Physiological model using diffuse reflectance spectroscopy for nonmelanoma skin cancer diagnosis

Yao Zhang, Austin J. Moy, Xu Feng, Hieu T.M. Nguyen, Jason S. Reichenberg, Mia K. Markey, James W. Tunnell

Research output: Contribution to journalArticle

Abstract

Diffuse reflectance spectroscopy (DRS) is a noninvasive, fast, and low-cost technology with potential to assist cancer diagnosis. The goal of this study was to test the capability of our physiological model, a computational Monte Carlo lookup table inverse model, for nonmelanoma skin cancer diagnosis. We applied this model on a clinical DRS dataset to extract scattering parameters, blood volume fraction, oxygen saturation and vessel radius. We found that the model was able to capture physiological information relevant to skin cancer. We used the extracted parameters to classify (basal cell carcinoma [BCC], squamous cell carcinoma [SCC]) vs actinic keratosis (AK) and (BCC, SCC, AK) vs normal. The area under the receiver operating characteristic curve achieved by the classifiers trained on the parameters extracted using the physiological model is comparable to that of classifiers trained on features extracted via Principal Component Analysis. Our findings suggest that DRS can reveal physiologic characteristics of skin and this physiologic model offers greater flexibility for diagnosing skin cancer than a pure statistical analysis. Physiological parameters extracted from diffuse reflectance spectra data for nonmelanoma skin cancer diagnosis.

Original languageEnglish (US)
Article numbere201900154
JournalJournal of Biophotonics
Volume12
Issue number12
DOIs
StatePublished - Dec 1 2019

Fingerprint

Physiological models
Skin Neoplasms
Spectrum Analysis
Skin
cancer
Spectroscopy
Actinic Keratosis
reflectance
Basal Cell Carcinoma
spectroscopy
Squamous Cell Carcinoma
Classifiers
Principal Component Analysis
Blood Volume
Table lookup
ROC Curve
classifiers
Scattering parameters
Principal component analysis
Oxygen

Keywords

  • Monte Carlo look-up table model
  • classification
  • diffuse reflectance spectroscopy
  • physiological basis
  • skin cancer

ASJC Scopus subject areas

  • Chemistry(all)
  • Materials Science(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Engineering(all)
  • Physics and Astronomy(all)

Cite this

Physiological model using diffuse reflectance spectroscopy for nonmelanoma skin cancer diagnosis. / Zhang, Yao; Moy, Austin J.; Feng, Xu; Nguyen, Hieu T.M.; Reichenberg, Jason S.; Markey, Mia K.; Tunnell, James W.

In: Journal of Biophotonics, Vol. 12, No. 12, e201900154, 01.12.2019.

Research output: Contribution to journalArticle

@article{9e8001b7eb414d2ba0db97a25bd570af,
title = "Physiological model using diffuse reflectance spectroscopy for nonmelanoma skin cancer diagnosis",
abstract = "Diffuse reflectance spectroscopy (DRS) is a noninvasive, fast, and low-cost technology with potential to assist cancer diagnosis. The goal of this study was to test the capability of our physiological model, a computational Monte Carlo lookup table inverse model, for nonmelanoma skin cancer diagnosis. We applied this model on a clinical DRS dataset to extract scattering parameters, blood volume fraction, oxygen saturation and vessel radius. We found that the model was able to capture physiological information relevant to skin cancer. We used the extracted parameters to classify (basal cell carcinoma [BCC], squamous cell carcinoma [SCC]) vs actinic keratosis (AK) and (BCC, SCC, AK) vs normal. The area under the receiver operating characteristic curve achieved by the classifiers trained on the parameters extracted using the physiological model is comparable to that of classifiers trained on features extracted via Principal Component Analysis. Our findings suggest that DRS can reveal physiologic characteristics of skin and this physiologic model offers greater flexibility for diagnosing skin cancer than a pure statistical analysis. Physiological parameters extracted from diffuse reflectance spectra data for nonmelanoma skin cancer diagnosis.",
keywords = "Monte Carlo look-up table model, classification, diffuse reflectance spectroscopy, physiological basis, skin cancer",
author = "Yao Zhang and Moy, {Austin J.} and Xu Feng and Nguyen, {Hieu T.M.} and Reichenberg, {Jason S.} and Markey, {Mia K.} and Tunnell, {James W.}",
year = "2019",
month = "12",
day = "1",
doi = "10.1002/jbio.201900154",
language = "English (US)",
volume = "12",
journal = "Journal of Biophotonics",
issn = "1864-063X",
publisher = "Wiley-VCH Verlag",
number = "12",

}

TY - JOUR

T1 - Physiological model using diffuse reflectance spectroscopy for nonmelanoma skin cancer diagnosis

AU - Zhang, Yao

AU - Moy, Austin J.

AU - Feng, Xu

AU - Nguyen, Hieu T.M.

AU - Reichenberg, Jason S.

AU - Markey, Mia K.

AU - Tunnell, James W.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Diffuse reflectance spectroscopy (DRS) is a noninvasive, fast, and low-cost technology with potential to assist cancer diagnosis. The goal of this study was to test the capability of our physiological model, a computational Monte Carlo lookup table inverse model, for nonmelanoma skin cancer diagnosis. We applied this model on a clinical DRS dataset to extract scattering parameters, blood volume fraction, oxygen saturation and vessel radius. We found that the model was able to capture physiological information relevant to skin cancer. We used the extracted parameters to classify (basal cell carcinoma [BCC], squamous cell carcinoma [SCC]) vs actinic keratosis (AK) and (BCC, SCC, AK) vs normal. The area under the receiver operating characteristic curve achieved by the classifiers trained on the parameters extracted using the physiological model is comparable to that of classifiers trained on features extracted via Principal Component Analysis. Our findings suggest that DRS can reveal physiologic characteristics of skin and this physiologic model offers greater flexibility for diagnosing skin cancer than a pure statistical analysis. Physiological parameters extracted from diffuse reflectance spectra data for nonmelanoma skin cancer diagnosis.

AB - Diffuse reflectance spectroscopy (DRS) is a noninvasive, fast, and low-cost technology with potential to assist cancer diagnosis. The goal of this study was to test the capability of our physiological model, a computational Monte Carlo lookup table inverse model, for nonmelanoma skin cancer diagnosis. We applied this model on a clinical DRS dataset to extract scattering parameters, blood volume fraction, oxygen saturation and vessel radius. We found that the model was able to capture physiological information relevant to skin cancer. We used the extracted parameters to classify (basal cell carcinoma [BCC], squamous cell carcinoma [SCC]) vs actinic keratosis (AK) and (BCC, SCC, AK) vs normal. The area under the receiver operating characteristic curve achieved by the classifiers trained on the parameters extracted using the physiological model is comparable to that of classifiers trained on features extracted via Principal Component Analysis. Our findings suggest that DRS can reveal physiologic characteristics of skin and this physiologic model offers greater flexibility for diagnosing skin cancer than a pure statistical analysis. Physiological parameters extracted from diffuse reflectance spectra data for nonmelanoma skin cancer diagnosis.

KW - Monte Carlo look-up table model

KW - classification

KW - diffuse reflectance spectroscopy

KW - physiological basis

KW - skin cancer

UR - http://www.scopus.com/inward/record.url?scp=85071611192&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071611192&partnerID=8YFLogxK

U2 - 10.1002/jbio.201900154

DO - 10.1002/jbio.201900154

M3 - Article

AN - SCOPUS:85071611192

VL - 12

JO - Journal of Biophotonics

JF - Journal of Biophotonics

SN - 1864-063X

IS - 12

M1 - e201900154

ER -