End-to-end deep learning nonrigid motion-corrected reconstruction for highly accelerated free-breathing coronary MRA
Loading...
Date
2021
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Purpose: 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).
Methods: 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 (similar to 22x) 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.
Results: The acquisition time for ninefold accelerated CMRA was similar to 2.5 min. The reconstruction time was similar to 22 s for the proposed MoCo-MoDL and similar to 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.
Conclusion: 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.
Methods: 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 (similar to 22x) 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.
Results: The acquisition time for ninefold accelerated CMRA was similar to 2.5 min. The reconstruction time was similar to 22 s for the proposed MoCo-MoDL and similar to 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.
Conclusion: 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.
Description
Keywords
Coronary MRA, Deep learning nonrigid motion correction, Deep learning reconstruction, Free-breathing cardiac MRI