Non-invasive caries detection and delineation via novel laser-induced fluorescence with hyperspectral imaging

Abstract

Carious is a global chronic disease; 2 billion people and 520 million children suffer from permanent and primary teeth caries respectively. Early caries detection via precise, non-invasive, non-ionizing radiation is highly appreciated. Carious deteriorate the chemical structure of sound tooth tissues, with variation in its optical properties. In this study, customized laser-induced fluorescence system consists of non-ionizing laser light source and hyperspectral camera was developed for early caries detection. Tested tooth sample was illuminated with laser source of 385 nm and 5 mW power. The emitted spectrum signature for main tooth elements including enamel, dentin, stain, and caries were captured. Logarithmic scale of spectrum signature was applied in an attempt to enhance system sensitivity to fluorescent signal. Fluorescence signature at 500 nm secured the maximum fluorescence intensity difference for different tooth elements. Consequently 2D hyperspectral image at 500 nm was constructed. Enhanced 2D image was accomplished via nonlinear filter to enhance contrast. Segmentation via K mean clustering was adopted for precise caries delineation. This narrative, facile, non-invasive, non-ionizing technique experienced precise and accurate delineation of different caries stages (normal, moderate, and severe).