Self-Supervised Learning for Improved Calibrationless Radial MRI with NLINV-Net

Abstract

Purpose: To develop a neural network architecture for improved calibrationless reconstruction of radial data when no ground truth is available for training. Methods: NLINV-Net is a model-based neural network architecture that directly estimates images and coil sensitivities from (radial) k-space data via non-linear inversion (NLINV). Combined with a training strategy using self-supervision via data undersampling (SSDU), it can be used for imaging problems where no ground truth reconstructions are available. We validated the method for (1) real-time cardiac imaging and (2) single-shot subspace-based quantitative T1 mapping. Furthermore, region-optimized virtual (ROVir) coils were used to suppress artifacts stemming from outside the FoV and to focus the k-space based SSDU loss on the region of interest. NLINV-Net based reconstructions were compared with conventional NLINV and PI-CS (parallel imaging + compressed sensing) reconstruction and the effect of the region-optimized virtual coils and the type of training loss was evaluated qualitatively. Results: NLINV-Net based reconstructions contain significantly less noise than the NLINV-based counterpart. ROVir coils effectively suppress streakings which are not suppressed by the neural networks while the ROVir-based focussed loss leads to visually sharper time series for the movement of the myocardial wall in cardiac real-time imaging. For quantitative imaging, T1-maps reconstructed using NLINV-Net show similar quality as PI-CS reconstructions, but NLINV-Net does not require slice-specific tuning of the regularization parameter. Conclusion: NLINV-Net is a versatile tool for calibrationless imaging which can be used in challenging imaging scenarios where a ground truth is not available.

Submitted to Magnetic Resonance in Medicine

References in corpus (11)

• MoDL: Model Based Deep Learning Architecture for Inverse Problems
• Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference Data
• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Real-time Cardiovascular MR with Spatio-temporal Artifact Suppression using Deep Learning - Proof of Concept in Congenital Heart Disease
• Simple Auto-Calibrated Gradient Delay Estimation From Few Spokes Using Radial Intersections (RING)
• Physics-based Reconstruction Methods for Magnetic Resonance Imaging
• An End-To-End-Trainable Iterative Network Architecture for Accelerated Radial Multi-Coil 2D Cine MR Image Reconstruction
• Self-Supervised Physics-Guided Deep Learning Reconstruction For High-Resolution 3D LGE CMR
• Zero-DeepSub: Zero-Shot Deep Subspace Reconstruction for Rapid Multiparametric Quantitative MRI Using 3D-QALAS
• Joint T1 and T2 Mapping with Tiny Dictionaries and Subspace-Constrained Reconstruction
• Physics-informed self-supervised deep learning reconstruction for accelerated first-pass perfusion cardiac MRI

Cited by in corpus (3)

• A Tutorial on MRI Reconstruction: From Modern Methods to Clinical Implications
• Rapid, High-resolution and Distortion-free $R_2^{\ast }$ Mapping of Fetal Brain using Multi-echo Radial FLASH and Model-based Reconstruction
• BART Streams: Real-time Reconstruction Using a Modular Framework for Pipeline Processing