Advanced

Multivariate analysis of laryngeal fluorescence spectra recorded in vivo

Eker, Charlotta; Rydell, Roland LU ; Svanberg, Katarina LU and Andersson-Engels, Stefan LU (2001) In Lasers in Surgery and Medicine 28(3). p.259-266
Abstract
Background and Objective: The potential of using various multivariate analysis methods for classification of fluorescence spectra acquired in vivo from laryngeal tissues in Patients was investigated. Study Design/Materials and Methods: Autofluorescence spectra were measured on 29 normal tissue sites and 25 laryngeal lesions using 337-nm excitation. Four different multivariate analysis schemes were applied. Laryngeal fluorescence spectra from patients who had been administered F-aminolevulinic acid (ALA) were obtained using 405-nm excitation and were classified using partial least squares discriminant analysis (PLS-DA). Results: For autofluorescence spectra, logistic regression based on principal component analysis (PCA) or PLS, or PLS-DA... (More)
Background and Objective: The potential of using various multivariate analysis methods for classification of fluorescence spectra acquired in vivo from laryngeal tissues in Patients was investigated. Study Design/Materials and Methods: Autofluorescence spectra were measured on 29 normal tissue sites and 25 laryngeal lesions using 337-nm excitation. Four different multivariate analysis schemes were applied. Laryngeal fluorescence spectra from patients who had been administered F-aminolevulinic acid (ALA) were obtained using 405-nm excitation and were classified using partial least squares discriminant analysis (PLS-DA). Results: For autofluorescence spectra, logistic regression based on principal component analysis (PCA) or PLS, or PLS-DA all resulted in sensitivities and specificities around 90% for lesion vs. normal. Using ALA and 405-nm excitation gave a sensitivity of 100% and a specificity of 69%. Conclusion: Multivariate analysis of fluorescence spectra could allow classification of laryngeal lesions in vivo with high sensitivity and specificity. PLS performs at least as well as PCA, and PLS-DA performs as well as logistic regression techniques on these data. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
in vivo diagnosis, larynx, laser-induced fluorescence, partial least squares (PLS), spectroscopy, tissue characterization, multivariate analysis
in
Lasers in Surgery and Medicine
volume
28
issue
3
pages
259 - 266
publisher
John Wiley & Sons
external identifiers
  • wos:000167953500011
  • scopus:0035066557
ISSN
0196-8092
DOI
10.1002/lsm.1048
language
English
LU publication?
yes
id
6612df9d-d80e-488d-a4eb-d584143580ba (old id 1119318)
date added to LUP
2008-06-26 14:57:14
date last changed
2018-05-29 11:57:30
@article{6612df9d-d80e-488d-a4eb-d584143580ba,
  abstract     = {Background and Objective: The potential of using various multivariate analysis methods for classification of fluorescence spectra acquired in vivo from laryngeal tissues in Patients was investigated. Study Design/Materials and Methods: Autofluorescence spectra were measured on 29 normal tissue sites and 25 laryngeal lesions using 337-nm excitation. Four different multivariate analysis schemes were applied. Laryngeal fluorescence spectra from patients who had been administered F-aminolevulinic acid (ALA) were obtained using 405-nm excitation and were classified using partial least squares discriminant analysis (PLS-DA). Results: For autofluorescence spectra, logistic regression based on principal component analysis (PCA) or PLS, or PLS-DA all resulted in sensitivities and specificities around 90% for lesion vs. normal. Using ALA and 405-nm excitation gave a sensitivity of 100% and a specificity of 69%. Conclusion: Multivariate analysis of fluorescence spectra could allow classification of laryngeal lesions in vivo with high sensitivity and specificity. PLS performs at least as well as PCA, and PLS-DA performs as well as logistic regression techniques on these data.},
  author       = {Eker, Charlotta and Rydell, Roland and Svanberg, Katarina and Andersson-Engels, Stefan},
  issn         = {0196-8092},
  keyword      = {in vivo diagnosis,larynx,laser-induced fluorescence,partial least squares (PLS),spectroscopy,tissue characterization,multivariate analysis},
  language     = {eng},
  number       = {3},
  pages        = {259--266},
  publisher    = {John Wiley & Sons},
  series       = {Lasers in Surgery and Medicine},
  title        = {Multivariate analysis of laryngeal fluorescence spectra recorded in vivo},
  url          = {http://dx.doi.org/10.1002/lsm.1048},
  volume       = {28},
  year         = {2001},
}