Non-Cochrane · DTA · PM41634741
Artificial intelligence for binary dental caries diagnosis using intraoral images and dental radiographs: a systematic review and meta-analysis.
Lai Jing, Guo Shanshan, Wang Ke, et al. · BMC oral health · 2026 · PubMed · doi:10.1186/s12903-026-07770-4
Findings
Population Dental images (radiographs and clinical intraoral images) assessed for caries
12 findings
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Pooled specificity | Specificity 0.91 [0.88, 0.94] GRADE not reported 13 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Pooled sensitivity | Sensitivity 0.86 [0.82, 0.89] GRADE not reported 13 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Area under the SROC curve (AUC) | AUC 0.94 [0.92, 0.96] GRADE not reported 13 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Pooled sensitivity Image type: dental radiographs | Sensitivity 0.83 [0.79, 0.87] GRADE not reported 8 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Pooled specificity Image type: dental radiographs | Specificity 0.92 [0.87, 0.95] GRADE not reported 8 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Area under the SROC curve (AUC) Image type: dental radiographs | AUC 0.93 [0.90, 0.95] GRADE not reported 8 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Area under the SROC curve (AUC) Image type: clinical intraoral images | AUC 0.95 [0.93, 0.97] GRADE not reported 5 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Pooled sensitivity Image type: clinical intraoral images | Sensitivity 0.88 [0.83, 0.92] GRADE not reported 5 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Pooled specificity Image type: clinical intraoral images | Specificity 0.91 [0.86, 0.94] GRADE not reported 5 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Pooled sensitivity Unit of analysis: tooth-level | Sensitivity 0.87 [0.83, 0.89] GRADE not reported 11 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Area under the SROC curve (AUC) Unit of analysis: tooth-level | AUC 0.94 [0.92, 0.96] GRADE not reported 11 studies |
| AI (deep learning) models for binary caries classification | Reference standard (expert examiners or clinical/diagnostic reference) | Pooled specificity Unit of analysis: tooth-level | Specificity 0.91 [0.88, 0.94] GRADE not reported 11 studies |
Included primary studies 40
Open in Studies| Study | Year | Also included by | Outcomes it informs here | Trial data |
|---|---|---|---|---|
| Chen 2022 Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method. PMID:36215971 | 2022 | 2 other reviews | Pooled sensitivity | not extracted yet |
| Kuhnisch 2022 Caries Detection on Intraoral Images Using Artificial Intelligence. PMID:34416824 | 2022 | 2 other reviews | Pooled sensitivity | not extracted yet |
| Lee 2018 Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm. PMID:30056118 | 2018 | 2 other reviews | Pooled sensitivity | not extracted yet |
| Vinayahalingam 2021 Classification of caries in third molars on panoramic radiographs using deep learning. PMID:34131266 | 2021 | 2 other reviews | Pooled sensitivity | not extracted yet |
| Lee 2018 Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm DOI:10.1016/j.jdent.2018.07.015 | 2018 | 1 other review | not stated | not extracted yet |
| Oztekin 2023 An Explainable Deep Learning Model to Prediction Dental Caries Using Panoramic Radiograph Images. PMID:36673036 | 2023 | 1 other review | Pooled sensitivity | not extracted yet |
| Zhang 2024 Diagnostic accuracy of artificial intelligence-assisted caries detection: a clinical evaluation. PMID:39285427 | 2024 | 1 other review | Pooled sensitivity | not extracted yet |
| Alam 2024 Al-Based Detection of Dental Caries: Comparative Analysis with Clinical Examination. PMID:38595520 | 2024 | this review only | not stated | not extracted yet |
| AlSayyed 2023 Analysis of the influence of perceived value on browsing behavior in C2C E-Commerce with depth of review as antecedent DOI:10.5267/j.ijdns.2023.8.002 | 2023 | this review only | not stated | not extracted yet |
| Bui 2021 Deep Fusion Feature Extraction for Caries Detection on Dental Panoramic Radiographs DOI:10.3390/app11052005 | 2021 | this review only | not stated | not extracted yet |
| Das 2024 Evaluating the Accuracy of AI-Based Software vs Human Interpretation in the Diagnosis of Dental Caries Using Intraoral Radiographs: An RCT. PMID:38595404 | 2024 | this review only | not stated | not extracted yet |
| ForouzeshFar 2024 Dental Caries diagnosis from bitewing images using convolutional neural networks DOI:10.1186/s12903-024-03973-9 | 2024 | this review only | not stated | not extracted yet |
| ForouzeshFar 2024 Dental Caries diagnosis from bitewing images using convolutional neural networks. PMID:38341526 | 2024 | this review only | not stated | not extracted yet |
| Frenkel 2024 Caries Detection and Classification in Photographs Using an Artificial Intelligence-Based Model—An External Validation Study DOI:10.3390/diagnostics14202281 | 2024 | this review only | not stated | not extracted yet |
| Frenkel 2024 Caries Detection and Classification in Photographs Using an Artificial Intelligence-Based Model-An External Validation Study. PMID:39451605 | 2024 | this review only | Pooled sensitivity | not extracted yet |
| Holtkamp 2021 Generalizability of Deep Learning Models for Caries Detection in Near-Infrared Light Transillumination Images DOI:10.3390/jcm10050961 | 2021 | this review only | not stated | not extracted yet |
| Holtkamp 2021 Generalizability of Deep Learning Models for Caries Detection in Near-Infrared Light Transillumination Images. PMID:33804562 | 2021 | this review only | not stated | not extracted yet |
| Kang 2024 Diagnostic accuracy of dental caries detection using ensemble techniques in deep learning with intraoral camera images DOI:10.1371/journal.pone.0310004 | 2024 | this review only | not stated | not extracted yet |
| Kang 2024 Diagnostic accuracy of dental caries detection using ensemble techniques in deep learning with intraoral camera images. PMID:39241044 | 2024 | this review only | Pooled sensitivity | not extracted yet |
| Kawazu 2024 DOI:10.1007/s40846-023-00874-1 | NR | this review only | not stated | not extracted yet |
| Lasri 2023 Automated Detection of Dental Caries from Oral Images using Deep Convolutional Neural Networks DOI:10.3991/ijoe.v19i18.45133 | 2023 | this review only | not stated | not extracted yet |
| Liu 2024 Artificial intelligence for caries detection: a novel diagnostic tool using deep learning algorithms DOI:10.1007/s11282-024-00741-x | 2024 | this review only | not stated | not extracted yet |
| Liu 2024 Artificial intelligence for caries detection: a novel diagnostic tool using deep learning algorithms. PMID:38498223 | 2024 | this review only | Pooled sensitivity | not extracted yet |
| Park 2023 Tooth caries classification with quantitative light-induced fluorescence (QLF) images using convolutional neural network for permanent… DOI:10.1186/s12903-023-03669-6 | 2023 | this review only | not stated | not extracted yet |
| Park 2023 Tooth caries classification with quantitative light-induced fluorescence (QLF) images using convolutional neural network for permanent… PMID:38066624 | 2023 | this review only | Pooled sensitivity | not extracted yet |
| Portella 2023 Improving accuracy of early dental carious lesions detection using deep learning-based automated method DOI:10.1007/s00784-023-05355-x | 2023 | this review only | not stated | not extracted yet |
| Portella 2023 Improving accuracy of early dental carious lesions detection using deep learning-based automated method. PMID:37906303 | 2023 | this review only | not stated | not extracted yet |
| Schwendicke 2020 Deep learning for caries lesion detection in near-infrared light transillumination images: A pilot study DOI:10.1016/j.jdent.2019.103260 | 2020 | this review only | not stated | not extracted yet |
| Schwendicke 2020 Deep learning for caries lesion detection in near-infrared light transillumination images: A pilot study. PMID:31821853 | 2020 | this review only | not stated | not extracted yet |
| Szabo 2024 Validation of artificial intelligence application for dental caries diagnosis on intraoral bitewing and periapical radiographs DOI:10.1016/j.jdent.2024.105105 | 2024 | this review only | not stated | not extracted yet |
| Szabo 2024 Validation of artificial intelligence application for dental caries diagnosis on intraoral bitewing and periapical radiographs. PMID:38821394 | 2024 | this review only | Pooled sensitivity | not extracted yet |
| Taleb 2022 Self-Supervised Learning Methods for Label-Efficient Dental Caries Classification DOI:10.3390/diagnostics12051237 | 2022 | this review only | not stated | not extracted yet |
| Taleb 2022 Self-Supervised Learning Methods for Label-Efficient Dental Caries Classification. PMID:35626392 | 2022 | this review only | not stated | not extracted yet |
| Turosz 2024 Artificial Intelligence (AI) Assessment of Pediatric Dental Panoramic Radiographs (DPRs): A Clinical Study. PMID:39311330 | 2024 | this review only | not stated | not extracted yet |
| Vinayahalingam 2021 Classification of caries in third molars on panoramic radiographs using deep learning DOI:10.1038/s41598-021-92121-2 | 2021 | this review only | not stated | not extracted yet |
| Zhang 2024 Diagnostic accuracy of artificial intelligence-assisted caries detection: a clinical evaluation DOI:10.1186/s12903-024-04847-w | 2024 | this review only | not stated | not extracted yet |
| Zhou 2022 Context Aware Convolutional Neural Network for Children Caries Diagnosis on Dental Panoramic Radiographs DOI:10.1155/2022/6029245 | 2022 | this review only | not stated | not extracted yet |
| Zhou 2022 Context Aware Convolutional Neural Network for Children Caries Diagnosis on Dental Panoramic Radiographs. PMID:36188109 | 2022 | this review only | Pooled sensitivity | not extracted yet |
| Zhou 2023 Tooth Type Enhanced Transformer for Children Caries Diagnosis on Dental Panoramic Radiographs DOI:10.3390/diagnostics13040689 | 2023 | this review only | not stated | not extracted yet |
| Zhou 2023 Tooth Type Enhanced Transformer for Children Caries Diagnosis on Dental Panoramic Radiographs. PMID:36832177 | 2023 | this review only | Pooled sensitivity | not extracted yet |
Overlap with other reviews
Reviews that include the same primary studies are not independent evidence. Shared counts match studies by PMID, DOI or NCT, and otherwise by author and year (a probable match). Only the non-Cochrane dental reviews have study lists, so overlap with Cochrane reviews is not counted yet.
Review question
| Element | Planned (methods) | Found (results) |
|---|---|---|
| Population | Dental images (clinical intraoral images or dental radiographs) assessed for dental caries | Teeth, images and tooth surfaces from intraoral photographs, bitewing, periapical and panoramic radiographs, QLF and NILT (n=25 studies; 13 in meta-analysis) |
| Intervention | AI models performing binary diagnostic classification of dental caries | Deep learning models: CNNs, transformers, self-supervised learning (n=25) |
| Comparison | Reference standard (expert examiners) | Expert reference standard: 2 or more experts (n=13), single reader (n=7), diagnostic report (n=1), artificial lesions (n=1), not reported (n=3) |
| Outcomes | Sensitivity, specificity, accuracy, AUC | Pooled sensitivity, specificity, AUC (n=13) |
| Study designs | Diagnostic accuracy studies | Diagnostic accuracy studies (n=25) |
| Timing | Published January 2015 to June 2025 | Studies published 2018 to 2024 |