The Potential of the Double Debye Parameters to Discriminate between Basal Cell Carcinoma and Normal Skin

Bao C Q Truong, Hoang Duong Tuan, Vincent P. Wallace, Anthony J. Fitzgerald, Hung T. Nguyen

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The potential of terahertz imaging for improving the efficiency of Mohs's micrographic surgery in terms of tumor margin detection was previously studied. Thanks to high water content of human skin, its dielectric response to terahertz radiation can be described by the double Debye model which uses five parameters to fit experimental data. Skin tumors typically have a higher water content than normal tissues do, and this should be apparent in the parameters. The goal of this paper is to apply statistical methods to these parameters to test their power to differentiate skin cancer from normal tissue. Based on the prediction accuracy estimated using a cross-validation method, we found the best classifier was the static permittivity at low frequency (εs). By combining the most relevant parameters, we obtained a classification accuracy of 95.7%, confirming the classification capability of the parameters, thereby supporting their application to improve terahertz imaging for the purpose of skin cancer delineation.

Original languageEnglish
Article number7302086
Pages (from-to)990-998
Number of pages9
JournalIEEE Transactions on Terahertz Science and Technology
Volume5
Issue number6
Early online date26 Oct 2015
DOIs
Publication statusPublished - 1 Nov 2015

Fingerprint

Skin
cancer
Cells
Water content
Tumors
moisture content
Tissue
Imaging techniques
tumors
delineation
Surgery
Statistical methods
classifiers
Classifiers
Permittivity
surgery
margins
Radiation
permittivity
low frequencies

Cite this

@article{513b4b6910c64bc49672422969ca4f33,
title = "The Potential of the Double Debye Parameters to Discriminate between Basal Cell Carcinoma and Normal Skin",
abstract = "The potential of terahertz imaging for improving the efficiency of Mohs's micrographic surgery in terms of tumor margin detection was previously studied. Thanks to high water content of human skin, its dielectric response to terahertz radiation can be described by the double Debye model which uses five parameters to fit experimental data. Skin tumors typically have a higher water content than normal tissues do, and this should be apparent in the parameters. The goal of this paper is to apply statistical methods to these parameters to test their power to differentiate skin cancer from normal tissue. Based on the prediction accuracy estimated using a cross-validation method, we found the best classifier was the static permittivity at low frequency (εs). By combining the most relevant parameters, we obtained a classification accuracy of 95.7{\%}, confirming the classification capability of the parameters, thereby supporting their application to improve terahertz imaging for the purpose of skin cancer delineation.",
keywords = "Classification, dielectric properties, optimization, statistical analysis, support vector machine, terahertz (THz)",
author = "Truong, {Bao C Q} and Tuan, {Hoang Duong} and Wallace, {Vincent P.} and Fitzgerald, {Anthony J.} and Nguyen, {Hung T.}",
year = "2015",
month = "11",
day = "1",
doi = "10.1109/TTHZ.2015.2485208",
language = "English",
volume = "5",
pages = "990--998",
journal = "IEEE Transactions on Terahertz Science and Technology",
issn = "2156-3446",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
number = "6",

}

The Potential of the Double Debye Parameters to Discriminate between Basal Cell Carcinoma and Normal Skin. / Truong, Bao C Q; Tuan, Hoang Duong; Wallace, Vincent P.; Fitzgerald, Anthony J.; Nguyen, Hung T.

In: IEEE Transactions on Terahertz Science and Technology, Vol. 5, No. 6, 7302086, 01.11.2015, p. 990-998.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The Potential of the Double Debye Parameters to Discriminate between Basal Cell Carcinoma and Normal Skin

AU - Truong, Bao C Q

AU - Tuan, Hoang Duong

AU - Wallace, Vincent P.

AU - Fitzgerald, Anthony J.

AU - Nguyen, Hung T.

PY - 2015/11/1

Y1 - 2015/11/1

N2 - The potential of terahertz imaging for improving the efficiency of Mohs's micrographic surgery in terms of tumor margin detection was previously studied. Thanks to high water content of human skin, its dielectric response to terahertz radiation can be described by the double Debye model which uses five parameters to fit experimental data. Skin tumors typically have a higher water content than normal tissues do, and this should be apparent in the parameters. The goal of this paper is to apply statistical methods to these parameters to test their power to differentiate skin cancer from normal tissue. Based on the prediction accuracy estimated using a cross-validation method, we found the best classifier was the static permittivity at low frequency (εs). By combining the most relevant parameters, we obtained a classification accuracy of 95.7%, confirming the classification capability of the parameters, thereby supporting their application to improve terahertz imaging for the purpose of skin cancer delineation.

AB - The potential of terahertz imaging for improving the efficiency of Mohs's micrographic surgery in terms of tumor margin detection was previously studied. Thanks to high water content of human skin, its dielectric response to terahertz radiation can be described by the double Debye model which uses five parameters to fit experimental data. Skin tumors typically have a higher water content than normal tissues do, and this should be apparent in the parameters. The goal of this paper is to apply statistical methods to these parameters to test their power to differentiate skin cancer from normal tissue. Based on the prediction accuracy estimated using a cross-validation method, we found the best classifier was the static permittivity at low frequency (εs). By combining the most relevant parameters, we obtained a classification accuracy of 95.7%, confirming the classification capability of the parameters, thereby supporting their application to improve terahertz imaging for the purpose of skin cancer delineation.

KW - Classification

KW - dielectric properties

KW - optimization

KW - statistical analysis

KW - support vector machine

KW - terahertz (THz)

UR - http://www.scopus.com/inward/record.url?scp=84960492382&partnerID=8YFLogxK

U2 - 10.1109/TTHZ.2015.2485208

DO - 10.1109/TTHZ.2015.2485208

M3 - Article

VL - 5

SP - 990

EP - 998

JO - IEEE Transactions on Terahertz Science and Technology

JF - IEEE Transactions on Terahertz Science and Technology

SN - 2156-3446

IS - 6

M1 - 7302086

ER -