Deep, Deep Learning with BART

Abstract

Purpose: To develop a deep-learning-based image reconstruction framework for reproducible research in MRI. Methods: The BART toolbox offers a rich set of implementations of calibration and reconstruction algorithms for parallel imaging and compressed sensing. In this work, BART was extended by a non-linear operator framework that provides automatic differentiation to allow computation of gradients. Existing MRI-specific operators of BART, such as the non-uniform fast Fourier transform, are directly integrated into this framework and are complemented by common building blocks used in neural networks. To evaluate the use of the framework for advanced deep-learning-based reconstruction, two state-of-the-art unrolled reconstruction networks, namely the Variational Network [1] and MoDL [2], were implemented. Results: State-of-the-art deep image-reconstruction networks can be constructed and trained using BART's gradient based optimization algorithms. The BART implementation achieves a similar performance in terms of training time and reconstruction quality compared to the original implementations based on TensorFlow. Conclusion: By integrating non-linear operators and neural networks into BART, we provide a general framework for deep-learning-based reconstruction in MRI.

arXiv commentSubmitted to Magnetic Resonance in Medicine

References in corpus (10)

• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Image reconstruction by domain transform manifold learning
• MoDL: Model Based Deep Learning Architecture for Inverse Problems
• Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge
• Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems
• MRI Reconstruction Using Deep Bayesian Estimation
• Simple Auto-Calibrated Gradient Delay Estimation From Few Spokes Using Radial Intersections (RING)
• Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
• An End-To-End-Trainable Iterative Network Architecture for Accelerated Radial Multi-Coil 2D Cine MR Image Reconstruction
• ENLIVE: An Efficient Nonlinear Method for Calibrationless and Robust Parallel Imaging

Cited by in corpus (2)

• Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Models
• Quantitative Magnetic Resonance Imaging by Nonlinear Inversion of the Bloch Equations