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

Clinical Oral Investigations, vol. 28, pp. 381

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.

Authors 13

1. Ila Motmaen

   Universitätsklinikum Knappschaftskrankenhaus Bochum

   Affiliation as printed

   Department of Oral and Maxillofacial Surgery, University Hospital Knappschaftskrankenhaus Bochum, 44892, Bochum, Germany

2. Kunpeng Xie Aachen Institute of Medical Informatics Department of Oral and Maxillofacial Surgery

   RWTH Aachen University · Universitätsklinikum Aachen

   Affiliation as printed

   Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

   Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

3. Leon Schönbrunn Aachen Institute of Medical Informatics Department of Oral and Maxillofacial Surgery

   RWTH Aachen University · Universitätsklinikum Aachen

   Affiliation as printed

   Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

   Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

4. Jeff Berens Aachen Institute of Medical Informatics Department of Oral and Maxillofacial Surgery

   RWTH Aachen University · Universitätsklinikum Aachen

   Affiliation as printed

   Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

   Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

5. Kim Grunert Aachen Institute of Medical Informatics Department of Oral and Maxillofacial Surgery

   RWTH Aachen University · Universitätsklinikum Aachen

   Affiliation as printed

   Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

   Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

6. Anna Maria Plum Aachen Institute of Medical Informatics Department of Oral and Maxillofacial Surgery

   RWTH Aachen University · Universitätsklinikum Aachen

   Affiliation as printed

   Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

   Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

7. Johannes Raufeisen Aachen Institute of Medical Informatics Department of Oral and Maxillofacial Surgery

   RWTH Aachen University · Universitätsklinikum Aachen

   Affiliation as printed

   Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

   Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

8. André Filipe Ferreira Aachen Institute of Medical Informatics Department of Oral and Maxillofacial Surgery

   RWTH Aachen University · Universitätsklinikum Aachen · University of Minho · Essen University Hospital

   Affiliation as printed

   Centre Algoritmi / LASI, University of Minho, 4710-057, Braga, Portugal

   Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

   Institute for Artificial Intelligence in Medicine, Essen University Hospital, 45147, Essen, Germany

   Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

9. Alexander Hermans Aachen Visual Computing Institute Department of Diagnostic and Interventional Radiology

   RWTH Aachen University

   Affiliation as printed

   Department of Diagnostic and Interventional Radiology, RWTH Aachen University, 52074, Aachen, Germany

   Visual Computing Institute, Computer Science and Natural Sciences, RWTH Aachen University, 52074, Aachen, Germany

10. Jan Egger

    Essen University Hospital

    Affiliation as printed

    Institute for Artificial Intelligence in Medicine, Essen University Hospital, 45147, Essen, Germany

11. Frank Hölzle Aachen Department of Oral and Maxillofacial Surgery

    RWTH Aachen University · Universitätsklinikum Aachen

    Affiliation as printed

    Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany

12. Daniel Truhn Aachen Department of Diagnostic and Interventional Radiology

    RWTH Aachen University

    Affiliation as printed

    Department of Diagnostic and Interventional Radiology, RWTH Aachen University, 52074, Aachen, Germany

13. Behrus Puladi corresponding Aachen Institute of Medical Informatics Department of Oral and Maxillofacial Surgery

    RWTH Aachen University · Universitätsklinikum Aachen

    Affiliation as printed

    Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany. bpuladi@ukaachen.de

    Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany. bpuladi@ukaachen.de

    Institute of Medical Informatics, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany