Simultaneous detection of dental caries and fissure sealant in intraoral photos by deep learning: a pilot study

Yanshan Xiong; Hongyuan Zhang; Shiyong Zhou; Minhua Lu; Jiahui Huang; Qiangtai Huang; Bingsheng Huang; Jiangfeng Ding

doi:10.1186/s12903-024-04254-1

Simultaneous detection of dental caries and fissure sealant in intraoral photos by deep learning: a pilot study

BMC Oral Health. 2024 May 12;24(1):553. doi: 10.1186/s12903-024-04254-1.

Authors

Yanshan Xiong^#¹, Hongyuan Zhang^#², Shiyong Zhou¹, Minhua Lu³, Jiahui Huang², Qiangtai Huang², Bingsheng Huang⁴, Jiangfeng Ding^{5

6}

Affiliations

¹ Department of Endodontics, Shenzhen Stomatology Hospital, Shenzhen, Guangdong, China.
² Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, Guangdong, China.
³ Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, Guangdong, China.
⁴ Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, Guangdong, China. huangb@szu.edu.cn.
⁵ Department of Endodontics, Shenzhen Stomatology Hospital, Shenzhen, Guangdong, China. dentist_djf@hotmail.com.
⁶ Department of Pediatric Stomatology, Shenzhen Stomatology Hospital, Shenzhen, Guangdong, China. dentist_djf@hotmail.com.

^# Contributed equally.

Abstract

Background: Deep learning, as an artificial intelligence method has been proved to be powerful in analyzing images. The purpose of this study is to construct a deep learning-based model (ToothNet) for the simultaneous detection of dental caries and fissure sealants in intraoral photos.

Methods: A total of 1020 intraoral photos were collected from 762 volunteers. Teeth, caries and sealants were annotated by two endodontists using the LabelMe tool. ToothNet was developed by modifying the YOLOX framework for simultaneous detection of caries and fissure sealants. The area under curve (AUC) in the receiver operating characteristic curve (ROC) and free-response ROC (FROC) curves were used to evaluate model performance in the following aspects: (i) classification accuracy of detecting dental caries and fissure sealants from a photograph (image-level); and (ii) localization accuracy of the locations of predicted dental caries and fissure sealants (tooth-level). The performance of ToothNet and dentist with 1year of experience (1-year dentist) were compared at tooth-level and image-level using Wilcoxon test and DeLong test.

Results: At the image level, ToothNet achieved an AUC of 0.925 (95% CI, 0.880-0.958) for caries detection and 0.902 (95% CI, 0.853-0.940) for sealant detection. At the tooth level, with a confidence threshold of 0.5, the sensitivity, precision, and F1-score for caries detection were 0.807, 0.814, and 0.810, respectively. For fissure sealant detection, the values were 0.714, 0.750, and 0.731. Compared with ToothNet, the 1-year dentist had a lower F1 value (0.599, p < 0.0001) and AUC (0.749, p < 0.0001) in caries detection, and a lower F1 value (0.727, p = 0.023) and similar AUC (0.829, p = 0.154) in sealant detection.

Conclusions: The proposed deep learning model achieved multi-task simultaneous detection in intraoral photos and showed good performance in the detection of dental caries and fissure sealants. Compared with 1-year dentist, the model has advantages in caries detection and is equivalent in fissure sealants detection.

Keywords: Artificial intelligence; Deep learning; Dental caries; Fissure sealant.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adult
Deep Learning*
Dental Caries* / diagnosis
Female
Humans
Male
Photography, Dental / methods
Pilot Projects
Pit and Fissure Sealants* / therapeutic use

Substances

Pit and Fissure Sealants