Gingival Biotype Assessment in Intraoral Photographs Using Deep Learning

This study aimed to construct a novel artificial intelligence (AI) model to assessment gingival biotype and investigate the accuracy of it based on intraoral photographs. To our knowledge, this is the first attempt to use deep learning algorithms to determine gingival biotype. A total of 1600 subjects fulfilling selection criteria were included. The gingival biotype of the maxillary anterior teeth was determined by the probe transparency method and novel artificial intelligent models. Accuracy, sensitivity, specificity, and F1 score were measured for gingival biotype detection and classification. This research demonstrates that deep learning models can determine gingival biotype in oral photographs with high accuracy, sensitivity and specificity. The successful application of deep learning in the field will undoubtedly assist the clinical diagnosis and treatment planning of dentists.