Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning

Ekaterina O. Bryanskaya; Viktor V. Dremin; Valery V. Shupletsov; Alexey V. Kornaev; Mikhail Yu Kirillin; Anna V. Bakotina; Dmitry N. Panchenkov; Konstantin V. Podmasteryev; Viacheslav G. Artyushenko; Andrey V. Dunaev

doi:10.1002/jbio.202300138

Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning

Ekaterina O. Bryanskaya^*, Viktor V. Dremin, Valery V. Shupletsov, Alexey V. Kornaev, Mikhail Yu Kirillin, Anna V. Bakotina, Dmitry N. Panchenkov, Konstantin V. Podmasteryev, Viacheslav G. Artyushenko, Andrey V. Dunaev

^*Corresponding author for this work

Aston Institute of Photonic Technologies (AiPT)

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

Abstract

Maxillary sinus pathologies remain among the most common ENT diseases requiring timely diagnosis for successful treatment. Standard ENT inspection approaches indicate low sensitivity in detecting maxillary sinus pathologies. In this paper, we report on capabilities of digital diaphanoscopy combined with machine learning tools in the detection of such pathologies. We provide a comparative analysis of two machine learning approaches applied to digital diapahnoscopy data, namely, convolutional neural networks and linear discriminant analysis. The sensitivity and specificity values obtained for both employed approaches exceed the reported accuracy indicators for traditional screening diagnosis methods (such as nasal endoscopy or ultrasound), suggesting the prospects of their usage for screening maxillary sinuses alterations. The analysis of the obtained values showed that the linear discriminant analysis, being a simpler approach as compared to neural networks, allows one to detect the maxillary sinus pathologies with the sensitivity and specificity of 0.88 and 0.98, respectively.

Original language	English
Article number	e202300138
Journal	Journal of Biophotonics
Volume	16
Issue number	9
Early online date	5 Jun 2023
DOIs	https://doi.org/10.1002/jbio.202300138 https://doi.org/10.1002/JBIO.202300138
Publication status	Published - Sept 2023

Bibliographical note

Copyright © 2023 Wiley-VCH GmbH. This is the peer reviewed version of the following article: "Bryanskaya, E.O. et al. (2023) ‘Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning’, Journal of Biophotonics," which has been published in final form at https://doi.org/10.1002/jbio.202300138. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley’s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited.

Acknowledgements: This study was funded by RFBR according to the research project No. 20-32-90147 and by FASIE according to the project No. 353ГС1ЦТС10-D5/80270. Thanks to the volunteers and patients of the University Clinic of the Yevdokimov A.I. Moscow State University of Medicine and Dentistry (Moscow, Russia).

Keywords

convolutional neural networks
digital diaphanoscopy
linear discriminant analysis
maxillary sinuses
optical diagnostics

Access to Document

Bryanskaya Dremin at el_AAM_Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning
Copyright © 2023 Wiley-VCH GmbH. This is the peer reviewed version of the following article: "Bryanskaya, E.O. et al. (2023) ‘Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning’, Journal of Biophotonics," which has been published in final form at https://doi.org/10.1002/jbio.202300138. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archived Versions.
Accepted author manuscript, 1.15 MBLicence: CC BY-NC-ND 4.0

Cite this

Bryanskaya, E. O., Dremin, V. V., Shupletsov, V. V., Kornaev, A. V., Kirillin, M. Y., Bakotina, A. V., Panchenkov, D. N., Podmasteryev, K. V., Artyushenko, V. G., & Dunaev, A. V. (2023). Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning. Journal of Biophotonics, 16(9), Article e202300138. https://doi.org/10.1002/jbio.202300138, https://doi.org/10.1002/JBIO.202300138

@article{5639b8b9aad342f2a6fca998927b535c,

title = "Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning",

abstract = "Maxillary sinus pathologies remain among the most common ENT diseases requiring timely diagnosis for successful treatment. Standard ENT inspection approaches indicate low sensitivity in detecting maxillary sinus pathologies. In this paper, we report on capabilities of digital diaphanoscopy combined with machine learning tools in the detection of such pathologies. We provide a comparative analysis of two machine learning approaches applied to digital diapahnoscopy data, namely, convolutional neural networks and linear discriminant analysis. The sensitivity and specificity values obtained for both employed approaches exceed the reported accuracy indicators for traditional screening diagnosis methods (such as nasal endoscopy or ultrasound), suggesting the prospects of their usage for screening maxillary sinuses alterations. The analysis of the obtained values showed that the linear discriminant analysis, being a simpler approach as compared to neural networks, allows one to detect the maxillary sinus pathologies with the sensitivity and specificity of 0.88 and 0.98, respectively.",

keywords = "convolutional neural networks, digital diaphanoscopy, linear discriminant analysis, maxillary sinuses, optical diagnostics",

author = "Bryanskaya, {Ekaterina O.} and Dremin, {Viktor V.} and Shupletsov, {Valery V.} and Kornaev, {Alexey V.} and Kirillin, {Mikhail Yu} and Bakotina, {Anna V.} and Panchenkov, {Dmitry N.} and Podmasteryev, {Konstantin V.} and Artyushenko, {Viacheslav G.} and Dunaev, {Andrey V.}",

note = "Copyright {\textcopyright} 2023 Wiley-VCH GmbH. This is the peer reviewed version of the following article: {"}Bryanskaya, E.O. et al. (2023) {\textquoteleft}Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning{\textquoteright}, Journal of Biophotonics,{"} which has been published in final form at https://doi.org/10.1002/jbio.202300138. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley{\textquoteright}s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited. Acknowledgements: This study was funded by RFBR according to the research project No. 20-32-90147 and by FASIE according to the project No. 353ГС1ЦТС10-D5/80270. Thanks to the volunteers and patients of the University Clinic of the Yevdokimov A.I. Moscow State University of Medicine and Dentistry (Moscow, Russia).",

year = "2023",

month = sep,

doi = "10.1002/jbio.202300138",

language = "English",

volume = "16",

journal = "Journal of Biophotonics",

issn = "1864-063X",

publisher = "Wiley",

number = "9",

}

Bryanskaya, EO, Dremin, VV, Shupletsov, VV, Kornaev, AV, Kirillin, MY, Bakotina, AV, Panchenkov, DN, Podmasteryev, KV, Artyushenko, VG & Dunaev, AV 2023, 'Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning', Journal of Biophotonics, vol. 16, no. 9, e202300138. https://doi.org/10.1002/jbio.202300138, https://doi.org/10.1002/JBIO.202300138

TY - JOUR

T1 - Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning

AU - Bryanskaya, Ekaterina O.

AU - Dremin, Viktor V.

AU - Shupletsov, Valery V.

AU - Kornaev, Alexey V.

AU - Kirillin, Mikhail Yu

AU - Bakotina, Anna V.

AU - Panchenkov, Dmitry N.

AU - Podmasteryev, Konstantin V.

AU - Artyushenko, Viacheslav G.

AU - Dunaev, Andrey V.

N1 - Copyright © 2023 Wiley-VCH GmbH. This is the peer reviewed version of the following article: "Bryanskaya, E.O. et al. (2023) ‘Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning’, Journal of Biophotonics," which has been published in final form at https://doi.org/10.1002/jbio.202300138. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley’s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited. Acknowledgements: This study was funded by RFBR according to the research project No. 20-32-90147 and by FASIE according to the project No. 353ГС1ЦТС10-D5/80270. Thanks to the volunteers and patients of the University Clinic of the Yevdokimov A.I. Moscow State University of Medicine and Dentistry (Moscow, Russia).

PY - 2023/9

Y1 - 2023/9

N2 - Maxillary sinus pathologies remain among the most common ENT diseases requiring timely diagnosis for successful treatment. Standard ENT inspection approaches indicate low sensitivity in detecting maxillary sinus pathologies. In this paper, we report on capabilities of digital diaphanoscopy combined with machine learning tools in the detection of such pathologies. We provide a comparative analysis of two machine learning approaches applied to digital diapahnoscopy data, namely, convolutional neural networks and linear discriminant analysis. The sensitivity and specificity values obtained for both employed approaches exceed the reported accuracy indicators for traditional screening diagnosis methods (such as nasal endoscopy or ultrasound), suggesting the prospects of their usage for screening maxillary sinuses alterations. The analysis of the obtained values showed that the linear discriminant analysis, being a simpler approach as compared to neural networks, allows one to detect the maxillary sinus pathologies with the sensitivity and specificity of 0.88 and 0.98, respectively.

AB - Maxillary sinus pathologies remain among the most common ENT diseases requiring timely diagnosis for successful treatment. Standard ENT inspection approaches indicate low sensitivity in detecting maxillary sinus pathologies. In this paper, we report on capabilities of digital diaphanoscopy combined with machine learning tools in the detection of such pathologies. We provide a comparative analysis of two machine learning approaches applied to digital diapahnoscopy data, namely, convolutional neural networks and linear discriminant analysis. The sensitivity and specificity values obtained for both employed approaches exceed the reported accuracy indicators for traditional screening diagnosis methods (such as nasal endoscopy or ultrasound), suggesting the prospects of their usage for screening maxillary sinuses alterations. The analysis of the obtained values showed that the linear discriminant analysis, being a simpler approach as compared to neural networks, allows one to detect the maxillary sinus pathologies with the sensitivity and specificity of 0.88 and 0.98, respectively.

KW - convolutional neural networks

KW - digital diaphanoscopy

KW - linear discriminant analysis

KW - maxillary sinuses

KW - optical diagnostics

UR - https://onlinelibrary.wiley.com/doi/10.1002/jbio.202300138

UR - http://www.scopus.com/inward/record.url?scp=85162954623&partnerID=8YFLogxK

U2 - 10.1002/jbio.202300138

DO - 10.1002/jbio.202300138

M3 - Article

AN - SCOPUS:85162954623

SN - 1864-063X

VL - 16

JO - Journal of Biophotonics

JF - Journal of Biophotonics

IS - 9

M1 - e202300138

ER -

Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Erratum to Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning (J. Biophotonics, 10.1002/jbio.202300138)

Cite this