Machine learning estimation of tissue optical properties

Abstract Dynamic, in vivo measurement of the optical properties of biological tissues is still an elusive and critically important problem. Here we develop a technique for inverting a Monte Carlo simulation to extract tissue optical properties from the statistical moments of the spatio-temporal resp...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Brett H. Hokr, Joel N. Bixler
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/cad84211eeee413db0d3df40825ec13e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:cad84211eeee413db0d3df40825ec13e
record_format dspace
spelling oai:doaj.org-article:cad84211eeee413db0d3df40825ec13e2021-12-02T17:04:35ZMachine learning estimation of tissue optical properties10.1038/s41598-021-85994-w2045-2322https://doaj.org/article/cad84211eeee413db0d3df40825ec13e2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85994-whttps://doaj.org/toc/2045-2322Abstract Dynamic, in vivo measurement of the optical properties of biological tissues is still an elusive and critically important problem. Here we develop a technique for inverting a Monte Carlo simulation to extract tissue optical properties from the statistical moments of the spatio-temporal response of the tissue by training a 5-layer fully connected neural network. We demonstrate the accuracy of the method across a very wide parameter space on a single homogeneous layer tissue model and demonstrate that the method is insensitive to parameter selection of the neural network model itself. Finally, we propose an experimental setup capable of measuring the required information in real time in an in vivo environment and demonstrate proof-of-concept level experimental results.Brett H. HokrJoel N. BixlerNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-7 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Brett H. Hokr
Joel N. Bixler
Machine learning estimation of tissue optical properties
description Abstract Dynamic, in vivo measurement of the optical properties of biological tissues is still an elusive and critically important problem. Here we develop a technique for inverting a Monte Carlo simulation to extract tissue optical properties from the statistical moments of the spatio-temporal response of the tissue by training a 5-layer fully connected neural network. We demonstrate the accuracy of the method across a very wide parameter space on a single homogeneous layer tissue model and demonstrate that the method is insensitive to parameter selection of the neural network model itself. Finally, we propose an experimental setup capable of measuring the required information in real time in an in vivo environment and demonstrate proof-of-concept level experimental results.
format article
author Brett H. Hokr
Joel N. Bixler
author_facet Brett H. Hokr
Joel N. Bixler
author_sort Brett H. Hokr
title Machine learning estimation of tissue optical properties
title_short Machine learning estimation of tissue optical properties
title_full Machine learning estimation of tissue optical properties
title_fullStr Machine learning estimation of tissue optical properties
title_full_unstemmed Machine learning estimation of tissue optical properties
title_sort machine learning estimation of tissue optical properties
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/cad84211eeee413db0d3df40825ec13e
work_keys_str_mv AT bretthhokr machinelearningestimationoftissueopticalproperties
AT joelnbixler machinelearningestimationoftissueopticalproperties
_version_ 1718381875855097856