Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty

K. M. O'Brien, Arthur F Gmitro, G. R. Gindi, M. L. Stetz, F. W. Cutruzzola, L. I. Laifer, L. I. Deckelbaum

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Laser angioplasty, or the ablation of atherosclerotic plaque using laser energy, has tremendous potential to expand the scope of nonsurgical treatment of obstructive vascular disease. Clinical laser angioplasty, however, has been hindered by an unacceptable risk of vessel perforation. Laser-induced fluorescence spectroscopy can discriminate atherosclerotic from normal artery and may therefore be capable of guiding selective plaque ablation. To assess the feasibility of utilizing spectral information to discriminate arterial tissue type, several classification algorithms were developed and evaluated. Arterial fluorescence spectra from 350 to 700 nm were obtained from 100 human aortic specimens. Seven spectral classification algorithms were developed with the following techniques: multivariate linear regression, stepwise multivariate linear regression, principal components analysis, decision plane analysis, Bayes decision theory, principal peak ratio, and spectral width. The classification ability of each algorithm was evaluated by its application to the training set and to a validation set containing 82 additional spectra. All seven spectral classification algorithms prospectively classified atherosclerotic and normal aorta with an accuracy greater than 80 percent (range: 82-96 percent). Laser angioplasty systems incorporating spectral classification algorithms may therefore be capable of detection and selective ablation of atherosclerotic plaque.

Original languageEnglish (US)
Pages (from-to)424-431
Number of pages8
JournalIEEE Transactions on Biomedical Engineering
Volume36
Issue number4
StatePublished - 1989

Fingerprint

Fluorescence
Ablation
Lasers
Linear regression
Decision theory
Fluorescence spectroscopy
Principal component analysis
Tissue

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

O'Brien, K. M., Gmitro, A. F., Gindi, G. R., Stetz, M. L., Cutruzzola, F. W., Laifer, L. I., & Deckelbaum, L. I. (1989). Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty. IEEE Transactions on Biomedical Engineering, 36(4), 424-431.

Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty. / O'Brien, K. M.; Gmitro, Arthur F; Gindi, G. R.; Stetz, M. L.; Cutruzzola, F. W.; Laifer, L. I.; Deckelbaum, L. I.

In: IEEE Transactions on Biomedical Engineering, Vol. 36, No. 4, 1989, p. 424-431.

Research output: Contribution to journalArticle

O'Brien, KM, Gmitro, AF, Gindi, GR, Stetz, ML, Cutruzzola, FW, Laifer, LI & Deckelbaum, LI 1989, 'Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty', IEEE Transactions on Biomedical Engineering, vol. 36, no. 4, pp. 424-431.
O'Brien, K. M. ; Gmitro, Arthur F ; Gindi, G. R. ; Stetz, M. L. ; Cutruzzola, F. W. ; Laifer, L. I. ; Deckelbaum, L. I. / Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty. In: IEEE Transactions on Biomedical Engineering. 1989 ; Vol. 36, No. 4. pp. 424-431.
@article{0104cdd63bfd4e38ac10cf23cbf190a3,
title = "Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty",
abstract = "Laser angioplasty, or the ablation of atherosclerotic plaque using laser energy, has tremendous potential to expand the scope of nonsurgical treatment of obstructive vascular disease. Clinical laser angioplasty, however, has been hindered by an unacceptable risk of vessel perforation. Laser-induced fluorescence spectroscopy can discriminate atherosclerotic from normal artery and may therefore be capable of guiding selective plaque ablation. To assess the feasibility of utilizing spectral information to discriminate arterial tissue type, several classification algorithms were developed and evaluated. Arterial fluorescence spectra from 350 to 700 nm were obtained from 100 human aortic specimens. Seven spectral classification algorithms were developed with the following techniques: multivariate linear regression, stepwise multivariate linear regression, principal components analysis, decision plane analysis, Bayes decision theory, principal peak ratio, and spectral width. The classification ability of each algorithm was evaluated by its application to the training set and to a validation set containing 82 additional spectra. All seven spectral classification algorithms prospectively classified atherosclerotic and normal aorta with an accuracy greater than 80 percent (range: 82-96 percent). Laser angioplasty systems incorporating spectral classification algorithms may therefore be capable of detection and selective ablation of atherosclerotic plaque.",
author = "O'Brien, {K. M.} and Gmitro, {Arthur F} and Gindi, {G. R.} and Stetz, {M. L.} and Cutruzzola, {F. W.} and Laifer, {L. I.} and Deckelbaum, {L. I.}",
year = "1989",
language = "English (US)",
volume = "36",
pages = "424--431",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "4",

}

TY - JOUR

T1 - Development and evaluation of spectral classification algorithms for fluorescence guided laser angioplasty

AU - O'Brien, K. M.

AU - Gmitro, Arthur F

AU - Gindi, G. R.

AU - Stetz, M. L.

AU - Cutruzzola, F. W.

AU - Laifer, L. I.

AU - Deckelbaum, L. I.

PY - 1989

Y1 - 1989

N2 - Laser angioplasty, or the ablation of atherosclerotic plaque using laser energy, has tremendous potential to expand the scope of nonsurgical treatment of obstructive vascular disease. Clinical laser angioplasty, however, has been hindered by an unacceptable risk of vessel perforation. Laser-induced fluorescence spectroscopy can discriminate atherosclerotic from normal artery and may therefore be capable of guiding selective plaque ablation. To assess the feasibility of utilizing spectral information to discriminate arterial tissue type, several classification algorithms were developed and evaluated. Arterial fluorescence spectra from 350 to 700 nm were obtained from 100 human aortic specimens. Seven spectral classification algorithms were developed with the following techniques: multivariate linear regression, stepwise multivariate linear regression, principal components analysis, decision plane analysis, Bayes decision theory, principal peak ratio, and spectral width. The classification ability of each algorithm was evaluated by its application to the training set and to a validation set containing 82 additional spectra. All seven spectral classification algorithms prospectively classified atherosclerotic and normal aorta with an accuracy greater than 80 percent (range: 82-96 percent). Laser angioplasty systems incorporating spectral classification algorithms may therefore be capable of detection and selective ablation of atherosclerotic plaque.

AB - Laser angioplasty, or the ablation of atherosclerotic plaque using laser energy, has tremendous potential to expand the scope of nonsurgical treatment of obstructive vascular disease. Clinical laser angioplasty, however, has been hindered by an unacceptable risk of vessel perforation. Laser-induced fluorescence spectroscopy can discriminate atherosclerotic from normal artery and may therefore be capable of guiding selective plaque ablation. To assess the feasibility of utilizing spectral information to discriminate arterial tissue type, several classification algorithms were developed and evaluated. Arterial fluorescence spectra from 350 to 700 nm were obtained from 100 human aortic specimens. Seven spectral classification algorithms were developed with the following techniques: multivariate linear regression, stepwise multivariate linear regression, principal components analysis, decision plane analysis, Bayes decision theory, principal peak ratio, and spectral width. The classification ability of each algorithm was evaluated by its application to the training set and to a validation set containing 82 additional spectra. All seven spectral classification algorithms prospectively classified atherosclerotic and normal aorta with an accuracy greater than 80 percent (range: 82-96 percent). Laser angioplasty systems incorporating spectral classification algorithms may therefore be capable of detection and selective ablation of atherosclerotic plaque.

UR - http://www.scopus.com/inward/record.url?scp=0024475888&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024475888&partnerID=8YFLogxK

M3 - Article

C2 - 2714821

AN - SCOPUS:0024475888

VL - 36

SP - 424

EP - 431

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 4

ER -