Real-time Cardiovascular MR with Spatio-temporal Artifact Suppression using Deep Learning - Proof of Concept in Congenital Heart Disease

Abstract

PURPOSE: Real-time assessment of ventricular volumes requires high acceleration factors. Residual convolutional neural networks (CNN) have shown potential for removing artifacts caused by data undersampling. In this study we investigated the effect of different radial sampling patterns on the accuracy of a CNN. We also acquired actual real-time undersampled radial data in patients with congenital heart disease (CHD), and compare CNN reconstruction to Compressed Sensing (CS). METHODS: A 3D (2D plus time) CNN architecture was developed, and trained using 2276 gold-standard paired 3D data sets, with 14x radial undersampling. Four sampling schemes were tested, using 169 previously unseen 3D 'synthetic' test data sets. Actual real-time tiny Golden Angle (tGA) radial SSFP data was acquired in 10 new patients (122 3D data sets), and reconstructed using the 3D CNN as well as a CS algorithm; GRASP. RESULTS: Sampling pattern was shown to be important for image quality, and accurate visualisation of cardiac structures. For actual real-time data, overall reconstruction time with CNN (including creation of aliased images) was shown to be more than 5x faster than GRASP. Additionally, CNN image quality and accuracy of biventricular volumes was observed to be superior to GRASP for the same raw data. CONCLUSION: This paper has demonstrated the potential for the use of a 3D CNN for deep de-aliasing of real-time radial data, within the clinical setting. Clinical measures of ventricular volumes using real-time data with CNN reconstruction are not statistically significantly different from the gold-standard, cardiac gated, BH techniques.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems
• A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• Anisotropic field-of-views in radial imaging
• Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction

Cited by in corpus (20)

• Plug and play methods for magnetic resonance imaging (long version)
• Deep Learning in Photoacoustic Tomography: Current approaches and future directions
• Spatio-Temporal Deep Learning-Based Undersampling Artefact Reduction for 2D Radial Cine MRI with Limited Data
• Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
• Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networks
• An End-To-End-Trainable Iterative Network Architecture for Accelerated Radial Multi-Coil 2D Cine MR Image Reconstruction
• OCMR (v1.0)--Open-Access Multi-Coil k-Space Dataset for Cardiovascular Magnetic Resonance Imaging
• $\Sigma$-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction
• HyperSLICE: HyperBand optimized Spiral for Low-latency Interactive Cardiac Examination
• Self-Supervised Learning for Improved Calibrationless Radial MRI with NLINV-Net
• Complementary Time-Frequency Domain Networks for Dynamic Parallel MR Image Reconstruction
• Real-Time Cardiac Cine MRI with Residual Convolutional Recurrent Neural Network
• Self-supervised feature learning for cardiac Cine MR image reconstruction
• NoSENSE: Learned unrolled cardiac MRI reconstruction without explicit sensitivity maps
• Artificial Intelligence-Based Image Reconstruction in Cardiac Magnetic Resonance
• Detection and Correction of Cardiac MR Motion Artefacts during Reconstruction from K-space
• Localized Motion Artifact Reduction on Brain MRI Using Deep Learning with Effective Data Augmentation Techniques
• Machine Learning aided k-t SENSE for fast reconstruction of highly accelerated PCMR data
• Unsupervised Metal Artifact Reduction in Dental CBCT using Fine-tuned Cycle-Consistent Adversarial Networks
• Unsupervised Adaptive Neural Network Regularization for Accelerated Radial Cine MRI