Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Restoration of ultrasound images using spatially-variant kernel deconvolution

Abstract: 

Most of the existing ultrasound image restoration methods consider a spatially-invariant point-spread function (PSF) model and circulant boundary conditions. While computationally efficient, this model is not realistic and severely limits the quality of reconstructed images. In this work, we address ultrasound image restoration under the hypothesis of vertical variation of the PSF. To regularize the solution, we use the classical elastic net constraint. Existing methodologies are rendered impractical either due to their reliance on matrix inversion or due to their inability to exploit the strong convexity of the objective. Therefore, we propose an optimization algorithm based on the Accelerated Composite Gradient Method, adapted and optimized for this task. Our method is guaranteed to converge at a linear rate and is able to adaptively estimate unknown problem parameters. We support our theoretical results with simulation examples.

up
0 users have voted:

Paper Details

Authors:
Mihai I. Florea, Adrian Basarab, Denis Kouame, Sergiy A. Vorobyov
Submitted On:
17 April 2018 - 9:01pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Mihai I. Florea
Paper Code:
2938
Document Year:
2018
Cite

Document Files

Florea2018ICASSP.pdf

(79 downloads)

Keywords

Subscribe

[1] Mihai I. Florea, Adrian Basarab, Denis Kouame, Sergiy A. Vorobyov, "Restoration of ultrasound images using spatially-variant kernel deconvolution", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2954. Accessed: Sep. 20, 2018.
@article{2954-18,
url = {http://sigport.org/2954},
author = {Mihai I. Florea; Adrian Basarab; Denis Kouame; Sergiy A. Vorobyov },
publisher = {IEEE SigPort},
title = {Restoration of ultrasound images using spatially-variant kernel deconvolution},
year = {2018} }
TY - EJOUR
T1 - Restoration of ultrasound images using spatially-variant kernel deconvolution
AU - Mihai I. Florea; Adrian Basarab; Denis Kouame; Sergiy A. Vorobyov
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2954
ER -
Mihai I. Florea, Adrian Basarab, Denis Kouame, Sergiy A. Vorobyov. (2018). Restoration of ultrasound images using spatially-variant kernel deconvolution. IEEE SigPort. http://sigport.org/2954
Mihai I. Florea, Adrian Basarab, Denis Kouame, Sergiy A. Vorobyov, 2018. Restoration of ultrasound images using spatially-variant kernel deconvolution. Available at: http://sigport.org/2954.
Mihai I. Florea, Adrian Basarab, Denis Kouame, Sergiy A. Vorobyov. (2018). "Restoration of ultrasound images using spatially-variant kernel deconvolution." Web.
1. Mihai I. Florea, Adrian Basarab, Denis Kouame, Sergiy A. Vorobyov. Restoration of ultrasound images using spatially-variant kernel deconvolution [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2954