's Republic of China.
Magn Reson Med. 2021 Oct;86(4):1983-1996. doi: 10.1002/mrm.28851. Epub 2021 Jun 6.
To develop an end-to-end deep learning technique for nonrigid motion-corrected (MoCo) reconstruction of ninefold undersampled free-breathing whole-heart coronary MRA (CMRA).
A novel deep learning framework was developed consisting of a diffeomorphic registration network and a motion-informed model-based deep learning (MoDL) reconstruction network. The registration network receives as input highly undersampled (~22×) respiratory-resolved images and outputs 3D nonrigid respiratory motion fields between the images. The motion-informed MoDL performs MoCo reconstruction from undersampled data using the predicted motion fields. The whole deep learning framework, termed as MoCo-MoDL, was trained end-to-end in a supervised manner for simultaneous 3D nonrigid motion estimation and MoCo reconstruction. MoCo-MoDL was compared with a state-of-the-art nonrigid MoCo CMRA reconstruction technique in 15 retrospectively undersampled datasets and 9 prospectively undersampled acquisitions.
The acquisition time for ninefold accelerated CMRA was ~2.5 min. The reconstruction time was ~22 s for the proposed MoCo-MoDL and ~35 min for the conventional approach. MoCo-MoDL achieved higher peak SNR (27.86 ± 3.00 vs. 26.71 ± 2.79; P < .05) and structural similarity (0.78 ± 0.06 vs. 0.75 ± 0.06; P < .05) than the conventional approach. Similar vessel length and visual image quality score were obtained with the 2 methods, whereas improved vessel sharpness was observed with MoCo-MoDL.
An end-to-end deep learning approach was introduced for simultaneous nonrigid motion estimation and MoCo reconstruction of highly undersampled free-breathing whole-heart CMRA. The rapid free-breathing CMRA acquisition together with the fast reconstruction of the proposed approach promises easy integration into clinical workflow.
开发一种端到端深度学习技术，用于对九倍欠采样自由呼吸全心冠状动脉 MRA（CMRA）进行非刚性运动校正（MoCo）重建。
开发了一种新的深度学习框架，由变形配准网络和运动感知基于模型的深度学习（MoDL）重建网络组成。该配准网络接收高度欠采样（约 22×）呼吸分辨图像，并输出图像之间的 3D 非刚性呼吸运动场。运动感知的 MoDL 使用预测的运动场从欠采样数据中进行 MoCo 重建。整个深度学习框架，称为 MoCo-MoDL，通过监督方式进行端到端训练，用于同时进行 3D 非刚性运动估计和 MoCo 重建。MoCo-MoDL 在 15 个回顾性欠采样数据集和 9 个前瞻性欠采样采集的研究中与一种先进的非刚性 MoCo CMRA 重建技术进行了比较。
九倍加速 CMRA 的采集时间约为 2.5 分钟。所提出的 MoCo-MoDL 的重建时间约为 22 秒，而传统方法的重建时间约为 35 分钟。MoCo-MoDL 获得了更高的峰值信噪比（27.86 ± 3.00 与 26.71 ± 2.79；P <.05）和结构相似性（0.78 ± 0.06 与 0.75 ± 0.06；P <.05）比传统方法。两种方法都获得了相似的血管长度和视觉图像质量评分，而 MoCo-MoDL 观察到了更好的血管锐利度。
提出了一种端到端深度学习方法，用于高度欠采样自由呼吸全心 CMRA 的非刚性运动估计和 MoCo 重建。快速自由呼吸 CMRA 采集与所提出的快速重建方法的结合有望轻松集成到临床工作流程中。
