Anatomy-Based Algorithms for Detecting Oral Cancer Using Reflectance and Fluorescence Spectroscopy

Abstract

Objectives:We used reflectance and fluorescence spectroscopy to noninvasively and quantitatively distinguish benign from dysplastic/malignant oral lesions. We designed diagnostic algorithms to account for differences in the spectral properties among anatomic sites (gingiva, buccal mucosa, etc). Mettiods: In vivo reflectance and fluorescence spectra were collected from 71 patients with oral lesions. The tissue was then biopsied and the specimen evaluated by histopathology. Quantitative parameters related to tissue morphology and biochemistry were extracted from the spectra. Diagnostic algorithms specific for combinations of sites with similar spectral properties were developed. Resutts: Discrimination of benign from dysplastic/malignant lesions was most successful when algorithms were designed for individual sites (area under the receiver operator characteristic curve [ROC-AUC], 0.75 for the lateral surface of the tongue) and was least accurate when all sites were combined (ROC-AUC, 0.60). The combination of sites with similar spectral properties (floor of mouth and lateral surface of the tongue) yielded an ROC-AUC of 0.71. Conctusions:Accurate spectroscopic detection of oral disease must account for spectral variations among anatomic sites. Anatomy-based algorithms for single sites or combinations of sites demonstrated good diagnostic performance in distinguishing benign lesions from dysplastic/malignant lesions and consistently performed better than algorithms developed for all sites combined.

Characterizing variability in in vivo Raman spectroscopic properties of different anatomical sites of normal tissue in the oral cavity

“…Figure S1 essentially indicates that the tissues could be grossly divided into three major clusterings, namely, (1) buccal, inner lip, and soft palate; (2) dorsal, ventral tongue, and floor; (3) gingiva 0 34 0 0 1 0 3 4 Floor 7 1 17 0 0 3 1 11 Gingiva 0 4 0 34 3 5 1 3 Hard palate 3 7 6 17 15 5 4 3 Inner lip 17 1 5 0 3 20 3 2 Soft palate 12 6 11 2 0 9 3 7 Ventral tongue 1 17 7 0 0 5 6 and hard palate, which was also partly established by means of fluorescence spectroscopy. [7] The gross biomolecular/biochemical profiles of different oral tissue types were further assessed by rendering semi-quantitative NNCLSM models constructed from essential Raman active constituents associated with oral tissues. The complex biochemical profiles (Fig.…”

Portable Optical Fiber Probe-Based Spectroscopic Scanner for Rapid Cancer Diagnosis: A New Tool for Intraoperative Margin Assessment

“…The glass plate flattens the tissue surface and provides a reasonably uniform probe-tissue imaging distance. This allows us to make quantitative measurements, by preserving the key optical characteristics of the probe (spot size and NA), and take full advantage of our clinically proven, probe-based spectroscopic models [12]–[15], which would not be applicable to data acquired with a free space imaging system. Excitation beam spot size at the surface of a tissue sample sitting on the glass plate is estimated to be <1 mm.…”

“…Spectral modeling provides physically meaningful fitting parameters that are quantitative measures the contributions of specific tissue components. These spectral parameters are the basis of decision algorithms used in the diagnosis of breast [15] and other cancers [12]–[14]. DRS modeling yields 3 scattering parameters: A, which is related to the amount of Mie scatterers; B, which is related to the size of the scatterers; and C, which is related to the amount of Rayleigh scatterers; and absorption fitting parameters for hemoglobin (Hb) and β-carotene, two well-characterized absorbers in breast tissue.…”

“…The scanner significantly advances our optical fiber probe-based spectroscopy instruments [10], [11], which have been successfully employed in clinical studies for the diagnosis of oral, esophageal, cervical and breast cancer [12]–[15], to a wide field, high resolution imaging regime as required to be an effective clinical tool for intraoperative margin assessment at cancer surgery. This tissue scanner is simpler in design, images a larger field of view at higher resolution and provides a more physically meaningful tissue diagnosis than other spectroscopic margin imaging systems currently in development.…”

Prospective evaluation of a portable depth-sensitive optical spectroscopy device to identify oral neoplasia

“…Considerable success has been reported in distinguishing lesions from healthy oral mucosa, but the spectral variations among different anatomic sites within the oral cavity and the problem of discriminating benign lesions from precancerous/cancerous lesions continue to pose challenges [23,24]. Recent investigations reflect these complexities, including measurement techniques that target localized, superficial tissue regions where early premalignant changes are believed to occur [25,26]; algorithms that are explicitly based on specific anatomic sites within the oral cavity [27]; and multi-class algorithms that are designed to classify tissue into a range of diagnostic categories [28]. …”