Photoacoustic spectra of normal, benign, and malignant ovarian tissues are recorded using 325-nm pulsed laser excitation in vitro. A total of 102 (34 normal, 38 benign, and 30 malignant) spectra are obtained from 22 samples belonging to normal, benign, and malignant subjects. Applying multi-algorithm approach, comprised of methods such as, principal component analysis (PCA) based k-nearest neighbor (k-NN) analysis, artificial neural network (ANN) analysis, and support vector machine (SVM) analysis, classification of the data has been carried out. For PCA, first the calibration set is formed by pooling 45 spectra, 15 belonging to each of pathologically certified normal, benign, and malignant samples. PCA is then performed on the data matrix, comprised of the six spectral features extracted from each of 45 calibration samples, and three principal components (PCs) containing maximum diagnostic information are selected. The scores of the selected PCs are used to train the k-NN, ANN, and SVM classifiers. The ANN used is a classical multilayer feed forward network with back propagation algorithm for its training. For k-NN, the Euclidean distance based algorithm is used and for SVM, one-versus-rest multiclass kernel-radial basis function is used. The performance evaluation of the classification results are obtained by calculating statistical parameters like specificity and sensitivity. ANN and k-NN techniques showed identical performance with specificity and sensitivity values of 100 and 86.76%, whereas SVM had these values at 100 and 80.18%, respectively. In order to determine the relative diagnostic performance of the techniques, receiver operating characteristics analysis is also performed.
The spectral analysis and classification for discrimination of pulsed laser-induced autofluorescence spectra of pathologically certified normal, premalignant, and malignant oral tissues recorded at a 325-nm excitation are carried out using MATLAB@R6-based principal component analysis (PCA) and k-means nearest neighbor (k-NN) analysis separately on the same set of spectral data. Six features such as mean, median, maximum intensity, energy, spectral residuals, and standard deviation are extracted from each spectrum of the 60 training samples (spectra) belonging to the normal, premalignant, and malignant groups and they are used to perform PCA on the reference database. Standard calibration models of normal, premalignant, and malignant samples are made using cluster analysis. We show that a feature vector of length 6 could be reduced to three components using the PCA technique. After performing PCA on the feature space, the first three principal component (PC) scores, which contain all the diagnostic information, are retained and the remaining scores containing only noise are discarded. The new feature space is thus constructed using three PC scores only and is used as input database for the k-NN classification. Using this transformed feature space, the centroids for normal, premalignant, and malignant samples are computed and the efficient classification for different classes of oral samples is achieved. A performance evaluation of k-NN classification results is made by calculating the statistical parameters specificity, sensitivity, and accuracy and they are found to be 100, 94.5, and 96.17%, respectively.