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.

Diffuse reflectance spectroscopy as a potential method for nonmelanoma skin cancer margin assessment

“…These results are all consistent with our previous study. [ 12 ] Note that the shape of DRS data in Figure 2 is slightly different between two clinical datasets due to differences in the instruments and heterogeneity in the patients, so some minor differences in parameter values between these two clinical datasets are expected.…”

“…We investigated whether our physiological MCLUT model based on DRS alone could be used for NMSC tumor margin assessment. We applied our physiological MCLUT model [11,12,15] to these two clinical DRS datasets to extract scattering parameters, melanin concentration, blood volume fraction, oxygen saturation and vessel radius. Using the extracted parameters, we then trained logistic regression classifiers to classify BCC vs normal and SCC vs normal with our training dataset and tested our models on our test dataset.…”

“…[ 10 ] Recently, our group used a physiological model, Monte Carlo look‐up table (MCLUT) model, to extract physiological parameters from the above clinical DRS data and achieved comparable classification results to that of classifiers trained on features extracted via PCA while offering greater flexibility for diagnosing skin cancer than a purely statistical analysis. [ 11, 12 ] However, no study has yet used independent clinical datasets to demonstrate the potential use of DRS for tumor margin assessment.…”

Skin Complications of Diabetes Mellitus Revealed by Polarized Hyperspectral Imaging and Machine Learning

“…Diffuse reflectance spectroscopy (DRS) has found its application in many areas of medicine [8], including endoscopic diagnosis of cancer [9], [10], cancer surgery [11], dermatology [12], etc. Analysis of the changes in the spectrum of diffuse reflectance of tissues can provide rich information about their physiological and morphological state.…”

Machine learning to extract physiological parameters from multispectral diffuse reflectance spectroscopy

“…Diffuse reflectance spectroscopy (DRS) is an optical technology that uses light to non-invasively measure optical properties of biological tissue and has applications in the diagnosis of several cancers such as breast, 1 colorectal, 2 cervical, 3,4 oral, 5,6 lung, 7 and skin. [8][9][10] DRS instruments typically use an optical fiber probe to emit light onto tissue, where the light is scattered and absorbed. The light is then collected back into the fiber and is sent into a spectrometer to return reflectance values to a computer.…”