Dental anomaly detection using intraoral photos via deep learning

• Autores: Ragodos, Ronilo; Wang, Tong; Padilla, Carmencita; Hecht, Jacqueline T.; Poletta, Fernando Adrián; Orioli, Ieda Maria; Buxó, Carmen J.; Butali, Azeez; Valencia Ramirez, Consuelo; Restrepo Muñeton, Claudia; Wehby, George; Weinberg, Seth M.; Marazita, Mary L.; Moreno Uribe, Lina M.; Howe, Brian J.
• Año de publicación: 2022
• Idioma: inglés
• Tipo de recurso: artículo
• Materia: dental anomaly; oral cleft; deep learning
• Institución: Consejo Nacional de Investigaciones Científicas y Técnicas

Children with orofacial clefting (OFC) present with a wide range of dental anomalies. Identifying these anomalies is vital to understand their etiology and to discern the complex phenotypic spectrum of OFC. Such anomalies are currently identified using intra-oral exams by dentists, a costly and time-consuming process. We claim that automating the process of anomaly detection using deep neural networks (DNNs) could increase efficiency and provide reliable anomaly detection while potentially increasing the speed of research discovery. This study characterizes the use of` DNNs to identify dental anomalies by training a DNN model using intraoral photographs from the largest international cohort to date of children with nonsyndromic OFC and controls (OFC1). In this project, the intraoral images were submitted to a Convolutional Neural Network model to perform multi-label multi-class classification of 10 dental anomalies. The network predicts whether an individual exhibits any of the 10 anomalies and can do so significantly faster than a human rater can. For all but three anomalies, F1 scores suggest that our model performs competitively at anomaly detection when compared to a dentist with 8 years of clinical experience. In addition, we use saliency maps to provide a post-hoc interpretation for our model’s predictions. This enables dentists to examine and verify our model’s predictions.
Fil: Ragodos, Ronilo. University of Iowa; Estados Unidos
Fil: Wang, Tong. University of Iowa; Estados Unidos
Fil: Padilla, Carmencita. University of the Philippines; Filipinas
Fil: Hecht, Jacqueline T.. University of Texas Health Science Center at Houston; Estados Unidos
Fil: Poletta, Fernando Adrián. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Parque Centenario. CEMIC-CONICET. Centro de Educaciones Médicas e Investigaciones Clínicas "Norberto Quirno". CEMIC-CONICET; Argentina
Fil: Orioli, Ieda Maria. Universidade Federal do Rio de Janeiro; Brasil
Fil: Buxó, Carmen J.. Universidad de Puerto Rico; Puerto Rico
Fil: Butali, Azeez. University of Iowa; Estados Unidos
Fil: Valencia Ramirez, Consuelo. Fundación Clínica Noel; Colombia
Fil: Restrepo Muñeton, Claudia. Fundación Clínica Noel; Colombia
Fil: Wehby, George. University of Iowa; Estados Unidos
Fil: Weinberg, Seth M.. University of Pittsburgh; Estados Unidos. University of Pittsburgh at Johnstown; Estados Unidos
Fil: Marazita, Mary L.. University of Pittsburgh at Johnstown; Estados Unidos. University of Pittsburgh; Estados Unidos
Fil: Moreno Uribe, Lina M.. University of Iowa; Estados Unidos
Fil: Howe, Brian J.. University of Iowa; Estados Unidos