Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging

Omar B. Osman; Zachery B. Harris; Juin Wan Zhou; Mahmoud E. Khani; Andrew Chen; Adam J. Singer; M. Hassan Arbab

doi:10.1109/IRMMW-THz50926.2021.9567529

Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging

Omar B. Osman, Zachery B. Harris, Juin Wan Zhou, Mahmoud E. Khani, Andrew Chen, Adam J. Singer, M. Hassan Arbab

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Patients arrive in burn centers with many etiologies of burn incidence (such as scald, contact, flame, steam, etc.). Treatment of these injuries depends on the burn depth and surface area of these burns. Moreover, earlier diagnosis and treatment of these burns lead to better patient outcomes. In this study, we show that THz-TDS imaging with a neural network classification algorithm can reproducibly classify burns, independent of their etiology, with an ROC-AUC of 88% in a porcine model.

Original language	English
Title of host publication	2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021
Publisher	Institute of Electrical and Electronics Engineers
ISBN (Electronic)	9781728194240
DOIs	https://doi.org/10.1109/IRMMW-THz50926.2021.9567529
State	Published - 1 Jan 2021
Externally published	Yes
Event	46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021 - Chengdu, China Duration: 30 Aug 2021 → 3 Sep 2021

Publication series

Name	International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz
Volume	2021-August
ISSN (Print)	2162-2027
ISSN (Electronic)	2162-2035

Conference

Conference	46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021
Country/Territory	China
City	Chengdu
Period	30/08/21 → 3/09/21

ASJC Scopus subject areas

Energy Engineering and Power Technology
Electrical and Electronic Engineering

Access to Document

10.1109/IRMMW-THz50926.2021.9567529

Cite this

Osman, O. B., Harris, Z. B., Zhou, J. W., Khani, M. E., Chen, A., Singer, A. J., & Arbab, M. H. (2021). Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging. In 2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021 (International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz; Vol. 2021-August). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IRMMW-THz50926.2021.9567529

Osman, Omar B. ; Harris, Zachery B. ; Zhou, Juin Wan et al. / Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging. 2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021. Institute of Electrical and Electronics Engineers, 2021. (International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz).

@inproceedings{59f08e57f81b45a5bcbc4f632f789028,

title = "Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging",

abstract = "Patients arrive in burn centers with many etiologies of burn incidence (such as scald, contact, flame, steam, etc.). Treatment of these injuries depends on the burn depth and surface area of these burns. Moreover, earlier diagnosis and treatment of these burns lead to better patient outcomes. In this study, we show that THz-TDS imaging with a neural network classification algorithm can reproducibly classify burns, independent of their etiology, with an ROC-AUC of 88\% in a porcine model.",

author = "Osman, \{Omar B.\} and Harris, \{Zachery B.\} and Zhou, \{Juin Wan\} and Khani, \{Mahmoud E.\} and Andrew Chen and Singer, \{Adam J.\} and Arbab, \{M. Hassan\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021 ; Conference date: 30-08-2021 Through 03-09-2021",

year = "2021",

month = jan,

day = "1",

doi = "10.1109/IRMMW-THz50926.2021.9567529",

language = "English",

series = "International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz",

publisher = "Institute of Electrical and Electronics Engineers",

booktitle = "2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021",

address = "United States",

}

Osman, OB, Harris, ZB, Zhou, JW, Khani, ME, Chen, A, Singer, AJ & Arbab, MH 2021, Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging. in 2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021. International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz, vol. 2021-August, Institute of Electrical and Electronics Engineers, 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021, Chengdu, China, 30/08/21. https://doi.org/10.1109/IRMMW-THz50926.2021.9567529

Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging. / Osman, Omar B.; Harris, Zachery B.; Zhou, Juin Wan et al.
2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021. Institute of Electrical and Electronics Engineers, 2021. (International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz; Vol. 2021-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging

AU - Osman, Omar B.

AU - Harris, Zachery B.

AU - Zhou, Juin Wan

AU - Khani, Mahmoud E.

AU - Chen, Andrew

AU - Singer, Adam J.

AU - Arbab, M. Hassan

PY - 2021/1/1

Y1 - 2021/1/1

N2 - Patients arrive in burn centers with many etiologies of burn incidence (such as scald, contact, flame, steam, etc.). Treatment of these injuries depends on the burn depth and surface area of these burns. Moreover, earlier diagnosis and treatment of these burns lead to better patient outcomes. In this study, we show that THz-TDS imaging with a neural network classification algorithm can reproducibly classify burns, independent of their etiology, with an ROC-AUC of 88% in a porcine model.

AB - Patients arrive in burn centers with many etiologies of burn incidence (such as scald, contact, flame, steam, etc.). Treatment of these injuries depends on the burn depth and surface area of these burns. Moreover, earlier diagnosis and treatment of these burns lead to better patient outcomes. In this study, we show that THz-TDS imaging with a neural network classification algorithm can reproducibly classify burns, independent of their etiology, with an ROC-AUC of 88% in a porcine model.

UR - https://www.scopus.com/pages/publications/85125292948

U2 - 10.1109/IRMMW-THz50926.2021.9567529

DO - 10.1109/IRMMW-THz50926.2021.9567529

M3 - Conference contribution

AN - SCOPUS:85125292948

T3 - International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz

BT - 2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021

PB - Institute of Electrical and Electronics Engineers

T2 - 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021

Y2 - 30 August 2021 through 3 September 2021

ER -

Osman OB, Harris ZB, Zhou JW, Khani ME, Chen A, Singer AJ et al. Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging. In 2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021. Institute of Electrical and Electronics Engineers. 2021. (International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz). doi: 10.1109/IRMMW-THz50926.2021.9567529

Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this