Hyperspecral skin imaging with artificial neural networks validated by optical biotissue phantoms

Alexander Bykov; Evgeny Zherebtsov; Viktor Dremin; Alexey Popov; Alexander Doronin; Igor Meglinski

doi:10.1364/COSI.2019.CW1A.3

Hyperspecral skin imaging with artificial neural networks validated by optical biotissue phantoms

Alexander Bykov^*
, Evgeny Zherebtsov
, Viktor Dremin
, Alexey Popov
, Alexander Doronin
, Igor Meglinski

^*Corresponding author for this work

Not published at VTT

University of Oulu
Victoria University of Wellington

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

State-of-the-art micro-optic multichannel matrix sensor combined with the tunable Fabry-Perot micro interferometer enables a compact diagnostic device sensitive to the changes of the oxygen saturation as well as the blood volume fraction of human skin. The possibility of using Monte-Carlo modelling for neural network training in the problem of hyperspectral image processing has been demonstrated and validated using biotissue phantom and human skin in vivo. The proposed approach enables a tool combining both the speed of neural network processing and the accuracy and flexibility of Monte-Carlo modelling.

Original language	English
Title of host publication	Computational Optical Sensing and Imaging
Subtitle of host publication	Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP)
Publisher	Optica Publishing Group
ISBN (Print)	978-1-943580-63-7
DOIs	https://doi.org/10.1364/COSI.2019.CW1A.3
Publication status	Published - 2019
MoE publication type	A4 Article in a conference publication
Event	Computational Optical Sensing and Imaging, COSI 2019 - Munich, Germany Duration: 24 Jun 2019 → 27 Jun 2019

Publication series

Series	Optics InfoBase Conference Papers
ISSN	2162-2701

Conference

Conference	Computational Optical Sensing and Imaging, COSI 2019
Country/Territory	Germany
City	Munich
Period	24/06/19 → 27/06/19

Funding

Authors acknowledge the support of the Academy of Finland (grants: 290596, 296408).

Access to Document

10.1364/COSI.2019.CW1A.3

http://urn.fi/urn:nbn:fi-fe2020110589358

Cite this

@inproceedings{e3ba5ab2ad864f59a614777e9d1eb1b6,

title = "Hyperspecral skin imaging with artificial neural networks validated by optical biotissue phantoms",

abstract = "State-of-the-art micro-optic multichannel matrix sensor combined with the tunable Fabry-Perot micro interferometer enables a compact diagnostic device sensitive to the changes of the oxygen saturation as well as the blood volume fraction of human skin. The possibility of using Monte-Carlo modelling for neural network training in the problem of hyperspectral image processing has been demonstrated and validated using biotissue phantom and human skin in vivo. The proposed approach enables a tool combining both the speed of neural network processing and the accuracy and flexibility of Monte-Carlo modelling.",

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

note = "Publisher Copyright: {\textcopyright} OSA 2019 {\textcopyright} 2019 The Author(s); Computational Optical Sensing and Imaging, COSI 2019 ; Conference date: 24-06-2019 Through 27-06-2019",

year = "2019",

doi = "10.1364/COSI.2019.CW1A.3",

language = "English",

isbn = "978-1-943580-63-7",

series = "Optics InfoBase Conference Papers",

publisher = "Optica Publishing Group",

booktitle = "Computational Optical Sensing and Imaging",

address = "United States",

}

Bykov, A, Zherebtsov, E, Dremin, V, Popov, A, Doronin, A & Meglinski, I 2019, Hyperspecral skin imaging with artificial neural networks validated by optical biotissue phantoms. in Computational Optical Sensing and Imaging: Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP)., CW1A.3, Optica Publishing Group, Optics InfoBase Conference Papers, Computational Optical Sensing and Imaging, COSI 2019, Munich, Germany, 24/06/19. https://doi.org/10.1364/COSI.2019.CW1A.3

Hyperspecral skin imaging with artificial neural networks validated by optical biotissue phantoms. / Bykov, Alexander; Zherebtsov, Evgeny; Dremin, Viktor et al.
Computational Optical Sensing and Imaging: Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP). Optica Publishing Group, 2019. CW1A.3 (Optics InfoBase Conference Papers).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Hyperspecral skin imaging with artificial neural networks validated by optical biotissue phantoms

AU - Bykov, Alexander

AU - Zherebtsov, Evgeny

AU - Dremin, Viktor

AU - Popov, Alexey

AU - Doronin, Alexander

AU - Meglinski, Igor

PY - 2019

Y1 - 2019

N2 - State-of-the-art micro-optic multichannel matrix sensor combined with the tunable Fabry-Perot micro interferometer enables a compact diagnostic device sensitive to the changes of the oxygen saturation as well as the blood volume fraction of human skin. The possibility of using Monte-Carlo modelling for neural network training in the problem of hyperspectral image processing has been demonstrated and validated using biotissue phantom and human skin in vivo. The proposed approach enables a tool combining both the speed of neural network processing and the accuracy and flexibility of Monte-Carlo modelling.

AB - State-of-the-art micro-optic multichannel matrix sensor combined with the tunable Fabry-Perot micro interferometer enables a compact diagnostic device sensitive to the changes of the oxygen saturation as well as the blood volume fraction of human skin. The possibility of using Monte-Carlo modelling for neural network training in the problem of hyperspectral image processing has been demonstrated and validated using biotissue phantom and human skin in vivo. The proposed approach enables a tool combining both the speed of neural network processing and the accuracy and flexibility of Monte-Carlo modelling.

UR - https://www.scopus.com/pages/publications/85089887089

U2 - 10.1364/COSI.2019.CW1A.3

DO - 10.1364/COSI.2019.CW1A.3

M3 - Conference article in proceedings

AN - SCOPUS:85089887089

SN - 978-1-943580-63-7

T3 - Optics InfoBase Conference Papers

BT - Computational Optical Sensing and Imaging

PB - Optica Publishing Group

T2 - Computational Optical Sensing and Imaging, COSI 2019

Y2 - 24 June 2019 through 27 June 2019

ER -

Bykov A, Zherebtsov E, Dremin V, Popov A, Doronin A, Meglinski I. Hyperspecral skin imaging with artificial neural networks validated by optical biotissue phantoms. In Computational Optical Sensing and Imaging: Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP). Optica Publishing Group. 2019. CW1A.3. (Optics InfoBase Conference Papers). doi: 10.1364/COSI.2019.CW1A.3

Hyperspecral skin imaging with artificial neural networks validated by optical biotissue phantoms

Abstract

Publication series

Conference

Funding

Access to Document

Other files and links

Fingerprint

Cite this