Clinical study for classification of benign, dysplastic, and malignant oral lesions using autofluorescence spectroscopy

Abstract

Abstract. Autofluorescence spectroscopy shows promising results for detection and staging of oral (pre-)malignancies. To improve staging reliability, we develop and compare algorithms for lesion classification. Furthermore, we examine the potential for detecting invisible tissue alterations. Autofluorescence spectra are recorded at six excitation wavelengths from 172 benign, dysplastic, and cancerous lesions and from 97 healthy volunteers. We apply principal components analysis (PCA), artificial neural networks, and red/green intensity ratio's to separate benign from (pre-)malignant lesions, using four normalization techniques. To assess the potential for detecting invisible tissue alterations, we compare PC scores of healthy mucosa and surroundings/contralateral positions of lesions. The spectra show large variations in shape and intensity within each lesion group. Intensities and PC score distributions demonstrate large overlap between benign and (pre-)malignant lesions. The receiver-operator characteristic areas under the curve (ROC-AUCs) for distinguishing cancerous from healthy tissue are excellent (0.90 to 0.97).

Autofluorescence and diffuse reflectance spectroscopy of oral epithelial tissue using a depth-sensitive fiber-optic probe

“…Badizadegan et al reported a similar progressive reduction in fluorescence intensity and wavelength shift in dysplastic and cancerous oral tissue compared to normal tissue, with an excitation wavelength of 337 nm [9]. De Veld et al found a progressive decrease in blue-green fluorescence intensity in dysplastic and tumor tissue compared to healthy tissue at 405 nm excitation, but also found a decrease in the fluorescence intensity of benign lesion sites compared to healthy tissue [10]. This raises the concern that this parameter may not provide sufficient specificity to distinguish dysplastic and cancerous lesions from benign lesions.…”

“…Optical spectroscopy is a noninvasive technique whose potential to facilitate diagnosis of oral lesions has been demonstrated by a number of groups [6][7][8][9][10][11][12]. Loss of autofluorescence in the blue-green region of the spectrum is thought to be diagnostically significant, and according to recent reports may be associated with subclinical genetic alterations in the cancer risk field [4]; but the nature of this association has not been explained.…”

Breast Ductoscopy: Technical Development from a Diagnostic to an Interventional Procedure and Its Future Perspective

“…Only after inverting the picture and adding and cross-fading an additional picture from the blue-violet spectrum, additional visual intraductal information results which could allow a visual identification of early ductal wall alterations and possibly even ductal carcinoma in situ. From the initial development and application in bronchoscopy, a semi-quantitative visual evaluation of tissue dignity seems to be possible allowing the physician to instantly differentiate between benign and non-benign lesions during ductoscopy [20,21]. Regarding the application of autofluorescence ductoscopy, these are preliminary experimental results at a very early stage of clinical evaluation, therefore evidencebased study results are not available at present.…”

Model-based spectroscopic analysis of the oral cavity: impact of anatomy

“…Reflectance spectra were fit over the range of 380-700 nm using a constrained nonlinear least squares fitting algorithm. A double power law equation was used to represent the wavelength dependence of , (1) Here, the wavelength, λ, is expressed in units of microns and λ 0 is equal to 1 μm. A power law description of has been widely used to model data collected from both cells and tissue.…”