Application of RESNET50 Convolution Neural Network for the Extraction of Optical Parameters in Scattering Media

TL;DR

This paper demonstrates that a ResNet-50 convolutional neural network trained on simulated scattering data can accurately estimate optical properties of scattering media, improving efficiency and accuracy over previous methods.

Contribution

The study introduces a ResNet-50 based machine learning approach trained on simulated data for optical parameter extraction, achieving comparable or better accuracy with less data and multi-parameter training.

Findings

ResNet-50 achieves high accuracy in optical property estimation.

Training on multiple parameters improves reconstruction performance.

Limitations identified in absorption coefficient estimation.

Abstract

Estimation of the optical properties of scattering media such as tissue is important in diagnostics as well as in the development of techniques to image deeper. As light penetrates the sample scattering events occur that alter the propagation direction of the photons in a random manner leading degradation of image quality. The distribution of the scattered light does, however, give a measure of the optical properties such as the reduced scattering coefficient and the absorption coefficient. Unfortunately, inverting scattering patterns to recover the optical properties is not simple especially in the regime where the light is partially randomized. Machine learning has been proposed by several authors as a means of recovering these properties from either the back scattered or the transmitted light. In the present paper we train a general purpose convolutional neural network RESNET 50 with simulated data based on Monte Carlo simulations. We show that compared with previous work our approach gives comparable or better reconstruction accuracy with training on a much smaller dataset. Moreover, by training on multiple parameters such as the intensity distribution at multiple planes or the exit angle and spatial distribution one achieves improved performance compared to training on a single input such as the intensity distribution captured at the sample surface. While our approach gives good parameter reconstruction, we identify factors that limit accuracy of the recovered properties, particularly the absorption coefficient. In the light of these limitations, we suggest how the present approach may be enhanced for even better performance.