Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns

Abstract Fabricated tissue phantoms are instrumental in optical in-vitro investigations concerning cancer diagnosis, therapeutic applications, and drug efficacy tests. We present a simple non-invasive computational technique that, when coupled with experiments, has the potential for characterization...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Iman Hassaninia, Ramin Bostanabad, Wei Chen, Hooman Mohseni
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/116070acbdd242d2aaa6774572b2dfa2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:116070acbdd242d2aaa6774572b2dfa2
record_format	dspace
spelling	oai:doaj.org-article:116070acbdd242d2aaa6774572b2dfa22021-12-02T11:52:17ZCharacterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns10.1038/s41598-017-15601-42045-2322https://doaj.org/article/116070acbdd242d2aaa6774572b2dfa22017-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-15601-4https://doaj.org/toc/2045-2322Abstract Fabricated tissue phantoms are instrumental in optical in-vitro investigations concerning cancer diagnosis, therapeutic applications, and drug efficacy tests. We present a simple non-invasive computational technique that, when coupled with experiments, has the potential for characterization of a wide range of biological tissues. The fundamental idea of our approach is to find a supervised learner that links the scattering pattern of a turbid sample to its thickness and scattering parameters. Once found, this supervised learner is employed in an inverse optimization problem for estimating the scattering parameters of a sample given its thickness and scattering pattern. Multi-response Gaussian processes are used for the supervised learning task and a simple setup is introduced to obtain the scattering pattern of a tissue sample. To increase the predictive power of the supervised learner, the scattering patterns are filtered, enriched by a regressor, and finally characterized with two parameters, namely, transmitted power and scaled Gaussian width. We computationally illustrate that our approach achieves errors of roughly 5% in predicting the scattering properties of many biological tissues. Our method has the potential to facilitate the characterization of tissues and fabrication of phantoms used for diagnostic and therapeutic purposes over a wide range of optical spectrum.Iman HassaniniaRamin BostanabadWei ChenHooman MohseniNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-14 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Iman Hassaninia Ramin Bostanabad Wei Chen Hooman Mohseni Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns
description	Abstract Fabricated tissue phantoms are instrumental in optical in-vitro investigations concerning cancer diagnosis, therapeutic applications, and drug efficacy tests. We present a simple non-invasive computational technique that, when coupled with experiments, has the potential for characterization of a wide range of biological tissues. The fundamental idea of our approach is to find a supervised learner that links the scattering pattern of a turbid sample to its thickness and scattering parameters. Once found, this supervised learner is employed in an inverse optimization problem for estimating the scattering parameters of a sample given its thickness and scattering pattern. Multi-response Gaussian processes are used for the supervised learning task and a simple setup is introduced to obtain the scattering pattern of a tissue sample. To increase the predictive power of the supervised learner, the scattering patterns are filtered, enriched by a regressor, and finally characterized with two parameters, namely, transmitted power and scaled Gaussian width. We computationally illustrate that our approach achieves errors of roughly 5% in predicting the scattering properties of many biological tissues. Our method has the potential to facilitate the characterization of tissues and fabrication of phantoms used for diagnostic and therapeutic purposes over a wide range of optical spectrum.
format	article
author	Iman Hassaninia Ramin Bostanabad Wei Chen Hooman Mohseni
author_facet	Iman Hassaninia Ramin Bostanabad Wei Chen Hooman Mohseni
author_sort	Iman Hassaninia
title	Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns
title_short	Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns
title_full	Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns
title_fullStr	Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns
title_full_unstemmed	Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns
title_sort	characterization of the optical properties of turbid media by supervised learning of scattering patterns
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/116070acbdd242d2aaa6774572b2dfa2
work_keys_str_mv	AT imanhassaninia characterizationoftheopticalpropertiesofturbidmediabysupervisedlearningofscatteringpatterns AT raminbostanabad characterizationoftheopticalpropertiesofturbidmediabysupervisedlearningofscatteringpatterns AT weichen characterizationoftheopticalpropertiesofturbidmediabysupervisedlearningofscatteringpatterns AT hoomanmohseni characterizationoftheopticalpropertiesofturbidmediabysupervisedlearningofscatteringpatterns
_version_	1718395087808888832

Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns

Ejemplares similares