Advanced

Diffuse Reflectance Spectroscopy: Using Multivariate analysis method for determination of tissue optical properties

Yavari, Hasti LU (2016) FYSM31 20161
Department of Physics
Atomic Physics
Abstract
Diffuse reflectance Spectroscopy is a non-invasive and real-time technique used both in research and clinical studies for purposes such as identifying tumors and monitoring their response to therapy. Here, a compact, cost-effective and portable experimental setup is used in order to acquire the diffuse reflectance spectra from tissue-like liquid phantoms.
Two fiber optic probes with different source-detector separations are used for collecting the diffuse light. A phantom preparation protocol is proposed in order to construct a data set of diffuse reflectance spectra from phantoms with different tissue chromophores compositions. Nonlinear least-squares support vector machines (LS-SVM) regression technique within the Multivariate analysis... (More)
Diffuse reflectance Spectroscopy is a non-invasive and real-time technique used both in research and clinical studies for purposes such as identifying tumors and monitoring their response to therapy. Here, a compact, cost-effective and portable experimental setup is used in order to acquire the diffuse reflectance spectra from tissue-like liquid phantoms.
Two fiber optic probes with different source-detector separations are used for collecting the diffuse light. A phantom preparation protocol is proposed in order to construct a data set of diffuse reflectance spectra from phantoms with different tissue chromophores compositions. Nonlinear least-squares support vector machines (LS-SVM) regression technique within the Multivariate analysis (MVA) framework is employed in order to extract the optical properties of the tissue-like phantoms. Validation measurements of the liquid phantoms demonstrate a higher prediction accuracy for larger number of training samples. Percentage error of <2% is observed when testing 1 sample in both reduced scattering coefficient and blood volume fraction models. The reduced scattering coefficient can be estimated with higher accuracy
in the models constructed with the data collected using both probes. Ways to improve the regression models’ performance are proposed along with suggestions for future work. (Less)
Popular Abstract
What makes us see different objects in a room is the light reflected from the objects’ surfaces. The reflected light from each particular object contains specific information that enables us to distinguish different objects from each other in a surrounding area. Think of this reflected light as the object’s fingerprint that contains unique information about its physical
properties. The technique used in this thesis, Diffuse reflectance spectroscopy, follows the same concept. Here, the light that is shined to a biological tissue (or a sample mimicking the tissue properties) travels to a certain distance inside the sample and reflects back. The reflected light is recorded and studied using a scientific method in order to extract optical
... (More)
What makes us see different objects in a room is the light reflected from the objects’ surfaces. The reflected light from each particular object contains specific information that enables us to distinguish different objects from each other in a surrounding area. Think of this reflected light as the object’s fingerprint that contains unique information about its physical
properties. The technique used in this thesis, Diffuse reflectance spectroscopy, follows the same concept. Here, the light that is shined to a biological tissue (or a sample mimicking the tissue properties) travels to a certain distance inside the sample and reflects back. The reflected light is recorded and studied using a scientific method in order to extract optical
information from the tissue. The tissue type or its health state are investigated; do cancerous cells exist and if yes, what are the tumor characteristics? The main advantage of the Diffuse reflectance spectroscopy technique is that there is no need for inserting the instruments into the body. In this work, the Multivariate analysis tool is used as the scientific method for extracting information from the reflected light. In Multivariate analysis technique, a tissue’s properties are identified by comparing the light reflected from it with a collection of other signals for tissues with known properties using mathematical algorithms. (Less)
Please use this url to cite or link to this publication:
author
Yavari, Hasti LU
supervisor
organization
course
FYSM31 20161
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Diffuse reflectance spectroscopy, Multivariate analysis, Least-squares support vector machines
language
English
id
8880115
date added to LUP
2016-06-20 13:55:36
date last changed
2016-06-20 13:55:36
@misc{8880115,
  abstract     = {Diffuse reflectance Spectroscopy is a non-invasive and real-time technique used both in research and clinical studies for purposes such as identifying tumors and monitoring their response to therapy. Here, a compact, cost-effective and portable experimental setup is used in order to acquire the diffuse reflectance spectra from tissue-like liquid phantoms.
Two fiber optic probes with different source-detector separations are used for collecting the diffuse light. A phantom preparation protocol is proposed in order to construct a data set of diffuse reflectance spectra from phantoms with different tissue chromophores compositions. Nonlinear least-squares support vector machines (LS-SVM) regression technique within the Multivariate analysis (MVA) framework is employed in order to extract the optical properties of the tissue-like phantoms. Validation measurements of the liquid phantoms demonstrate a higher prediction accuracy for larger number of training samples. Percentage error of <2% is observed when testing 1 sample in both reduced scattering coefficient and blood volume fraction models. The reduced scattering coefficient can be estimated with higher accuracy
in the models constructed with the data collected using both probes. Ways to improve the regression models’ performance are proposed along with suggestions for future work.},
  author       = {Yavari, Hasti},
  keyword      = {Diffuse reflectance spectroscopy,Multivariate analysis,Least-squares support vector machines},
  language     = {eng},
  note         = {Student Paper},
  title        = {Diffuse Reflectance Spectroscopy: Using Multivariate analysis method for determination of tissue optical properties},
  year         = {2016},
}