Designing a Use-Error Robust Machine Learning Model for Quantitative Analysis of Diffuse Reflectance Spectra

Document Type

Article

Publication Date

1-2024

Publisher

Society of Photo-optical Instrumentation Engineers (SPIE)

Source Publication

Journal of Biomedical Optics

Source ISSN

1083-3668

Original Item ID

DOI: 10.1117/1.JBO.29.1.015001

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,μaand reduced scattering coefficient,μs′.

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, whereμa=0.44to2.45cm−1, andμs′=6.53to9.58cm−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% forμaand 1.53% forμs′, compared to the MCI’s 50.9% forμaand 24.6% forμs′. Regarding experimental data, WIR model had mean errors of 13.2% and 6.1% forμaandμs′, 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.

Comments

Journal of Biomedical Optics, Vol. 29, No. 1 (January 2024). DOI.

Link to Full Text

Share

COinS