Presentation
9 March 2020 Machine learning estimations of tissue optical properties for a multi-layered model (Conference Presentation)
Author Affiliations +
Abstract
Here, we present a technique for inverting a Monte Carlo simulation to extract tissue optical properties from the moments of the spatio-temporal response of the tissue by training a 5-layer fully connected neural network. Initial reports of this model were used to extract optical properties from a single layer tissue model with high accuracy. Here, we expand this method to demonstrate its ability to extract optical properties from individual layers in a multi-layer model. We demonstrate the accuracy of the method across a very wide parameter space and demonstrate that the method is insensitive to parameter selection of the neural network model itself.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Joel N. Bixler and Brett Hokr "Machine learning estimations of tissue optical properties for a multi-layered model (Conference Presentation)", Proc. SPIE 11238, Optical Interactions with Tissue and Cells XXXI, 112380Q (9 March 2020); https://doi.org/10.1117/12.2546816
Advertisement
Advertisement
KEYWORDS
Optical properties

Tissue optics

Machine learning

Monte Carlo methods

Laser tissue interaction

Neural networks

Tissues

Back to Top