Melanoma detection and characterization with a 6-layered multispectral model

Hyun Keol Kim, Natalie Tucker, Frank Debernardis, Andreas H. Hielscher

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We present here a retrospective clinical study on the detection of melanoma with a dedicated multispectral imaging system (MelaFind) that generates images of skin reflectance at 10 different wavelengths in the visible and near infrared range. The reflectance data was collected for 3609 skin lesions and analyzed with a multispectral image reconstruction algorithm that retrieves a multitude of skin parameters from multispectral data. The 6-layered skin model is used here to mimic the skin structure and the equation of radiative equation (ERT) as a light propagation model, which leads to a layered-dependent distribution of skin parameters: melanin content, blood volume fraction, and oxygen saturation (StO2). These reconstructed skin parameters are further analyzed with feature extraction and classification to evaluate the performance of the MelaFind system in terms of diagnostic accuracy. The results show that the depth-resolved skin parameters improve diagnostic accuracy with increased statistical significance (p-value).

Original languageEnglish (US)
Title of host publicationClinical and Translational Biophotonics, Translational 2016
PublisherOptica Publishing Group (formerly OSA)
ISBN (Print)9781943580101
StatePublished - Apr 18 2016
EventClinical and Translational Biophotonics, Translational 2016 - Fort Lauderdale, United States
Duration: Apr 25 2016Apr 28 2016

Publication series

NameOptics InfoBase Conference Papers
ISSN (Electronic)2162-2701


ConferenceClinical and Translational Biophotonics, Translational 2016
Country/TerritoryUnited States
CityFort Lauderdale

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Mechanics of Materials


Dive into the research topics of 'Melanoma detection and characterization with a 6-layered multispectral model'. Together they form a unique fingerprint.

Cite this