Next Article in Journal
Accuracy of a Semi-Quantitative Ultrasound Method to Determine Liver Fat Infiltration in Early Adulthood
Previous Article in Journal
Budget Impact Analysis of EGFR Mutation Liquid Biopsy for First- and Second-Line Treatment of Metastatic Non-Small Cell Lung Cancer in Greece
Open AccessArticle

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

1
Laboratory for Innovation Science, Harvard University, 175 N. Harvard Street, Suite 1350, Boston, MA 02134, USA
2
Institute for Data, Systems and Society, Massachusetts Institute of Technology, 50 Ames St, Cambridge, MA 02142, USA
3
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
4
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
5
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
6
Department of Oral- and Maxillofacial Surgery, Universitätsklinikum Hamburg, Eppendorf, Maritnistraße 52, 20246 Hamburg, Germany
7
Technology and Operations Management Unit, Harvard Business School, Wyss House, Boston, MA 02163, USA
*
Author to whom correspondence should be addressed.
Diagnostics 2020, 10(6), 430; https://doi.org/10.3390/diagnostics10060430
Received: 25 May 2020 / Revised: 18 June 2020 / Accepted: 19 June 2020 / Published: 24 June 2020
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
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. View Full-Text
Keywords: artificial intelligence; diagnosis; computer-assisted; image interpretation; computer-assisted; machine learning; radiography; panoramic radiograph artificial intelligence; diagnosis; computer-assisted; image interpretation; computer-assisted; machine learning; radiography; panoramic radiograph
Show Figures

Figure 1

MDPI and ACS Style

Endres, M.G.; Hillen, F.; Salloumis, M.; Sedaghat, A.R.; Niehues, S.M.; Quatela, O.; Hanken, H.; Smeets, R.; Beck-Broichsitter, B.; Rendenbach, C.; Lakhani, K.; Heiland, M.; Gaudin, R.A. Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs. Diagnostics 2020, 10, 430.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop