深度学习在龋齿检测中的应用：系统综述。

Deep learning for caries detection: A systematic review.

机构信息

Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Berlin, Germany; Department of Computer Engineering, Sharif University of Technology, Tehran, Iran.

Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Berlin, Germany; Dentofacial Deformities Research Center, Research Institute of Dental Sciences & Department of Orthodontics, School of Dentistry, Shahid Beheshti University of Medical Sciences, Tehran, Iran.

出版信息

J Dent. 2022 Jul;122:104115. doi: 10.1016/j.jdent.2022.104115. Epub 2022 Mar 30.

DOI:10.1016/j.jdent.2022.104115

PMID:35367318

Abstract

OBJECTIVES

Detecting caries lesions is challenging for dentists, and deep learning models may help practitioners to increase accuracy and reliability. We aimed to systematically review deep learning studies on caries detection.

DATA

We selected diagnostic accuracy studies that used deep learning models on dental imagery (including radiographs, photographs, optical coherence tomography images, near-infrared light transillumination images). The latest version of the quality assessment tool for diagnostic accuracy studies (QUADAS-2) tool was used for risk of bias assessment. Meta-analysis was not performed due to heterogeneity in the studies methods and their performance measurements.

SOURCES

Databases (Medline via PubMed, Google Scholar, Scopus, Embase) and a repository (ArXiv) were screened for publications published after 2010, without any limitation on language.

STUDY SELECTION

From 252 potentially eligible references, 48 studies were assessed full-text and 42 included, using classification (n = 26), object detection (n = 6), or segmentation models (n = 10). A wide range of performance metrics was used; image, object or pixel accuracy ranged between 68%-99%. The minority of studies (n = 11) showed a low risk of biases in all domains, and 13 studies (31.0%) low risk for concerns regarding applicability. The accuracy of caries classification models varied, i.e. 71% to 96% on intra-oral photographs, 82% to 99.2% on peri-apical radiographs, 87.6% to 95.4% on bitewing radiographs, 68.0% to 78.0% on near-infrared transillumination images, 88.7% to 95.2% on optical coherence tomography images, and 86.1% to 96.1% on panoramic radiographs. Pooled diagnostic odds ratios varied from 2.27 to 32,767. For detection and segmentation models, heterogeneity in reporting did not allow useful pooling.

CONCLUSION

An increasing number of studies investigated caries detection using deep learning, with a diverse types of architectures being employed. Reported accuracy seems promising, while study and reporting quality are currently low.

CLINICAL SIGNIFICANCE

Deep learning models can be considered as an assistant for decisions regarding the presence or absence of carious lesions.

摘要

目的

龋病检测对牙医来说具有挑战性，深度学习模型可能有助于提高医生的准确性和可靠性。本研究旨在系统地回顾龋病检测的深度学习研究。

资料来源

我们选择了使用牙科影像学（包括射线照相、照片、光相干断层扫描图像、近红外光透射图像）的深度学习模型的诊断准确性研究。使用诊断准确性研究的最新版质量评估工具（QUADAS-2）评估偏倚风险。由于研究方法和性能测量的异质性，未进行荟萃分析。

检索数据库

从 2010 年后发表的数据库（PubMed 中的 Medline、Google Scholar、Scopus、Embase）和存储库（ArXiv）中筛选出文献，对语言不设任何限制。

研究选择

从 252 篇可能符合条件的参考文献中，评估了 48 篇全文，其中 42 篇被纳入研究，包括分类模型（n=26）、目标检测模型（n=6）或分割模型（n=10）。研究中使用了多种性能指标；图像、目标或像素的准确率范围在 68%-99%之间。少数研究（n=11）在所有领域均显示低偏倚风险，13 项研究（31.0%）在适用性方面的风险较低。龋病分类模型的准确性存在差异，例如口腔内照片的准确率为 71%-96%，根尖周射线照片的准确率为 82%-99.2%，咬合翼射线照片的准确率为 87.6%-95.4%，近红外光透射图像的准确率为 68.0%-78.0%，光相干断层扫描图像的准确率为 88.7%-95.2%，全景射线照片的准确率为 86.1%-96.1%。汇总后的诊断比值比从 2.27 到 32767 不等。对于检测和分割模型，由于报告的异质性，无法进行有用的汇总。