$\Sigma$-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction

Abstract

Purpose: To systematically investigate the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a $\Sigma$-net, for accelerated parallel MR image reconstruction using deep learning. Theory and Methods: MR image reconstruction is formulated as learned unrolled optimization scheme with a Down-Up network as regularization and varying data consistency layers. The different architectures are split into sensitivity networks, which rely on explicit coil sensitivity maps, and parallel coil networks, which learn the combination of coils implicitly. Different content and adversarial losses, a semi-supervised fine-tuning scheme and model ensembling are investigated. Results: Evaluated on the fastMRI multicoil validation set, architectures involving raw k-space data outperform image enhancement methods significantly. Semi-supervised fine-tuning adapts to new k-space data and provides, together with reconstructions based on adversarial training, the visually most appealing results although quantitative quality metrics are reduced. The $\Sigma$-net ensembles the benefits from different models and achieves similar scores compared to the single state-of-the-art approaches. Conclusion: This work provides an open-source framework to perform a systematic wide-range comparison of state-of-the-art reconstruction approaches for parallel MR image reconstruction on the fastMRI knee dataset and explores the importance of data consistency. A suitable trade-off between perceptual image quality and quantitative scores are achieved with the ensembled $\Sigma$-net.

arXiv commentSubmitted to Magnetic Resonance in Medicine

References in corpus (13)

• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Image reconstruction by domain transform manifold learning
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
• MR fingerprinting Deep RecOnstruction NEtwork (DRONE)
• Real-time Cardiovascular MR with Spatio-temporal Artifact Suppression using Deep Learning - Proof of Concept in Congenital Heart Disease
• Is the deconvolution layer the same as a convolutional layer?
• ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
• Invert to Learn to Invert
• Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction
• DeepRED: Deep Image Prior Powered by RED
• DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution
• $\Sigma$-net: Ensembled Iterative Deep Neural Networks for Accelerated Parallel MR Image Reconstruction

Cited by in corpus (10)

• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
• J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction
• A Helmholtz equation solver using unsupervised learning: Application to transcranial ultrasound
• Complementary Time-Frequency Domain Networks for Dynamic Parallel MR Image Reconstruction
• MRI Image Reconstruction via Learning Optimization Using Neural ODEs
• Model Adaptation for Image Reconstruction using Generalized Stein's Unbiased Risk Estimator
• Estimating MRI Image Quality via Image Reconstruction Uncertainty
• AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry
• Reconstructing unseen modalities and pathology with an efficient Recurrent Inference Machine