Hyperspectral imaging of human skin aided by artificial neural networks

Evgeny Zherebtsov; Viktor Dremin; Alexey Popov; Alexander Doronin; Daria Kurakina; Mikhail Kirillin; Igor Meglinski; Alexander Bykov

doi:10.1364/BOE.10.003545

Hyperspectral imaging of human skin aided by artificial neural networks

Evgeny Zherebtsov, Viktor Dremin, Alexey Popov, Alexander Doronin, Daria Kurakina, Mikhail Kirillin, Igor Meglinski, Alexander Bykov^*

^*Corresponding author for this work

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

110 Citations (SciVal)

9 Downloads (Pure)

Abstract

We developed a compact, hand-held hyperspectral imaging system for 2D neural network-based visualization of skin chromophores and blood oxygenation. State-of-the-art micro-optic multichannel matrix sensor combined with the tunable Fabry-Perot micro interferometer enables a portable diagnostic device sensitive to the changes of the oxygen saturation as well as the variations of blood volume fraction of human skin. Generalized object-oriented Monte Carlo model is used extensively for the training of an artificial neural network utilized for the hyperspectral image processing. In addition, the results are verified and validated via actual experiments with tissue phantoms and human skin in vivo. The proposed approach enables a tool combining both the speed of an artificial neural network processing and the accuracy and flexibility of advanced Monte Carlo modeling. Finally, the results of the feasibility studies and the experimental tests on biotissue phantoms and healthy volunteers are presented.

Original language	English
Article number	364396
Pages (from-to)	3545-3559
Number of pages	15
Journal	Biomedical Optics Express
Volume	10
Issue number	7
DOIs	https://doi.org/10.1364/BOE.10.003545
Publication status	Published - 24 Jun 2019

Bibliographical note

© 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Funding: Academy of Finland (290596, 314369, 318281); Ministry of Science and Higher Education of Russian Federation (0035-2019-0014)

Funding

1Opto-Electronics and Measurement Techniques Research Unit, Faculty of Information Technology and Electrical Engineering, University of Oulu, PO Box 4500, 90014 Oulu, Finland 2School of Engineering and Computer Science, Victoria University of Wellington, PO Box 600, 6140 Wellington, New Zealand 3Institute of Applied Physics of the Russian Academy of Sciences, 46 Ul’yanov Street, 603950 Nizhny Novgorod, Russia 4Lobachevsky State University of Nizhny Novgorod, 23 Gagarin Avenue, 603950 Nizhny Novgorod, Russia 5Institute of Engineering Physics for Biomedicine, National Research Nuclear University MEPhI (Moscow Engineering Physics Institute), 115409 Moscow, Russia

Access to Document

10.1364/BOE.10.003545Licence: Other

Hyperspectral imaging of human skin
© 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Final published version, 7.17 MBLicence: Other

Cite this

@article{8f59fe18dfe54d96b7f4e7492082ac4e,

title = "Hyperspectral imaging of human skin aided by artificial neural networks",

abstract = "We developed a compact, hand-held hyperspectral imaging system for 2D neural network-based visualization of skin chromophores and blood oxygenation. State-of-the-art micro-optic multichannel matrix sensor combined with the tunable Fabry-Perot micro interferometer enables a portable diagnostic device sensitive to the changes of the oxygen saturation as well as the variations of blood volume fraction of human skin. Generalized object-oriented Monte Carlo model is used extensively for the training of an artificial neural network utilized for the hyperspectral image processing. In addition, the results are verified and validated via actual experiments with tissue phantoms and human skin in vivo. The proposed approach enables a tool combining both the speed of an artificial neural network processing and the accuracy and flexibility of advanced Monte Carlo modeling. Finally, the results of the feasibility studies and the experimental tests on biotissue phantoms and healthy volunteers are presented.",

author = "Evgeny Zherebtsov and Viktor Dremin and Alexey Popov and Alexander Doronin and Daria Kurakina and Mikhail Kirillin and Igor Meglinski and Alexander Bykov",

note = "{\textcopyright} 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement Funding: Academy of Finland (290596, 314369, 318281); Ministry of Science and Higher Education of Russian Federation (0035-2019-0014)",

year = "2019",

month = jun,

day = "24",

doi = "10.1364/BOE.10.003545",

language = "English",

volume = "10",

pages = "3545--3559",

journal = "Biomedical Optics Express",

issn = "2156-7085",

publisher = "The Optical Society",

number = "7",

}

TY - JOUR

T1 - Hyperspectral imaging of human skin aided by artificial neural networks

AU - Zherebtsov, Evgeny

AU - Dremin, Viktor

AU - Popov, Alexey

AU - Doronin, Alexander

AU - Kurakina, Daria

AU - Kirillin, Mikhail

AU - Meglinski, Igor

AU - Bykov, Alexander

N1 - © 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement Funding: Academy of Finland (290596, 314369, 318281); Ministry of Science and Higher Education of Russian Federation (0035-2019-0014)

PY - 2019/6/24

Y1 - 2019/6/24

N2 - We developed a compact, hand-held hyperspectral imaging system for 2D neural network-based visualization of skin chromophores and blood oxygenation. State-of-the-art micro-optic multichannel matrix sensor combined with the tunable Fabry-Perot micro interferometer enables a portable diagnostic device sensitive to the changes of the oxygen saturation as well as the variations of blood volume fraction of human skin. Generalized object-oriented Monte Carlo model is used extensively for the training of an artificial neural network utilized for the hyperspectral image processing. In addition, the results are verified and validated via actual experiments with tissue phantoms and human skin in vivo. The proposed approach enables a tool combining both the speed of an artificial neural network processing and the accuracy and flexibility of advanced Monte Carlo modeling. Finally, the results of the feasibility studies and the experimental tests on biotissue phantoms and healthy volunteers are presented.

AB - We developed a compact, hand-held hyperspectral imaging system for 2D neural network-based visualization of skin chromophores and blood oxygenation. State-of-the-art micro-optic multichannel matrix sensor combined with the tunable Fabry-Perot micro interferometer enables a portable diagnostic device sensitive to the changes of the oxygen saturation as well as the variations of blood volume fraction of human skin. Generalized object-oriented Monte Carlo model is used extensively for the training of an artificial neural network utilized for the hyperspectral image processing. In addition, the results are verified and validated via actual experiments with tissue phantoms and human skin in vivo. The proposed approach enables a tool combining both the speed of an artificial neural network processing and the accuracy and flexibility of advanced Monte Carlo modeling. Finally, the results of the feasibility studies and the experimental tests on biotissue phantoms and healthy volunteers are presented.

UR - http://www.scopus.com/inward/record.url?scp=85069871914&partnerID=8YFLogxK

U2 - 10.1364/BOE.10.003545

DO - 10.1364/BOE.10.003545

M3 - Article

AN - SCOPUS:85069871914

SN - 2156-7085

VL - 10

SP - 3545

EP - 3559

JO - Biomedical Optics Express

JF - Biomedical Optics Express

IS - 7

M1 - 364396

ER -

Hyperspectral imaging of human skin aided by artificial neural networks

Abstract

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this