Insights into Predicting Tooth Extraction from Panoramic Dental Images: Artificial Intelligence Vs. Dentists

Overview

Journal Clin Oral Investig

Specialty Dentistry

Date 2024 Jun 17

PMID 38886242

Authors

Ila Motmaen

Kunpeng Xie

Leon Schonbrunn

Jeff Berens

Kim Grunert

Anna Maria Plum

Johannes Raufeisen

Andre Ferreira

Alexander Hermans

Jan Egger

Frank Holzle

Daniel Truhn

Behrus Puladi

Affiliations

Soon will be listed here.

Abstract

Objectives: Tooth extraction is one of the most frequently performed medical procedures. The indication is based on the combination of clinical and radiological examination and individual patient parameters and should be made with great care. However, determining whether a tooth should be extracted is not always a straightforward decision. Moreover, visual and cognitive pitfalls in the analysis of radiographs may lead to incorrect decisions. Artificial intelligence (AI) could be used as a decision support tool to provide a score of tooth extractability.

Material And Methods: Using 26,956 single teeth images from 1,184 panoramic radiographs (PANs), we trained a ResNet50 network to classify teeth as either extraction-worthy or preservable. For this purpose, teeth were cropped with different margins from PANs and annotated. The usefulness of the AI-based classification as well that of dentists was evaluated on a test dataset. In addition, the explainability of the best AI model was visualized via a class activation mapping using CAMERAS.

Results: The ROC-AUC for the best AI model to discriminate teeth worthy of preservation was 0.901 with 2% margin on dental images. In contrast, the average ROC-AUC for dentists was only 0.797. With a 19.1% tooth extractions prevalence, the AI model's PR-AUC was 0.749, while the dentist evaluation only reached 0.589.

Conclusion: AI models outperform dentists/specialists in predicting tooth extraction based solely on X-ray images, while the AI performance improves with increasing contextual information.

Clinical Relevance: AI could help monitor at-risk teeth and reduce errors in indications for extractions.

References

Taylor J, Fenner J . The challenge of clinical adoption-the insurmountable obstacle that will stop machine learning?. BJR Open. 2020; 1(1):20180017. PMC: 7592408. DOI: 10.1259/bjro.20180017. View

Beckers R, Kwade Z, Zanca F . The EU medical device regulation: Implications for artificial intelligence-based medical device software in medical physics. Phys Med. 2021; 83:1-8. DOI: 10.1016/j.ejmp.2021.02.011. View

Broers D, Brands W, Welie J, de Jongh A . Deciding about patients' requests for extraction: ethical and legal guidelines. J Am Dent Assoc. 2010; 141(2):195-203. DOI: 10.14219/jada.archive.2010.0139. View

Lundgren D, Rylander H, Laurell L . To save or to extract, that is the question. Natural teeth or dental implants in periodontitis-susceptible patients: clinical decision-making and treatment strategies exemplified with patient case presentations. Periodontol 2000. 2008; 47:27-50. DOI: 10.1111/j.1600-0757.2007.00239.x. View

Gilbert G, Meng X, Duncan R, Shelton B . Incidence of tooth loss and prosthodontic dental care: effect on chewing difficulty onset, a component of oral health-related quality of life. J Am Geriatr Soc. 2004; 52(6):880-5. DOI: 10.1111/j.1532-5415.2004.52253.x. View

Broers D, Dubois L, de Lange J, Su N, de Jongh A . Reasons for Tooth Removal in Adults: A Systematic Review. Int Dent J. 2021; 72(1):52-57. PMC: 9275356. DOI: 10.1016/j.identj.2021.01.011. View

Perschbacher S . Interpretation of panoramic radiographs. Aust Dent J. 2012; 57 Suppl 1:40-5. DOI: 10.1111/j.1834-7819.2011.01655.x. View

Aeffner F, Wilson K, Martin N, Black J, Luengo Hendriks C, Bolon B . The Gold Standard Paradox in Digital Image Analysis: Manual Versus Automated Scoring as Ground Truth. Arch Pathol Lab Med. 2017; 141(9):1267-1275. DOI: 10.5858/arpa.2016-0386-RA. View

Yang H, Jo E, Kim H, Cha I, Jung Y, Nam W . Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs. J Clin Med. 2020; 9(6). PMC: 7356620. DOI: 10.3390/jcm9061839. View

10.

Watanabe H, Ariji Y, Fukuda M, Kuwada C, Kise Y, Nozawa M . Deep learning object detection of maxillary cyst-like lesions on panoramic radiographs: preliminary study. Oral Radiol. 2020; 37(3):487-493. DOI: 10.1007/s11282-020-00485-4. View

11.

Bilgir E, Bayrakdar I, Celik O, Orhan K, Akkoca F, Saglam H . An artifıcial ıntelligence approach to automatic tooth detection and numbering in panoramic radiographs. BMC Med Imaging. 2021; 21(1):124. PMC: 8361658. DOI: 10.1186/s12880-021-00656-7. View

12.

Kwon O, Yong T, Kang S, Kim J, Huh K, Heo M . Automatic diagnosis for cysts and tumors of both jaws on panoramic radiographs using a deep convolution neural network. Dentomaxillofac Radiol. 2020; 49(8):20200185. PMC: 7719862. DOI: 10.1259/dmfr.20200185. View

13.

Tuzoff D, Tuzova L, Bornstein M, Krasnov A, Kharchenko M, Nikolenko S . Tooth detection and numbering in panoramic radiographs using convolutional neural networks. Dentomaxillofac Radiol. 2019; 48(4):20180051. PMC: 6592580. DOI: 10.1259/dmfr.20180051. View

14.

Ekert T, Krois J, Meinhold L, Elhennawy K, Emara R, Golla T . Deep Learning for the Radiographic Detection of Apical Lesions. J Endod. 2019; 45(7):917-922.e5. DOI: 10.1016/j.joen.2019.03.016. View

15.

Hansen B, Ryndin S, Mullen K . Infections of Deep Neck Spaces. Semin Ultrasound CT MR. 2020; 41(1):74-84. DOI: 10.1053/j.sult.2019.10.001. View

16.

Vinayahalingam S, Kempers S, Limon L, Deibel D, Maal T, Hanisch M . Classification of caries in third molars on panoramic radiographs using deep learning. Sci Rep. 2021; 11(1):12609. PMC: 8206082. DOI: 10.1038/s41598-021-92121-2. View

17.

Cha J, Yoon H, Yeo I, Huh K, Han J . Panoptic Segmentation on Panoramic Radiographs: Deep Learning-Based Segmentation of Various Structures Including Maxillary Sinus and Mandibular Canal. J Clin Med. 2021; 10(12). PMC: 8230590. DOI: 10.3390/jcm10122577. View

18.

Endres M, Hillen F, Salloumis M, Sedaghat A, Niehues S, Quatela O . Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs. Diagnostics (Basel). 2020; 10(6). PMC: 7344682. DOI: 10.3390/diagnostics10060430. View

19.

Lee J, Han S, Kim Y, Lee C, Kim I . Application of a fully deep convolutional neural network to the automation of tooth segmentation on panoramic radiographs. Oral Surg Oral Med Oral Pathol Oral Radiol. 2020; 129(6):635-642. DOI: 10.1016/j.oooo.2019.11.007. View

20.

Loh H, Ooi C, Seoni S, Barua P, Molinari F, Rajendra Acharya U . Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011-2022). Comput Methods Programs Biomed. 2022; 226:107161. DOI: 10.1016/j.cmpb.2022.107161. View