Computed Tomography Image Denoising by Learning to Separate Morphological Diversity

Computed Tomography Image Denoising by Learning to Separate Morphological Diversity Publisher

Khodabandeh A¹ ; Alirezaie J¹ ; Babyn P² ; Ahmadian A³

Show Affiliations

1. Department of Electrical and Computer Engineering, Ryerson University, Toronto, M5B2K3, ON, Canada
2. Department of Medical Imaging, University of Saskatoon Health Region, Royal University Hospital, Saskatoon, S7N0W8, SK, Canada
3. Medical Physics and Biomedical Engineering Department, Faculty of Medicine, Tehran University of Medical Sciences, Tehran, Iran

Source: 2015 38th International Conference on Telecommunications and Signal Processing# TSP 2015 Published:2015

Abstract

Computed Tomography (CT) image denoising is a challenging topic because of the difficulty in modeling noise. In this paper, we propose an image decomposition approach to remove noise from low-dose CT images. We model the image as y = X1 + X2 where the main structures and noise are two superimposed layers. Total Variation (TV) minimization is used to learn two dictionaries to represent structure and noise respectively and sparse coding is used to separate x1 and x2. Finally, an iterative post-processing stage is introduced that uses image-adapted curvelet dictionaries to recover edges. Our results demonstrate that image separation is a viable alternative to the classic K-SVD denoising method. © 2015 IEEE.

2. Three-Dimensional Curvelet-Based Dictionary Learning for Speckle Noise Removal of Optical Coherence Tomography, Biomedical Optics Express (2020)

3. A Novel Underdetermined Source Recovery Algorithm Based on K-Sparse Component Analysis, Circuits# Systems# and Signal Processing (2019)

Experts (# of related papers)

Bahador Makkiabadi (1)

Style	Citing Format
MLA	Khodabandeh A, et al.. "Computed Tomography Image Denoising by Learning to Separate Morphological Diversity." 2015 38th International Conference on Telecommunications and Signal Processing# TSP 2015, vol. , no. , 2015, pp. 513-517.
APA	Khodabandeh A, Alirezaie J, Babyn P, Ahmadian A (2015). Computed Tomography Image Denoising by Learning to Separate Morphological Diversity. 2015 38th International Conference on Telecommunications and Signal Processing# TSP 2015, (), 513-517.
Chicago	Khodabandeh A, Alirezaie J, Babyn P, Ahmadian A. "Computed Tomography Image Denoising by Learning to Separate Morphological Diversity." 2015 38th International Conference on Telecommunications and Signal Processing# TSP 2015 , no. (2015): 513-517.
Harvard	Khodabandeh A et al. (2015) 'Computed Tomography Image Denoising by Learning to Separate Morphological Diversity', 2015 38th International Conference on Telecommunications and Signal Processing# TSP 2015, (), pp. 513-517.
Vancouver	Khodabandeh A, Alirezaie J, Babyn P, Ahmadian A. Computed Tomography Image Denoising by Learning to Separate Morphological Diversity. 2015 38th International Conference on Telecommunications and Signal Processing# TSP 2015. 2015;():513-517.
BibTex	@article{ author = {Khodabandeh A and Alirezaie J and Babyn P and Ahmadian A}, title = {Computed Tomography Image Denoising by Learning to Separate Morphological Diversity}, journal = {2015 38th International Conference on Telecommunications and Signal Processing# TSP 2015}, volume = {}, number = {}, pages = {513-517}, year = {2015} }
RIS	TY - JOUR AU - Khodabandeh A AU - Alirezaie J AU - Babyn P AU - Ahmadian A TI - Computed Tomography Image Denoising by Learning to Separate Morphological Diversity JO - 2015 38th International Conference on Telecommunications and Signal Processing# TSP 2015 VL - IS - SP - 513 EP - 517 PY - 2015 ER -

Science Communicator Platform

Authors

Authors Affiliations

Abstract