Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery

Abstract

In "extreme" computational imaging that collects extremely undersampled or noisy measurements, obtaining an accurate image within a reasonable computing time is challenging. Incorporating image mapping convolutional neural networks (CNN) into iterative image recovery has great potential to resolve this issue. This paper 1) incorporates image mapping CNN using identical convolutional kernels in both encoders and decoders into a block coordinate descent (BCD) signal recovery method and 2) applies alternating direction method of multipliers to train the aforementioned image mapping CNN. We refer to the proposed recurrent network as BCD-Net using identical encoding-decoding CNN structures. Numerical experiments show that, for a) denoising low signal-to-noise-ratio images and b) extremely undersampled magnetic resonance imaging, the proposed BCD-Net achieves significantly more accurate image recovery, compared to BCD-Net using distinct encoding-decoding structures and/or the conventional image recovery model using both wavelets and total variation.

5 pages, 3 figures

References in corpus (6)

• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• Convolutional Dictionary Learning: Acceleration and Convergence
• Convolutional Sparse Coding for High Dynamic Range Imaging
• Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery
• Compressed Sensing and Parallel Acquisition
• Learning optimal nonlinearities for iterative thresholding algorithms

Cited by in corpus (18)

• Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning
• Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge
• Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery
• Transform Learning for Magnetic Resonance Image Reconstruction: From Model-based Learning to Building Neural Networks
• Wasserstein GANs for MR Imaging: from Paired to Unpaired Training
• Convolutional Analysis Operator Learning: Acceleration and Convergence
• Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
• Systematic Review on Learning-based Spectral CT
• Unified Supervised-Unsupervised (SUPER) Learning for X-ray CT Image Reconstruction
• Neumann Networks for Inverse Problems in Imaging
• Learning Deep Analysis Dictionaries for Image Super-Resolution
• Momentum-Net: Fast and convergent iterative neural network for inverse problems
• NESTANets: Stable, accurate and efficient neural networks for analysis-sparse inverse problems
• Momentum-Net for Low-Dose CT Image Reconstruction
• Cross-domain Denoising for Low-dose Multi-frame Spiral Computed Tomography
• AI-Enabled Ultra-Low-Dose CT Reconstruction
• Deep learning for fast MR imaging: a review for learning reconstruction from incomplete k-space data
• SUPER Learning: A Supervised-Unsupervised Framework for Low-Dose CT Image Reconstruction