Research ExplorerPublicationsDevelopment of a Deep Learning Algorithm for Periapical Dise...

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

Standard

Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs. / Endres, Michael G; Hillen, Florian; Salloumis, Marios; Sedaghat, Ahmad R; Niehues, Stefan M; Quatela, Olivia; Hanken, Henning; Smeets, Ralf; Beck-Broichsitter, Benedicta; Rendenbach, Carsten; Lakhani, Karim; Heiland, Max; Gaudin, Robert A.

In: DIAGNOSTICS, Vol. 10, No. 6, 24.06.2020.

Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review

Harvard

Endres, MG, Hillen, F, Salloumis, M, Sedaghat, AR, Niehues, SM, Quatela, O, Hanken, H, Smeets, R, Beck-Broichsitter, B, Rendenbach, C, Lakhani, K, Heiland, M & Gaudin, RA 2020, 'Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs', DIAGNOSTICS, vol. 10, no. 6. https://doi.org/10.3390/diagnostics10060430

APA

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. (2020). Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs. DIAGNOSTICS, 10(6). https://doi.org/10.3390/diagnostics10060430

Vancouver

Endres MG, Hillen F, Salloumis M, Sedaghat AR, Niehues SM, Quatela O et al. Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs. DIAGNOSTICS. 2020 Jun 24;10(6). https://doi.org/10.3390/diagnostics10060430

Bibtex

@article{21eede153d5c4b5789365c02afccafc9,
title = "Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs",
abstract = "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.",
author = "Endres, {Michael G} and Florian Hillen and Marios Salloumis and Sedaghat, {Ahmad R} and Niehues, {Stefan M} and Olivia Quatela and Henning Hanken and Ralf Smeets and Benedicta Beck-Broichsitter and Carsten Rendenbach and Karim Lakhani and Max Heiland and Gaudin, {Robert A}",
year = "2020",
month = jun,
day = "24",
doi = "10.3390/diagnostics10060430",
language = "English",
volume = "10",
journal = "DIAGNOSTICS",
issn = "2075-4418",
publisher = "MDPI AG",
number = "6",

}

RIS

TY - JOUR

T1 - Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs

AU - Endres, Michael G

AU - Hillen, Florian

AU - Salloumis, Marios

AU - Sedaghat, Ahmad R

AU - Niehues, Stefan M

AU - Quatela, Olivia

AU - Hanken, Henning

AU - Smeets, Ralf

AU - Beck-Broichsitter, Benedicta

AU - Rendenbach, Carsten

AU - Lakhani, Karim

AU - Heiland, Max

AU - Gaudin, Robert A

PY - 2020/6/24

Y1 - 2020/6/24

N2 - 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.

AB - 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.

U2 - 10.3390/diagnostics10060430

DO - 10.3390/diagnostics10060430

M3 - SCORING: Journal article

C2 - 32599942

VL - 10

JO - DIAGNOSTICS

JF - DIAGNOSTICS

SN - 2075-4418

IS - 6

ER -