Identification of dental implant systems from low-quality and distorted dental radiographs using AI trained on a large multi-center dataset.

Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE

Original Publication: London : Nature Publishing Group, copyright 2011-

Dental Implants* ; Artificial Intelligence* ; Radiography, Dental*/methods; Humans ; Algorithms ; Radiography, Panoramic/methods

Most artificial intelligence (AI) studies have attempted to identify dental implant systems (DISs) while excluding low-quality and distorted dental radiographs, limiting their actual clinical use. This study aimed to evaluate the effectiveness of an AI model, trained on a large and multi-center dataset, in identifying different types of DIS in low-quality and distorted dental radiographs. Based on the fine-tuned pre-trained ResNet-50 algorithm, 156,965 panoramic and periapical radiological images were used as training and validation datasets, and 530 low-quality and distorted images of four types (including those not perpendicular to the axis of the fixture, radiation overexposure, cut off the apex of the fixture, and containing foreign bodies) were used as test datasets. Moreover, the accuracy performance of low-quality and distorted DIS classification was compared using AI and five periodontists. Based on a test dataset, the performance evaluation of the AI model achieved accuracy, precision, recall, and F1 score metrics of 95.05%, 95.91%, 92.49%, and 94.17%, respectively. However, five periodontists performed the classification of nine types of DISs based on four different types of low-quality and distorted radiographs, achieving a mean overall accuracy of 37.2 ± 29.0%. Within the limitations of this study, AI demonstrated superior accuracy in identifying DIS from low-quality or distorted radiographs, outperforming dental professionals in classification tasks. However, for actual clinical application of AI, extensive standardization research on low-quality and distorted radiographic images is essential.
(© 2024. The Author(s).)

J Periodontal Implant Sci. 2018 Apr 30;48(2):114-123. (PMID: 29770240)
Med Image Anal. 2022 Jul;79:102470. (PMID: 35576821)
J Dent. 2018 Oct;77:106-111. (PMID: 30056118)
Clin Implant Dent Relat Res. 2018 Aug;20(4):463-469. (PMID: 29761926)
Medicine (Baltimore). 2020 Jun 26;99(26):e20787. (PMID: 32590758)
Dentomaxillofac Radiol. 1989 Nov;18(4):151-5. (PMID: 2640445)
Diagnostics (Basel). 2020 Nov 07;10(11):. (PMID: 33171758)
J Dent Res. 2023 Jul;102(7):727-733. (PMID: 37085970)
J Periodontal Res. 2018 Oct;53(5):657-681. (PMID: 29882313)
J Forensic Odontostomatol. 2008 Jun 01;26(1):8-11. (PMID: 22689351)
J Periodontal Implant Sci. 2022 Jun;52(3):220-229. (PMID: 35775697)
J Prosthet Dent. 2023 Sep 14;:. (PMID: 37716899)
J Prosthet Dent. 2023 Dec 28;:. (PMID: 38158266)
J Clin Med. 2020 Apr 14;9(4):. (PMID: 32295304)
Nat Rev Cancer. 2018 Aug;18(8):500-510. (PMID: 29777175)
J Oral Biol Craniofac Res. 2023 Mar-Apr;13(2):306-314. (PMID: 36923071)
J Adv Prosthodont. 2016 Apr;8(2):150-7. (PMID: 27141260)
Med Image Anal. 2023 Feb;84:102684. (PMID: 36516555)
Int J Multimed Inf Retr. 2022;11(1):19-38. (PMID: 34513553)
Front Digit Health. 2021 Jun 25;3:645232. (PMID: 34713115)
J Clin Epidemiol. 2008 Apr;61(4):344-9. (PMID: 18313558)
Clin Oral Implants Res. 2023 Sep;34 Suppl 26:257-265. (PMID: 37750516)
Diagnostics (Basel). 2021 Feb 03;11(2):. (PMID: 33546446)
Sci Rep. 2023 Mar 24;13(1):4862. (PMID: 36964171)
Int J Implant Dent. 2020 Sep 22;6(1):53. (PMID: 32959154)
J Prosthodont. 2015 Oct;24(7):517-524. (PMID: 26095585)
J Clin Med. 2020 Nov 25;9(12):. (PMID: 33255705)
Oral Dis. 2020 Jan;26(1):152-158. (PMID: 31677205)
J Forensic Sci. 2010 Jan;55(1):66-70. (PMID: 20002257)
Biomolecules. 2021 May 30;11(6):. (PMID: 34070916)
Acad Med. 2021 Jan 1;96(1):31-36. (PMID: 32852320)
J Periodontal Implant Sci. 2024 Feb;54(1):3-12. (PMID: 37154107)

2019R1A2C1083978 National Research Foundation of Korea

Keywords: Artificial intelligence; Deep learning; Dental implants; Diagnostic imaging

0 (Dental Implants)

Date Created: 20240601 Date Completed: 20240601 Latest Revision: 20240815

20250114

PMC11144187

10.1038/s41598-024-63422-z

38824187