Assessment of Clinical Examination Validity in Oral Cancer Risk Patients

Clinical Evaluation of the Optical Filter for Autofluorescence Glasses for Oral Cancer Curing Light Exposed (GOCCLES®) in the Management of Potentially Premalignant Disorders: A Retrospective Study

Background: Any oral potentially malignant disorders (OPMDs) must be regularly monitored through clinical examination to detect any possible malignant transformation. Conventional intraoral exams, however, can be difficult because these conditions may resemble benign lesions. For this reason, several non-invasive diagnostic technologies have been developed to help the clinician in detecting and distinguishing between cancerous and benign lesions. Epithelial dysplasia can be considered the most important predictor of malignant evolution. Therefore, in this study we aim to evaluate the ability of an optical filter for autofluorescence Glasses for Oral Cancer Curing Light Exposed (GOCCLES^®) and of toluidine blue staining in identifying dysplastic areas in patients with OPMDs. Methods: In this retrospective study, medical records, photographs and videos of 25 patients with oral lesions were analyzed. Forty-two biopsy samples in 25 patients with OPMDs and at least one suspicious oral mucosa lesion that were evaluated in white light, autofluorescence with optical filter GOCCLES^®, toluidine blue staining and then biopsied with histopathological analysis were analyzed. Results: The sensitivity and specificity for the autofluorescence evaluation with GOCCLES^® for identifying dysplasia or carcinoma were 66% and 48%, respectively. The positive and negative predictive values were 34% and 77%, respectively, and the accuracy was 53%. The sensitivity and specificity for toluidine blue staining were 91% and 68%, respectively. The positive and negative predictive values were 55% and 95%, respectively, and the accuracy was 75%. Conclusions: The optical filter for autofluorescence (GOCCLES^®) and toluidine blue staining are simple, inexpensive, rapid and non-invasive procedures that can assist the clinician in distinguishing OPMDs from healthy mucosa but they are not able to distinguish benign and malignant lesions.

Healthcare Professional in the Loop (HPIL): Classification of Standard and Oral Cancer-Causing Anomalous Regions of Oral Cavity Using Textural Analysis Technique in Autofluorescence Imaging

Oral mucosal lesions (OML) and oral potentially malignant disorders (OPMDs) have been identified as having the potential to transform into oral squamous cell carcinoma (OSCC). This research focuses on the human-in-the-loop-system named Healthcare Professionals in the Loop (HPIL) to support diagnosis through an advanced machine learning procedure. HPIL is a novel system approach based on the textural pattern of OML and OPMDs (anomalous regions) to differentiate them from standard regions of the oral cavity by using autofluorescence imaging. An innovative method based on pre-processing, e.g., the Deriche-Canny edge detector and circular Hough transform (CHT); a post-processing textural analysis approach using the gray-level co-occurrence matrix (GLCM); and a feature selection algorithm (linear discriminant analysis (LDA)), followed by k-nearest neighbor (KNN) to classify OPMDs and the standard region, is proposed in this paper. The accuracy, sensitivity, and specificity in differentiating between standard and anomalous regions of the oral cavity are 83%, 85%, and 84%, respectively. The performance evaluation was plotted through the receiver operating characteristics of periodontist diagnosis with the HPIL system and without the system. This method of classifying OML and OPMD areas may help the dental specialist to identify anomalous regions for performing their biopsies more efficiently to predict the histological diagnosis of epithelial dysplasia.