Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs

Diagnostics

Marios Salloumis¹  Carsten Rendenbach¹  Max Heiland¹  Benedicta Beck-Broichsitter¹  Henning Hanken²  Ralf Smeets²  Olivia Quatela²  AhmadR. Sedaghat³  StefanM. Niehues⁴  MichaelG. Endres⁵  RobertA. Gaudin⁵  Florian Hillen⁵  Karim Lakhani⁵ 

[1] Department of Oral- and Maxillofacial Surgery, Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Hindenburgdamm 30, 12203 Berlin, Germany;Department of Oral- and Maxillofacial Surgery, Universitätsklinikum Hamburg, Eppendorf, Maritnistraße 52, 20246 Hamburg, Germany;Department of Otolaryngology—Head and Neck Surgery, University of Cincinnati College of Medicine, Medical Sciences Building Room 6410, 231 Albert Sabin Way, Cincinnati, OH 45267, USA;Department of Radiology, Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Hindenburgdamm 30, 12203 Berlin, Germany;Laboratory for Innovation Science, Harvard University, 175 N. Harvard Street, Suite 1350, Boston, MA 02134, USA;

关键词: artificial intelligence;    diagnosis;    computer-assisted;    image interpretation;    computer-assisted;    machine learning;   

DOI  :  10.3390/diagnostics10060430

来源: DOAJ

【 摘 要 】

Periapical radiolucencies, which can be detected on panoramic radiographs, are one of the most common radiographic findings in dentistry and have a differential diagnosis including infections, granuloma, cysts and tumors. In this study, we seek to investigate the ability with which 24 oral and maxillofacial (OMF) surgeons assess the presence of periapical lucencies on panoramic radiographs, and we compare these findings to the performance of a predictive deep learning algorithm that we have developed using a curated data set of 2902 de-identified panoramic radiographs. The mean diagnostic positive predictive value (PPV) of OMF surgeons based on their assessment of panoramic radiographic images was 0.69(± 0.13), indicating that dentists on average falsely diagnose 31% of cases as radiolucencies. However, the mean diagnostic true positive rate (TPR) was 0.51(± 0.14), indicating that on average 49% of all radiolucencies were missed. We demonstrate that the deep learning algorithm achieves a better performance than 14 of 24 OMF surgeons within the cohort, exhibiting an average precision of 0.60(± 0.04), and an F₁ score of 0.58(± 0.04) corresponding to a PPV of 0.67(± 0.05) and TPR of 0.51(± 0.05). The algorithm, trained on limited data and evaluated on clinically validated ground truth, has potential to assist OMF surgeons in detecting periapical lucencies on panoramic radiographs.

【 授权许可】

Unknown