Learned Multi-layer Residual Sparsifying Transform Model for Low-dose CT Reconstruction

05/08/2020
by   Xikai Yang, et al.
0

Signal models based on sparse representation have received considerable attention in recent years. Compared to synthesis dictionary learning, sparsifying transform learning involves highly efficient sparse coding and operator update steps. In this work, we propose a Multi-layer Residual Sparsifying Transform (MRST) learning model wherein the transform domain residuals are jointly sparsified over layers. In particular, the transforms for the deeper layers exploit the more intricate properties of the residual maps. We investigate the application of the learned MRST model for low-dose CT reconstruction using Penalized Weighted Least Squares (PWLS) optimization. Experimental results on Mayo Clinic data show that the MRST model outperforms conventional methods such as FBP and PWLS methods based on edge-preserving (EP) regularizer and single-layer transform (ST) model, especially for maintaining some subtle details.

READ FULL TEXT

page 1

page 3

page 4

research
10/10/2020

Multi-layer Residual Sparsifying Transform (MARS) Model for Low-dose CT Image Reconstruction

Signal models based on sparse representations have received considerable...
research
03/22/2022

Multi-layer Clustering-based Residual Sparsifying Transform for Low-dose CT Image Reconstruction

The recently proposed sparsifying transform models incur low computation...
research
06/01/2019

Multi-layer Residual Sparsifying Transform Learning for Image Reconstruction

Signal models based on sparsity, low-rank and other properties have been...
research
11/01/2020

Two-layer clustering-based sparsifying transform learning for low-dose CT reconstruction

Achieving high-quality reconstructions from low-dose computed tomography...
research
10/26/2019

SUPER Learning: A Supervised-Unsupervised Framework for Low-Dose CT Image Reconstruction

Recent years have witnessed growing interest in machine learning-based m...
research
10/27/2020

CT Reconstruction with PDF: Parameter-Dependent Framework for Multiple Scanning Geometries and Dose Levels

Current mainstream of CT reconstruction methods based on deep learning u...
research
04/25/2018

Multi Layer Sparse Coding: the Holistic Way

The recently proposed multi-layer sparse model has raised insightful con...

Please sign up or login with your details

Forgot password? Click here to reset