Estimating physiological skin parameters from hyperspectral signatures

Saurabh Vyas, Amit Banerjee, Philippe Burlina

Research output: Contribution to journalArticle

Abstract

We describe an approach for estimating human skin parameters, such as melanosome concentration, collagen concentration, oxygen saturation, and blood volume, using hyperspectral radiometric measurements (signatures) obtained from in vivo skin. We use a computational model based on Kubelka-Munk theory and the Fresnel equations. This model forward maps the skin parameters to a corresponding multiband reflectance spectra. Machine-learning-based regression is used to generate the inverse map, and hence estimate skin parameters from hyperspectral signatures. We test our methods using synthetic and in vivo skin signatures obtained in the visible through the short wave infrared domains from 24 patients of both genders and Caucasian, Asian, and African American ethnicities. Performance validation shows promising results: good agreement with the ground truth and well-established physiological precepts. These methods have potential use in the characterization of skin abnormalities and in minimally-invasive prescreening of malignant skin cancers.

Original languageEnglish (US)
Article number057008
JournalJournal of Biomedical Optics
Volume18
Issue number5
DOIs
StatePublished - May 1 2013

Fingerprint

Skin
estimating
signatures
blood volume
machine learning
ground truth
abnormalities
collagens
regression analysis
cancer
saturation
reflectance
oxygen
estimates
Collagen
Learning systems
Blood
Oxygen
Infrared radiation

Keywords

  • hyperspectral signatures
  • inverse mapping
  • machine learning regression
  • skin parameters

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Biomedical Engineering

Cite this

Estimating physiological skin parameters from hyperspectral signatures. / Vyas, Saurabh; Banerjee, Amit; Burlina, Philippe.

In: Journal of Biomedical Optics, Vol. 18, No. 5, 057008, 01.05.2013.

Research output: Contribution to journalArticle

Vyas, Saurabh ; Banerjee, Amit ; Burlina, Philippe. / Estimating physiological skin parameters from hyperspectral signatures. In: Journal of Biomedical Optics. 2013 ; Vol. 18, No. 5.
@article{6d8384120bae4882815e79098c116293,
title = "Estimating physiological skin parameters from hyperspectral signatures",
abstract = "We describe an approach for estimating human skin parameters, such as melanosome concentration, collagen concentration, oxygen saturation, and blood volume, using hyperspectral radiometric measurements (signatures) obtained from in vivo skin. We use a computational model based on Kubelka-Munk theory and the Fresnel equations. This model forward maps the skin parameters to a corresponding multiband reflectance spectra. Machine-learning-based regression is used to generate the inverse map, and hence estimate skin parameters from hyperspectral signatures. We test our methods using synthetic and in vivo skin signatures obtained in the visible through the short wave infrared domains from 24 patients of both genders and Caucasian, Asian, and African American ethnicities. Performance validation shows promising results: good agreement with the ground truth and well-established physiological precepts. These methods have potential use in the characterization of skin abnormalities and in minimally-invasive prescreening of malignant skin cancers.",
keywords = "hyperspectral signatures, inverse mapping, machine learning regression, skin parameters",
author = "Saurabh Vyas and Amit Banerjee and Philippe Burlina",
year = "2013",
month = "5",
day = "1",
doi = "10.1117/1.JBO.18.5.057008",
language = "English (US)",
volume = "18",
journal = "Journal of Biomedical Optics",
issn = "1083-3668",
publisher = "SPIE",
number = "5",

}

TY - JOUR

T1 - Estimating physiological skin parameters from hyperspectral signatures

AU - Vyas, Saurabh

AU - Banerjee, Amit

AU - Burlina, Philippe

PY - 2013/5/1

Y1 - 2013/5/1

N2 - We describe an approach for estimating human skin parameters, such as melanosome concentration, collagen concentration, oxygen saturation, and blood volume, using hyperspectral radiometric measurements (signatures) obtained from in vivo skin. We use a computational model based on Kubelka-Munk theory and the Fresnel equations. This model forward maps the skin parameters to a corresponding multiband reflectance spectra. Machine-learning-based regression is used to generate the inverse map, and hence estimate skin parameters from hyperspectral signatures. We test our methods using synthetic and in vivo skin signatures obtained in the visible through the short wave infrared domains from 24 patients of both genders and Caucasian, Asian, and African American ethnicities. Performance validation shows promising results: good agreement with the ground truth and well-established physiological precepts. These methods have potential use in the characterization of skin abnormalities and in minimally-invasive prescreening of malignant skin cancers.

AB - We describe an approach for estimating human skin parameters, such as melanosome concentration, collagen concentration, oxygen saturation, and blood volume, using hyperspectral radiometric measurements (signatures) obtained from in vivo skin. We use a computational model based on Kubelka-Munk theory and the Fresnel equations. This model forward maps the skin parameters to a corresponding multiband reflectance spectra. Machine-learning-based regression is used to generate the inverse map, and hence estimate skin parameters from hyperspectral signatures. We test our methods using synthetic and in vivo skin signatures obtained in the visible through the short wave infrared domains from 24 patients of both genders and Caucasian, Asian, and African American ethnicities. Performance validation shows promising results: good agreement with the ground truth and well-established physiological precepts. These methods have potential use in the characterization of skin abnormalities and in minimally-invasive prescreening of malignant skin cancers.

KW - hyperspectral signatures

KW - inverse mapping

KW - machine learning regression

KW - skin parameters

UR - http://www.scopus.com/inward/record.url?scp=84886790294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886790294&partnerID=8YFLogxK

U2 - 10.1117/1.JBO.18.5.057008

DO - 10.1117/1.JBO.18.5.057008

M3 - Article

C2 - 23722495

AN - SCOPUS:84886790294

VL - 18

JO - Journal of Biomedical Optics

JF - Journal of Biomedical Optics

SN - 1083-3668

IS - 5

M1 - 057008

ER -