Resolution enhancement of wide-field interferometric microscopy by coupled deep autoencoders

Çaǧatay Işil; Mustafa Yorulmaz; Berkan Solmaz; Adil Burak Turhan; Celalettin Yurdakul; Selim Ünlü; Ekmel Ozbay; Aykut Koç

doi:10.1364/AO.57.002545

Resolution enhancement of wide-field interferometric microscopy by coupled deep autoencoders

Çaǧatay Işil, Mustafa Yorulmaz, Berkan Solmaz, Adil Burak Turhan, Celalettin Yurdakul, Selim Ünlü, Ekmel Ozbay, Aykut Koç

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Wide-field interferometric microscopy is a highly sensitive, label-free, and low-cost biosensing imaging technique capable of visualizing individual biological nanoparticles such as viral pathogens and exosomes. However, further resolution enhancement is necessary to increase detection and classification accuracy of subdiffraction-limited nanoparticles. In this study, we propose a deep-learning approach, based on coupled deep autoencoders, to improve resolution of images of L-shaped nanostructures. During training, our method utilizes microscope image patches and their corresponding manual truth image patches in order to learn the transformation between them. Following training, the designed network reconstructs denoised and resolution-enhanced image patches for unseen input.

Original language	English (US)
Pages (from-to)	2545-2552
Number of pages	8
Journal	Applied Optics
Volume	57
Issue number	10
DOIs	https://doi.org/10.1364/AO.57.002545
State	Published - Apr 1 2018
Externally published	Yes

ASJC Scopus subject areas

Atomic and Molecular Physics, and Optics
Engineering (miscellaneous)
Electrical and Electronic Engineering

Access to Document

10.1364/AO.57.002545

Cite this

@article{bd9a9d87b9844120b0ddf81b721f56a4,

title = "Resolution enhancement of wide-field interferometric microscopy by coupled deep autoencoders",

abstract = "Wide-field interferometric microscopy is a highly sensitive, label-free, and low-cost biosensing imaging technique capable of visualizing individual biological nanoparticles such as viral pathogens and exosomes. However, further resolution enhancement is necessary to increase detection and classification accuracy of subdiffraction-limited nanoparticles. In this study, we propose a deep-learning approach, based on coupled deep autoencoders, to improve resolution of images of L-shaped nanostructures. During training, our method utilizes microscope image patches and their corresponding manual truth image patches in order to learn the transformation between them. Following training, the designed network reconstructs denoised and resolution-enhanced image patches for unseen input.",

author = "{\c C}aǧatay I{\c s}il and Mustafa Yorulmaz and Berkan Solmaz and Turhan, {Adil Burak} and Celalettin Yurdakul and Selim {\"U}nl{\"u} and Ekmel Ozbay and Aykut Ko{\c c}",

note = "Publisher Copyright: {\textcopyright} 2018 Optical Society of America.",

year = "2018",

month = apr,

day = "1",

doi = "10.1364/AO.57.002545",

language = "English (US)",

volume = "57",

pages = "2545--2552",

journal = "Applied Optics",

issn = "1559-128X",

publisher = "The Optical Society",

number = "10",

}

TY - JOUR

T1 - Resolution enhancement of wide-field interferometric microscopy by coupled deep autoencoders

AU - Işil, Çaǧatay

AU - Yorulmaz, Mustafa

AU - Solmaz, Berkan

AU - Turhan, Adil Burak

AU - Yurdakul, Celalettin

AU - Ünlü, Selim

AU - Ozbay, Ekmel

AU - Koç, Aykut

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Wide-field interferometric microscopy is a highly sensitive, label-free, and low-cost biosensing imaging technique capable of visualizing individual biological nanoparticles such as viral pathogens and exosomes. However, further resolution enhancement is necessary to increase detection and classification accuracy of subdiffraction-limited nanoparticles. In this study, we propose a deep-learning approach, based on coupled deep autoencoders, to improve resolution of images of L-shaped nanostructures. During training, our method utilizes microscope image patches and their corresponding manual truth image patches in order to learn the transformation between them. Following training, the designed network reconstructs denoised and resolution-enhanced image patches for unseen input.

AB - Wide-field interferometric microscopy is a highly sensitive, label-free, and low-cost biosensing imaging technique capable of visualizing individual biological nanoparticles such as viral pathogens and exosomes. However, further resolution enhancement is necessary to increase detection and classification accuracy of subdiffraction-limited nanoparticles. In this study, we propose a deep-learning approach, based on coupled deep autoencoders, to improve resolution of images of L-shaped nanostructures. During training, our method utilizes microscope image patches and their corresponding manual truth image patches in order to learn the transformation between them. Following training, the designed network reconstructs denoised and resolution-enhanced image patches for unseen input.

UR - http://www.scopus.com/inward/record.url?scp=85044867705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044867705&partnerID=8YFLogxK

U2 - 10.1364/AO.57.002545

DO - 10.1364/AO.57.002545

M3 - Article

C2 - 29714238

AN - SCOPUS:85044867705

SN - 1559-128X

VL - 57

SP - 2545

EP - 2552

JO - Applied Optics

JF - Applied Optics

IS - 10

ER -

Resolution enhancement of wide-field interferometric microscopy by coupled deep autoencoders

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this