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

Eliana Dantas Costa; Hugo Gaêta-Araujo; José Andery Carneiro; Breno Augusto Guerra Zancan; José Augusto Baranauskas; Alessandra Alaniz Macedo; Camila Tirapelli

doi:10.1016/j.oooo.2023.12.006

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

Oral Surg Oral Med Oral Pathol Oral Radiol. 2023 Dec 14:S2212-4403(23)00765-4. doi: 10.1016/j.oooo.2023.12.006. Online ahead of print.

Authors

Eliana Dantas Costa¹, Hugo Gaêta-Araujo², José Andery Carneiro³, Breno Augusto Guerra Zancan³, José Augusto Baranauskas³, Alessandra Alaniz Macedo³, Camila Tirapelli⁴

Affiliations

¹ Department of Dental Materials and Prosthodontics, School of Dentistry of Ribeirão Preto, University of São Paulo, Ribeirão Preto, São Paulo, Brazil. Electronic address: edantasc@yahoo.com.br.
² Department of Stomatology, Public Health and Forensic Dentistry, Division of Oral Radiology, School of Dentistry of Ribeirão Preto, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
³ Department of Computing and Mathematics, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
⁴ Department of Dental Materials and Prosthodontics, School of Dentistry of Ribeirão Preto, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.

PMID: 38632036
DOI: 10.1016/j.oooo.2023.12.006

Abstract

Objective: The aim of this study was to present the development of a database (dataset) of panoramic radiographs.

Study design: Three radiologists labeled an image set consisting of 936 panoramic radiographs. Labeling includes tooth numbering (including teeth present and missing) and annotation of 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 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 JSON file was generated for each annotation.

Results: The database encompassed 23,619 annotations; disagreement between radiologists occurred in 0.7% of the notes.

Conclusions: This 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.