Reconstruction of undersampled 3D non‐Cartesian image‐based navigators for coronary MRA using an unrolled deep learning model

• Published in: Magnetic resonance in medicine Vol. 84; no. 2; pp. 800 - 812
• Main Authors: Malavé, Mario O., Baron, Corey A., Koundinyan, Srivathsan P., Sandino, Christopher M., Ong, Frank, Cheng, Joseph Y., Nishimura, Dwight G.
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.08.2020
• Subjects: 3D cones trajectory; Algorithms; Angiography; Artificial neural networks; Cartesian coordinates; Computer architecture; Cones; convolutional neural networks; Coronary Angiography; coronary MRA; Deep Learning; Heart; Humans; Image processing; Image quality; Image reconstruction; Imaging, Three-Dimensional; Machine learning; Magnetic resonance; Magnetic Resonance Angiography; Model accuracy; Navigators; Neural networks; non‐Cartesian; Regularization; Three dimensional models; non-Cartesian; 3D cones trajectory; convolutional neural networks; coronary MRA
• ISSN: 0740-3194; 1522-2594; 1522-2594
• DOI: 10.1002/mrm.28177

Purpose To rapidly reconstruct undersampled 3D non‐Cartesian image‐based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA). Methods An end‐to‐end unrolled network is trained to reconstruct beat‐to‐beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data‐consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable‐density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model‐based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with l1‐ESPIRiT. Then, the high‐resolution coronary MRA images motion corrected with autofocusing using the l1‐ESPIRiT and DL model‐based 3D iNAVs are assessed for differences. Results 3D iNAVs reconstructed using the DL model‐based approach and conventional l1‐ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of l1‐ESPIRiT (20× and 3× speed increases, respectively). Conclusions We have developed a deep neural network architecture to reconstruct undersampled 3D non‐Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction.