Self-Supervised Deep Active Accelerated MRI

Abstract

We propose to simultaneously learn to sample and reconstruct magnetic resonance images (MRI) to maximize the reconstruction quality given a limited sample budget, in a self-supervised setup. Unlike existing deep methods that focus only on reconstructing given data, thus being passive, we go beyond the current state of the art by considering both the data acquisition and the reconstruction process within a single deep-learning framework. As our network learns to acquire data, the network is active in nature. In order to do so, we simultaneously train two neural networks, one dedicated to reconstruction and the other to progressive sampling, each with an automatically generated supervision signal that links them together. The two supervision signals are created through Monte Carlo tree search (MCTS). MCTS returns a better sampling pattern than what the current sampling network can give and, thus, a better final reconstruction. The sampling network is trained to mimic the MCTS results using the previous sampling network, thus being enhanced. The reconstruction network is trained to give the highest reconstruction quality, given the MCTS sampling pattern. Through this framework, we are able to train the two networks without providing any direct supervision on sampling.

References in corpus (1)

• Deep Convolutional Neural Network for Inverse Problems in Imaging

Cited by in corpus (15)

• J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction
• B-spline Parameterized Joint Optimization of Reconstruction and K-space Trajectories (BJORK) for Accelerated 2D MRI
• Wasserstein GANs for MR Imaging: from Paired to Unpaired Training
• MRzero -- Fully automated discovery of MRI sequences using supervised learning
• PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
• Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI
• VS-Net: Variable splitting network for accelerated parallel MRI reconstruction
• Deep Learning for Biomedical Image Reconstruction: A Survey
• High-efficient Bloch simulation of magnetic resonance imaging sequences based on deep learning
• Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning
• Experimental design for MRI by greedy policy search
• Active 3D Shape Reconstruction from Vision and Touch
• Bayesian Optimization of Sampling Densities in MRI
• Off-the-grid data-driven optimization of sampling schemes in MRI
• One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline