37 Citations (Scopus)

Abstract

Pulsed laser-induced autofluorescence spectroscopic studies of pathologically certified normal, premalignant, and malignant oral tissues were carried out at 325 nm excitation. The spectral analysis and classification for discrimination among normal, premalignant, and malignant conditions were performed using principal component analysis (PCA) and artificial neural network (ANN) separately on the same set of spectral data. In case of PCA, spectral residuals, Mahalanobis distance, and scores of factors were used for discrimination among normal, premalignant, and malignant cases. In ANN, parameters like mean, spectral residual, standard deviation, and total energy were used to train the network. The ANN used in this study is a classical multiplayer feed-forward type with a back-propagation algorithm for the training of the network. The specificity and sensitivity were determined in both classification schemes. In the case of PCA, they are 100 and 92.9%, respectively, whereas for ANN they are 100 and 96.5% for the data set considered.

Original languageEnglish
Pages (from-to)152-166
Number of pages15
JournalBiopolymers
Volume82
Issue number2
DOIs
Publication statusPublished - 05-06-2006

Fingerprint

Electric network analysis
Principal Component Analysis
Principal component analysis
Fluorescence
Tissue
Neural networks
Backpropagation algorithms
Lasers
Pulsed lasers
Spectrum analysis
Sensitivity and Specificity
Datasets

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Biochemistry
  • Biomaterials
  • Organic Chemistry

Cite this

@article{3d2c844ff7f74f4e9a44e813531312bf,
title = "Principal component analysis and artificial neural network analysis of oral tissue fluorescence spectra: Classification of normal premalignant and malignant pathological conditions",
abstract = "Pulsed laser-induced autofluorescence spectroscopic studies of pathologically certified normal, premalignant, and malignant oral tissues were carried out at 325 nm excitation. The spectral analysis and classification for discrimination among normal, premalignant, and malignant conditions were performed using principal component analysis (PCA) and artificial neural network (ANN) separately on the same set of spectral data. In case of PCA, spectral residuals, Mahalanobis distance, and scores of factors were used for discrimination among normal, premalignant, and malignant cases. In ANN, parameters like mean, spectral residual, standard deviation, and total energy were used to train the network. The ANN used in this study is a classical multiplayer feed-forward type with a back-propagation algorithm for the training of the network. The specificity and sensitivity were determined in both classification schemes. In the case of PCA, they are 100 and 92.9{\%}, respectively, whereas for ANN they are 100 and 96.5{\%} for the data set considered.",
author = "Nayak, {G. S.} and Sudha Kamath and Pai, {Keerthilatha M.} and Arindam Sarkar and Satadru Ray and Jacob Kurien and Lawrence D'Almeida and Krishnanand, {B. R.} and C. Santhosh and Kartha, {V. B.} and Mahato, {K. K.}",
year = "2006",
month = "6",
day = "5",
doi = "10.1002/bip.20473",
language = "English",
volume = "82",
pages = "152--166",
journal = "Biopolymers",
issn = "0006-3525",
publisher = "John Wiley and Sons Inc.",
number = "2",

}

Principal component analysis and artificial neural network analysis of oral tissue fluorescence spectra : Classification of normal premalignant and malignant pathological conditions. / Nayak, G. S.; Kamath, Sudha; Pai, Keerthilatha M.; Sarkar, Arindam; Ray, Satadru; Kurien, Jacob; D'Almeida, Lawrence; Krishnanand, B. R.; Santhosh, C.; Kartha, V. B.; Mahato, K. K.

In: Biopolymers, Vol. 82, No. 2, 05.06.2006, p. 152-166.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Principal component analysis and artificial neural network analysis of oral tissue fluorescence spectra

T2 - Classification of normal premalignant and malignant pathological conditions

AU - Nayak, G. S.

AU - Kamath, Sudha

AU - Pai, Keerthilatha M.

AU - Sarkar, Arindam

AU - Ray, Satadru

AU - Kurien, Jacob

AU - D'Almeida, Lawrence

AU - Krishnanand, B. R.

AU - Santhosh, C.

AU - Kartha, V. B.

AU - Mahato, K. K.

PY - 2006/6/5

Y1 - 2006/6/5

N2 - Pulsed laser-induced autofluorescence spectroscopic studies of pathologically certified normal, premalignant, and malignant oral tissues were carried out at 325 nm excitation. The spectral analysis and classification for discrimination among normal, premalignant, and malignant conditions were performed using principal component analysis (PCA) and artificial neural network (ANN) separately on the same set of spectral data. In case of PCA, spectral residuals, Mahalanobis distance, and scores of factors were used for discrimination among normal, premalignant, and malignant cases. In ANN, parameters like mean, spectral residual, standard deviation, and total energy were used to train the network. The ANN used in this study is a classical multiplayer feed-forward type with a back-propagation algorithm for the training of the network. The specificity and sensitivity were determined in both classification schemes. In the case of PCA, they are 100 and 92.9%, respectively, whereas for ANN they are 100 and 96.5% for the data set considered.

AB - Pulsed laser-induced autofluorescence spectroscopic studies of pathologically certified normal, premalignant, and malignant oral tissues were carried out at 325 nm excitation. The spectral analysis and classification for discrimination among normal, premalignant, and malignant conditions were performed using principal component analysis (PCA) and artificial neural network (ANN) separately on the same set of spectral data. In case of PCA, spectral residuals, Mahalanobis distance, and scores of factors were used for discrimination among normal, premalignant, and malignant cases. In ANN, parameters like mean, spectral residual, standard deviation, and total energy were used to train the network. The ANN used in this study is a classical multiplayer feed-forward type with a back-propagation algorithm for the training of the network. The specificity and sensitivity were determined in both classification schemes. In the case of PCA, they are 100 and 92.9%, respectively, whereas for ANN they are 100 and 96.5% for the data set considered.

UR - http://www.scopus.com/inward/record.url?scp=33744494091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33744494091&partnerID=8YFLogxK

U2 - 10.1002/bip.20473

DO - 10.1002/bip.20473

M3 - Article

VL - 82

SP - 152

EP - 166

JO - Biopolymers

JF - Biopolymers

SN - 0006-3525

IS - 2

ER -