Skip to yearly menu bar Skip to main content


Deep ADMM-Net for Compressive Sensing MRI

Yan Yang · Jian Sun · Huibin Li · Zongben Xu

Area 5+6+7+8 #138

Keywords: [ (Other) Machine Learning Topics ] [ Sparsity and Feature Selection ] [ (Application) Signal and Speech Processing ] [ (Other) Optimization ] [ (Application) Computer Vision ] [ Deep Learning or Neural Networks ]


Compressive Sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI). It aims at reconstructing MR image from a small number of under-sampled data in k-space, and accelerating the data acquisition in MRI. To improve the current MRI system in reconstruction accuracy and computational speed, in this paper, we propose a novel deep architecture, dubbed ADMM-Net. ADMM-Net is defined over a data flow graph, which is derived from the iterative procedures in Alternating Direction Method of Multipliers (ADMM) algorithm for optimizing a CS-based MRI model. In the training phase, all parameters of the net, e.g., image transforms, shrinkage functions, etc., are discriminatively trained end-to-end using L-BFGS algorithm. In the testing phase, it has computational overhead similar to ADMM but uses optimized parameters learned from the training data for CS-based reconstruction task. Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that it significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed.

Live content is unavailable. Log in and register to view live content