Super-Resolution OCT Based on α-Stable Distributions and Sparse Representations

Daniel Valdez Zermeno; Perla Jazmin Mayo Diaz De Leon; Lindsay B Nicholson; Alin M Achim

Super-Resolution OCT Based on α-Stable Distributions and Sparse Representations

Daniel Valdez Zermeno, Perla Jazmin Mayo Diaz De Leon, Lindsay B Nicholson, Alin M Achim

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

81 Downloads (Pure)

Abstract

We present a new approach to single-image super-resolution in Optical Coherence Tomography (OCT) images. Indeed, although OCT is the one in-vivo retinal imaging modality offering the highest resolution, this is still far below what microscopy techniques can achieve, albeit ex-vivo. In this work we investigate a non-convex regularization technique using a multivariate generalization of the minimax-concave (GMC) scheme and a forward-backward splitting (FBS) algorithm. Based on the observation that sparse representations of OCT images are heavytailed, an -stable dictionary is employed. The resulting algorithm is tested on real OCT retinal images of murine eyes. Significant deblurring and general quality enhancement is noticed and in most cases our method provides the best results both objectively and subjectively.

Original language	English
Title of host publication	Proceedings of the International BASP Frontiers Workshop 2019
Publisher	Heriot-Watt University
Pages	61
Number of pages	1
Publication status	Published - 3 Feb 2019
Event	International Biomedical and Astronomical Signal Processing Frontiers workshop 2019 - Villars-sur-Ollon, Switzerland Duration: 3 Feb 2019 → 8 Feb 2019 Conference number: 5 http://www.baspfrontiers.org/index.php

Publication series

Name	International BASP Frontiers workshop

Workshop

Workshop	International Biomedical and Astronomical Signal Processing Frontiers workshop 2019
Abbreviated title	BASP Frontiers 2019
Country/Territory	Switzerland
City	Villars-sur-Ollon
Period	3/02/19 → 8/02/19
Internet address	http://www.baspfrontiers.org/index.php

Access to Document

Full-text PDF (accepted author manuscript
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via BASP at https://www.baspfrontiers.org/proceedings.php. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 1.32 MB

https://www.baspfrontiers.org/proceedings.php

Handle.net

Persistent link

Cite this

@inproceedings{afda5e16f9d94f169c9f8c334c079d7d,

title = "Super-Resolution OCT Based on α-Stable Distributions and Sparse Representations",

abstract = "We present a new approach to single-image super-resolution in Optical Coherence Tomography (OCT) images. Indeed, although OCT is the one in-vivo retinal imaging modality offering the highest resolution, this is still far below what microscopy techniques can achieve, albeit ex-vivo. In this work we investigate a non-convex regularization technique using a multivariate generalization of the minimax-concave (GMC) scheme and a forward-backward splitting (FBS) algorithm. Based on the observation that sparse representations of OCT images are heavytailed, an -stable dictionary is employed. The resulting algorithm is tested on real OCT retinal images of murine eyes. Significant deblurring and general quality enhancement is noticed and in most cases our method provides the best results both objectively and subjectively.",

author = "{Valdez Zermeno}, Daniel and {Mayo Diaz De Leon}, {Perla Jazmin} and Nicholson, {Lindsay B} and Achim, {Alin M}",

year = "2019",

month = feb,

day = "3",

language = "English",

series = "International BASP Frontiers workshop",

publisher = "Heriot-Watt University",

pages = "61",

booktitle = "Proceedings of the International BASP Frontiers Workshop 2019",

note = "International Biomedical and Astronomical Signal Processing Frontiers workshop 2019, BASP Frontiers 2019 ; Conference date: 03-02-2019 Through 08-02-2019",

url = "http://www.baspfrontiers.org/index.php",

}

Valdez Zermeno, D, Mayo Diaz De Leon, PJ , Nicholson, LB & Achim, AM 2019, Super-Resolution OCT Based on α-Stable Distributions and Sparse Representations. in Proceedings of the International BASP Frontiers Workshop 2019. International BASP Frontiers workshop, Heriot-Watt University, pp. 61, International Biomedical and Astronomical Signal Processing Frontiers workshop 2019, Villars-sur-Ollon, Switzerland, 3/02/19. <https://www.baspfrontiers.org/proceedings.php>

Super-Resolution OCT Based on α-Stable Distributions and Sparse Representations. / Valdez Zermeno, Daniel; Mayo Diaz De Leon, Perla Jazmin ; Nicholson, Lindsay B et al.
Proceedings of the International BASP Frontiers Workshop 2019. Heriot-Watt University, 2019. p. 61 (International BASP Frontiers workshop).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Super-Resolution OCT Based on α-Stable Distributions and Sparse Representations

AU - Valdez Zermeno, Daniel

AU - Mayo Diaz De Leon, Perla Jazmin

AU - Nicholson, Lindsay B

AU - Achim, Alin M

N1 - Conference code: 5

PY - 2019/2/3

Y1 - 2019/2/3

N2 - We present a new approach to single-image super-resolution in Optical Coherence Tomography (OCT) images. Indeed, although OCT is the one in-vivo retinal imaging modality offering the highest resolution, this is still far below what microscopy techniques can achieve, albeit ex-vivo. In this work we investigate a non-convex regularization technique using a multivariate generalization of the minimax-concave (GMC) scheme and a forward-backward splitting (FBS) algorithm. Based on the observation that sparse representations of OCT images are heavytailed, an -stable dictionary is employed. The resulting algorithm is tested on real OCT retinal images of murine eyes. Significant deblurring and general quality enhancement is noticed and in most cases our method provides the best results both objectively and subjectively.

AB - We present a new approach to single-image super-resolution in Optical Coherence Tomography (OCT) images. Indeed, although OCT is the one in-vivo retinal imaging modality offering the highest resolution, this is still far below what microscopy techniques can achieve, albeit ex-vivo. In this work we investigate a non-convex regularization technique using a multivariate generalization of the minimax-concave (GMC) scheme and a forward-backward splitting (FBS) algorithm. Based on the observation that sparse representations of OCT images are heavytailed, an -stable dictionary is employed. The resulting algorithm is tested on real OCT retinal images of murine eyes. Significant deblurring and general quality enhancement is noticed and in most cases our method provides the best results both objectively and subjectively.

M3 - Conference Contribution (Conference Proceeding)

T3 - International BASP Frontiers workshop

SP - 61

BT - Proceedings of the International BASP Frontiers Workshop 2019

PB - Heriot-Watt University

T2 - International Biomedical and Astronomical Signal Processing Frontiers workshop 2019

Y2 - 3 February 2019 through 8 February 2019

ER -

Super-Resolution OCT Based on α-Stable Distributions and Sparse Representations

Abstract

Publication series

Workshop

Access to Document

Handle.net

Fingerprint

Cite this