Using Modern Intraoral Scanners for Deep Learning-Assisted Diagnostic Solutions in Dentistry

Modern intraoral scanners are handheld devices that can produce point cloud-based representations of the human jaw. These scanners achieve 3-dimensional spatial resolution on the order of tens of micrometers by measuring light reflected from hard and soft intraoral tissue and applying advanced depth estimation techniques. In this work, a series of deep learning-based segmentation and registration methods for 3D intraoral data was developed for longitudinal monitoring of plaque accumulation and gingival inflammation. An intraoral scanner was used to acquire point cloud data from the upper and lower jaws of human subjects after an initial professional cleaning and then after multiple days abstaining from some oral hygiene. Individual teeth and gum regions within longitudinal datasets were identified using a deep learning algorithm for 3D instance segmentation. Next, automated spatial alignment of teeth and gum regions acquired over multi-day studies was achieved using a multiway registration method. The minimum distances between closest-correlated points were then calculated, allowing changes in tissue and plaque volume to be quantified. Differences in these measured quantities were found to correlate with the extent of plaque and inflammation assessed visually by a trained clinician. These methods provided precise measurements of morphological differences in patient tissue over longitudinal studies, allowing quantification of plaque accumulation and gingival inflammation. Integration of deep learning algorithms with commercial intraoral 3D scanning systems may provide a new approach for expanded screening of intraoral diseases.