Noise Reduction in CT Using Learned Wavelet-Frame Shrinkage Networks

Encoding-decoding (ED) CNNs have demonstrated state-of-the-art performance for noise reduction over the past years. This has triggered the pursuit of better understanding the inner workings of such architectures, which has led to the theory of deep convolutional framelets (TDCF), revealing important...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2022-08, Vol.41 (8), p.2048-2066
Main Authors: Zavala-Mondragon, Luis A., Rongen, Peter, Bescos, Javier Olivan, de With, Peter H. N., van der Sommen, Fons
Format: Article
Language:English
Subjects:
Computed tomography
Convolution
Convolutional neural networks
Discrete wavelet transforms
Encoding
Encoding-Decoding
Noise reduction
Redundancy
Shrinkage
Signal processing
Thresholding (Imaging)
wavelet frames
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Encoding-decoding (ED) CNNs have demonstrated state-of-the-art performance for noise reduction over the past years. This has triggered the pursuit of better understanding the inner workings of such architectures, which has led to the theory of deep convolutional framelets (TDCF), revealing important links between signal processing and CNNs. Specifically, the TDCF demonstrates that ReLU CNNs induce low-rankness, since these models often do not satisfy the necessary redundancy to achieve perfect reconstruction (PR). In contrast, this paper explores CNNs that do meet the PR conditions. We demonstrate that in these type of CNNs soft shrinkage and PR can be assumed. Furthermore, based on our explorations we propose the learned wavelet-frame shrinkage network , or LWFSN and its residual counterpart, the rLWFSN. The ED path of the (r)LWFSN complies with the PR conditions, while the shrinkage stage is based on the linear expansion of thresholds proposed Blu and Luisier. In addition, the LWFSN has only a fraction of the training parameters (
ISSN:0278-0062
1558-254X
DOI:10.1109/TMI.2022.3154011