Designing a use-error robust machine learning model for quantitative analysis of diffuse reflectance spectra

Abstract

Significance: Machine learning (ML)-enabled diffuse reflectance spectroscopy (DRS) is increasingly used as an alternative to the computation-intensive inverse Monte Carlo (MCI) simulation to predict tissue's optical properties, including the absorption coefficient, ${\mu }_a$ and reduced scattering coefficient, ${\mu }_s^{\text{'}}$.

Aim: We aim to develop a use-error-robust ML algorithm for optical property prediction from DRS spectra.

Approach: We developed a wavelength-independent regressor (WIR) to predict optical properties from DRS data. For validation, we generated 1520 simulated DRS spectra with the forward Monte Carlo model, where ${\mu }_a=0.44$ to $2.45{\mathrm{cm}}^{-1}$, and ${\mu }_s^{\text{'}}=6.53$ to $9.58{\mathrm{cm}}^{-1}$. We introduced common use-errors, such as wavelength miscalibrations and intensity fluctuations. Finally, we collected 882 experimental DRS images from 170 tissue-mimicking phantoms and compared performances of the WIR model, a dense neural network, and the MCI model.

Results: When compounding all use-errors on simulated data, the WIR model best balanced accuracy and speed, yielding errors of 1.75% for ${\mu }_a$ and 1.53% for ${\mu }_s^{\text{'}}$, compared to the MCI's 50.9% for ${\mu }_a$ and 24.6% for ${\mu }_s^{\text{'}}$. Regarding experimental data, WIR model had mean errors of 13.2% and 6.1% for ${\mu }_a$ and ${\mu }_s^{\text{'}}$, respectively. The errors for MCI were about eight times higher.

Conclusions: The WIR model presents reliable use-error-robust optical property predictions from DRS data.

Keywords: cancer detection; diffuse reflectance spectroscopy; machine learning; optical properties.