Deep ADMM-Net for Compressive Sensing MRI

By Yan Yang, Huibin Li, Zongben Xu. 2016

1,255 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Luc Van Gool
2. Kai Zhang
3. Radu Timofte
4. Lei Zhang
5. Dacheng Tao
6. Jun Shu
7. Wangmeng Zuo
8. Yoshua Bengio

Citations in the corpus

• Training Networks in Null Space of Feature Covariance for Continual Learning (2021, neutral): “Deep neural networks have achieved promising performance on various tasks in natural language processing, machine intelligence, etc., [5, 9, 47, 48, 51].”
• Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations (2017, methodology): “On the other hand, many deep network designs were inspired by optimization algorithms, such as the network LISTA (Gregor & LeCun, 2010) and the ADMM-Net (Yang et al., 2016).”
• Rank Minimization for Snapshot Compressive Imaging (2018, methodology): “Most recently, the deep learning algorithms have been used in CS inversion [63], [64], [65] and as mentioned in the introduction, deep learning has been employed for video CS in [30], [31] (but with some constraints).”
• Plug-and-Play Methods Provably Converge with Properly Trained Denoisers (2019, methodology): “(4)Some recent deep-learning based methods (Yang et al., 2016; Kulkarni et al., 2016; Metzler et al., 2017; Zhang & Ghanem, 2018) are not compared here because we assume we do not have enough medical images for training.”
• Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss (2017, background): “Another interesting deep learning-based CS-MRI approach is Deep ADMM-Net [34], which is a deep neural network architecture that learns parameters of the ADMM algorithm (e.g., penalty parameters, shrinkage functions, etc.) by using training data.”
• CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction (2017, methodology): “This includes learning a CNN as an unrolled version of ISTA [25] and ADMM [26].”
• Deep Unfolding Network for Image Super-Resolution (2020, background): “…e.g ., half-quadratic splitting [2], alternating direction method of multipliers [6] and primal-dual [1, 9]) have been proposed to solve different image restoration tasks, such as image de-noising [11, 32], image deblurring [29, 49], image compressive sensing [61, 63], and image demosaicking [28].”
• Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods (2018, background): “[49] showed that choosing a neural network in this way could achieve higher reconstruction performance than state-of-the-art methods.”
• Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction (2017, methodology): “ADMM-Net [17] was proposed by reformulating an alternating direction method of multipliers (ADMM) algorithm to a deep network, where each stage of the architecture corresponds to an iteration in ADMM algorithm.”
• Solving ill-posed inverse problems using iterative deep neural networks (2017, background): “An example of such a scheme for solving inverse problems is [42], which learns an ADMM-like scheme for Fourier inversion.”
• Learned Primal-Dual Reconstruction (2017, background): “One of the first works on learned iterative schemes is [12], which learns an ADMM-like scheme for MRI reconstruction.”
• Convolutional Neural Networks for Inverse Problems in Imaging: A Review (2017, methodology): “For example, in MRI reconstruction, [22] trains using under-sampled k-space data as inputs and reconstructions from fully-sampled k-space data as outputs.”
• Deep Generative Adversarial Neural Networks for Compressive Sensing (GANCS) MRI (2018, methodology): “[29] unrolls the ADMM optimization for solving the inverse problem for CS-MRI, and improves the modeling by representing projections with neural networks.”