Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs.
artificial intelligence
computer-assisted
diagnosis
image interpretation
machine learning
panoramic radiograph
radiography
Journal
Diagnostics (Basel, Switzerland)
ISSN: 2075-4418
Titre abrégé: Diagnostics (Basel)
Pays: Switzerland
ID NLM: 101658402
Informations de publication
Date de publication:
24 Jun 2020
24 Jun 2020
Historique:
received:
25
05
2020
revised:
18
06
2020
accepted:
19
06
2020
entrez:
1
7
2020
pubmed:
1
7
2020
medline:
1
7
2020
Statut:
epublish
Résumé
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 F
Identifiants
pubmed: 32599942
pii: diagnostics10060430
doi: 10.3390/diagnostics10060430
pmc: PMC7344682
pii:
doi:
Types de publication
Journal Article
Langues
eng
Subventions
Organisme : Eric and Wendy Schmidt Family Foundation
ID : 0000
Références
Iran J Radiol. 2015 Aug 05;12(4):e16242
pubmed: 26793287
Acta Odontol Scand. 2013 May-Jul;71(3-4):518-24
pubmed: 22816380
Radiographics. 2013 Jan-Feb;33(1):E15-32
pubmed: 23322846
Nature. 2017 Feb 2;542(7639):115-118
pubmed: 28117445
Caries Res. 2001 Jan-Feb;35(1):12-20
pubmed: 11125191
Int Endod J. 2017 May;50(5):427-436
pubmed: 27063356
Quant Imaging Med Surg. 2013 Feb;3(1):43-8
pubmed: 23483085
Eur J Oral Sci. 2002 Jun;110(3):199-203
pubmed: 12120704
PLoS Med. 2018 Nov 30;15(11):e1002707
pubmed: 30500815
PLoS Med. 2018 Nov 30;15(11):e1002708
pubmed: 30500811
Neurocomputing. 2016 May 26;191:214-223
pubmed: 28154470
Med Image Anal. 2017 Dec;42:1-13
pubmed: 28732268
Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2016 Jun-Jul;2016:2424-2433
pubmed: 27795661
Med Image Anal. 2016 Jul;31:63-76
pubmed: 26974042
Indian J Dent Res. 2011 Mar-Apr;22(2):362
pubmed: 21891917
Radiology. 2013 Jan;266(1):104-13
pubmed: 23169790
Imaging Sci Dent. 2012 Sep;42(3):183-90
pubmed: 23071969
Eur Radiol Exp. 2018 Oct 24;2(1):35
pubmed: 30353365
Aust Dent J. 2012 Mar;57 Suppl 1:40-5
pubmed: 22376096
J Am Dent Assoc. 1984 May;108(5):755-9
pubmed: 6588117
Sci Rep. 2017 Apr 18;7:46450
pubmed: 28418027
Community Dent Oral Epidemiol. 1986 Feb;14(1):8-9
pubmed: 3456878
J Am Dent Assoc. 1985 Dec;111(6):967-9
pubmed: 3864852
J Periodontol. 2005 Apr;76(4):605-13
pubmed: 15857102
Comput Struct Biotechnol J. 2018 Feb 09;16:34-42
pubmed: 30275936
J Endod. 2016 Mar;42(3):356-64
pubmed: 26902914
Radiology. 2019 Jun;291(3):781-791
pubmed: 30990384
Int Endod J. 2000 Nov;33(6):509-15
pubmed: 11307254
Cell. 2018 Feb 22;172(5):1122-1131.e9
pubmed: 29474911
Ann Oncol. 2018 Aug 1;29(8):1836-1842
pubmed: 29846502
Clin Radiol. 2001 Dec;56(12):938-46
pubmed: 11795921
J Endod. 2018 Oct;44(10):1500-1508
pubmed: 30154006
Int Endod J. 2002 Aug;35(8):690-7
pubmed: 12196222
Nat Med. 2018 Sep;24(9):1342-1350
pubmed: 30104768
Swed Dent J Suppl. 1996;119:1-26
pubmed: 8971997
J Endod. 2017 Oct;43(10):1640-1646
pubmed: 28807372
Ulster Med J. 2012 Jan;81(1):3-9
pubmed: 23536732
J Endod. 2019 Jul;45(7):917-922.e5
pubmed: 31160078