Dental caries remains one of the most prevalent chronic diseases of modern society. The initial stages of dental caries are characterized by demineralization of enamel, resulting in subclinical lesions, which are difficult to diagnose. If detected early enough, such demineralization can be arrested and reversed by noninvasive means through well-established preventive measures, such as fluoride therapy, anti-bacterial therapy, or low intensity laser irradiation. Near-infrared (NIR) hyperspectral imaging is a promising new technique for early detection of dental caries based on distinct spectral features of healthy and diseased dental tissues. In this study, we apply NIR hyperspectral imaging to classify and visualize healthy and diseased dental tissues including enamel, dentin, calculus, enamel caries, and dentin caries. For this purpose, a standardized teeth database was constructed consisting of 12 extracted human teeth with different degrees of caries lesions imaged by an NIR hyperspectral system, X-ray, and digital color camera. The color and X-ray images of teeth were presented to a clinician expert for localization of the dental tissues and classification of pathological changes, thereby obtaining the gold standard. Principal component analysis (PCA) was used for multivariate local modeling of healthy and diseased dental tissues. Finally, the dental tissues were classified by employing multiple discriminant analysis. Good agreement was observed between the resulting cross-validated classification and the gold standard with the classification sensitivity and specificity exceeding 79.8% and 93.8%, respectively. This study clearly shows that the proposed automated classification and visualization method based on NIR hyperspectral imaging has considerable diagnostic potential.
Vol. 7, Iss. 11 Virtual Journal for Biomedical Optics
Peter Usenik, Miran Bürmen, Aleš Fidler, Franjo Pernuš, and Boštjan Likar, "Automated Classification and Visualization of Healthy and Diseased Hard Dental Tissues by Near-Infrared Hyperspectral Imaging," Appl. Spectrosc. 66, 1067-1074 (2012)