Deep Learning-Based Automated Detection and Geometric Severity Assessment of Open Gingival Embrasures in Intraoral Photographs: A Multicentre Study.
OBJECTIVES To develop and validate a framework combining deep learning-based detection with geometric severity assessment of open gingival embrasures (OGEs) from intraoral photographs. METHODS A total of 3,995 OGEs from 653 intraoral photographs collected across three orthodontic centres were annotated at the pixel l...