Development of a dental digital data set for research in artificial intelligence: the importance of labeling performed by radiologists

Abstract

ObjectiveTo present the development of a database (dataset) of panoramic radiography images. Study DesignThree radiologists labeled an image set consisting of 936 panoramic radiographs. Labeling includes tooth numbering (including teeth present and missing) and annotation dental conditions (e.g., caries, dental restoration, residual root, endodontic treatment, implant, fixed prosthesis, incisal wear). The annotation process was performed in a Picture Archive and Communication System (PACS) software customized for the study purposes, using a small bounding box to delimit the entire tooth and items for radiographic diagnosis, and a large bounding box to simultaneously delimit the 2 dental arches (maxilla and mandible). A Java Script Object Notation (JSON) file was generated for each annotation. ResultsThe database encompassing 23,619 annotations, disagreement between radiologists occurred in 0.7% of the notes. ConclusionsThis work aims to inform researchers about the importance of the labeling process, in addition to providing the scientific community with a bank of labeled images to implement artificial intelligence systems in clinical practice. Statement of clinical relevanceRadiologists are reference for generating accurate and reliable labels on images for training artificial intelligence systems. Accuracy of the labels are essential characteristics for learning and for the subsequent reliable use of the artificial intelligence system in the clinical area.