RESUMO
BACKGROUND AND OBJECTIVES: Low survival rate of individuals with oral cancer emphasize the significance of early detection and treatment. Optical spectroscopic techniques are under various stages of development for diagnosis of epithelial neoplasm. This study evaluates the potential of a multivariate statistical algorithm to classify oral mucosa from autofluorescence spectral features recorded in vivo. STUDY DESIGN/METHODS: Autofluorescence spectra were recorded in a clinical trial from 15 healthy volunteers and 34 patients with diode laser excitation (404 nm) and pre-processed by normalization, mean-scaling and its combination. Linear discriminant analysis (LDA) based on leave-one-out (LOO) method of cross validation was performed on spectral data for tissue characterization. The sensitivity and specificity were determined for different lesion pairs from the scatter plot of discriminant function scores. RESULTS: Autofluorescence spectra of healthy volunteers consists of a broad emission at 500 nm that is characteristic of endogenous fluorophores, whereas in malignant lesions three additional peaks are observed at 635, 685, and 705 nm due to the accumulation of porphyrins in oral lesions. It was observed that classification design based on discriminant function scores obtained by LDA-LOO method was able to differentiate pre-malignant dysplasia from squamous cell carcinoma (SCC), benign hyperplasia from dysplasia and hyperplasia from normal with overall sensitivities of 86%, 78%, and 92%, and specificities of 90%, 100%, and 100%, respectively. CONCLUSIONS: The application of LDA-LOO method on the autofluorescence spectra recorded during a clinical trial in patients was found suitable to discriminate oral mucosal alterations during tissue transformation towards malignancy with improved diagnostic accuracies.