The Use of Artificial Intelligence in Endodontics

Abstract

Endodontics is the dental specialty foremost concerned with diseases of the pulp and periradicular tissues. Clinicians often face patients with varying symptoms, must critically assess radiographic images in 2 and 3 dimensions, derive complex diagnoses and decision making, and deliver sophisticated treatment. Paired with low intra- and interobserver agreement for radiographic interpretation and variations in treatment outcome resulting from nonstandardized clinical techniques, there exists an unmet need for support in the form of artificial intelligence (AI), providing automated biomedical image analysis, decision support, and assistance during treatment. In the past decade, there has been a steady increase in AI studies in endodontics but limited clinical application. This review focuses on critically assessing the recent advancements in endodontic AI research for clinical applications, including the detection and diagnosis of endodontic pathologies such as periapical lesions, fractures and resorptions, as well as clinical treatment outcome predictions. It discusses the benefits of AI-assisted diagnosis, treatment planning and execution, and future directions including augmented reality and robotics. It critically reviews the limitations and challenges imposed by the nature of endodontic data sets, AI transparency and generalization, and potential ethical dilemmas. In the near future, AI will significantly affect the everyday endodontic workflow, education, and continuous learning.

Keywords: computer vision/convolutional neural networks; cracked teeth; decision making; deep learning/machine learning; diagnostic systems; treatment planning.

Figure 1.

Full 3-dimensional multilabel segmentation with periapical lesion detection of dental limited field-of-view cone-beam computed tomography (CBCT) of the maxillary left quadrant (canine through wisdom tooth). Periapical lesion on the first maxillary left molar. Comparison of clinician-labeled ground truth segmentation (Clinician) with fully automated segmentation of the identical areas with the AI platform (AI). Ground truth labeling techniques as described by Setzer et al. (2020). Labels: lesion, red; tooth structure, yellow; bone, blue; restorative materials, green; background, black. (A) Original CBCT slice, sagittal view. (B) Original CBCT slice, coronal view. (C) Three-dimensional rendering of the entire limited field-of-view volume, ground truth labeling (clinician). (D) Three-dimensional rendering of the entire limited field-of-view volume, fully automated labeling (AI). (E) Ground truth labeling of (A) sagittal view (clinician). (F) Fully automated labeling of (A) sagittal view (AI). (G) Ground truth labeling of (B) coronal view (clinician). (H) Fully automated labeling of (B) coronal view (AI). Unpublished case example, courtesy of Rui Qi Chen, Center for Machine Learning, Georgia Institute of Technology, Atlanta, Georgia.

Figure 2.

Crack detection. (A) Original tooth volume. A strong crack (left) and a subtle crack (right) are indicated by 2 arrows. (B) Probability map overlay. Values are interpolated from 0 (red) to 1 (purple). The larger crack shown in purple indicates a strong probability (value = 1), while the subtle crack is shown in green (value = 0.6). Modified from Sahu et al. 2023.

Figure 3.

Visualization of 2 “test set” case examples. Each example shows the gray-scale preoperative periapical radiographs and corresponding Grad-CAM heat map of each feature or endodontic prediction. The red region represents a larger weight, which can be decoded by the color bar on the right. In this figure, 4 clinical features and the endodontic outcome prediction Grad-CAM heat map were superimposed on a preoperative preprocessed image. (A) Example of a mandibular right first premolar (failure). COD, coronal defect; FCR, full coverage restoration; PAR, periapical radiolucency; PRF, previous root filling. (B) Example of a mandibular left second premolar (success). Previously unpublished case examples from Lee et al. (2023). Courtesy Dr. Junghoon Lee, DDS, PhD, Microscope Center, Yonsei University College of Dentistry, Seoul, South Korea.