# Reconstruction of Undersampled 3D Non-Cartesian Image-Based Navigators for Coronary MRA Using an Unrolled Deep Learning Model

arXiv: https://arxiv.org/abs/1910.11414 · HTML: https://mlsanity.com/paper/1910.11414/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2019.

## Built on by (most cited first, 5 of 5)

- [AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis](https://mlsanity.com/paper/2112.12744/) (2021)
- [An End-To-End-Trainable Iterative Network Architecture for Accelerated Radial Multi-Coil 2D Cine MR Image Reconstruction](https://mlsanity.com/paper/2102.00783/) (2021)
- [A Projection-Based K-space Transformer Network for Undersampled Radial MRI Reconstruction with Limited Training Subjects](https://mlsanity.com/paper/2206.07219/) (2022)
- [Data-Consistent Non-Cartesian Deep Subspace Learning for Efficient Dynamic MR Image Reconstruction](https://mlsanity.com/paper/2205.01770/) (2022)
- [A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction](https://mlsanity.com/paper/2203.14769/) (2022)

## Abstract (arXiv)

Purpose: To rapidly reconstruct undersampled 3D non-Cartesian image-based navigators (iNAVs) using an unrolled deep learning (DL) model for non-rigid motion correction in coronary magnetic resonance angiography (CMRA). Methods: An unrolled network is trained to reconstruct beat-to-beat 3D iNAVs acquired as part of a CMRA sequence. The unrolled model incorporates a non-uniform FFT operator 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 textitl1-ESPIRiT. Then, the high-resolution coronary MRA images motion corrected with autofocusing using the textitl1-ESPIRiT and DL model-based 3D iNAVs are assessed for differences. Results: 3D iNAVs reconstructed using the DL model-based approach and conventional textitl1-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 textitl1-ESPIRiT (20x and 3x speed increases, respectively). Conclusion: 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 non-rigid motion information offered by them for correction.