Imaging modalities to inform the detection and diagnosis of early caries

Diagnostic performance of artificial intelligence-aided caries detection on bitewing radiographs: a systematic review and meta-analysis

The accuracy of artificial intelligence-aided (AI) caries diagnosis can vary considerably depending on numerous factors. This review aimed to assess the diagnostic accuracy of AI models for caries detection and classification on bitewing radiographs. Publications after 2010 were screened in five databases. A customized risk of bias (RoB) assessment tool was developed and applied to the 14 articles that met the inclusion criteria out of 935 references. Dataset sizes ranged from 112 to 3686 radiographs. While 86 % of the studies reported a model with an accuracy of ≥80 %, most exhibited unclear or high risk of bias. Three studies compared the model's diagnostic performance to dentists, in which the models consistently showed higher average sensitivity. Five studies were included in a bivariate diagnostic random-effects meta-analysis for overall caries detection. The diagnostic odds ratio was 55.8 (95 % CI= 28.8 - 108.3), and the summary sensitivity and specificity were 0.87 (0.76 - 0.94) and 0.89 (0.75 - 0.960), respectively. Independent meta-analyses for dentin and enamel caries detection were conducted and showed sensitivities of 0.84 (0.80 - 0.87) and 0.71 (0.66 - 0.75), respectively. Despite the promising diagnostic performance of AI models, the lack of high-quality, adequately reported, and externally validated studies highlight current challenges and future research needs.

Classification of Caries Based on CBCT: A Deep Learning Network Interpretability Study

This study aimed to create a caries classification scheme based on cone-beam computed tomography (CBCT) and develop two deep learning models to improve caries classification accuracy. A total of 2713 axial slices were obtained from CBCT images of 204 carious teeth. Both classification models were trained and tested using the same pretrained classification networks on the dataset, including ResNet50_vd, MobileNetV3_large_ssld, and ResNet50_vd_ssld. The first model was used directly to classify the original images (direct classification model). The second model incorporated a presegmentation step for interpretation (interpretable classification model). Performance evaluation metrics including accuracy, precision, recall, and F1 score were calculated. The Local Interpretable Model-agnostic Explanations (LIME) method was employed to elucidate the decision-making process of the two models. In addition, a minimum distance between caries and pulp was introduced for determining the treatment strategies for type II carious teeth. The direct model that utilized the ResNet50_vd_ssld network achieved top accuracy, precision, recall, and F1 score of 0.700, 0.786, 0.606, and 0.616, respectively. Conversely, the interpretable model consistently yielded metrics surpassing 0.917, irrespective of the network employed. The LIME algorithm confirmed the interpretability of the classification models by identifying key image features for caries classification. Evaluation of treatment strategies for type II carious teeth revealed a significant negative correlation (p < 0.01) with the minimum distance. These results demonstrated that the CBCT-based caries classification scheme and the two classification models appeared to be acceptable tools for the diagnosis and categorization of dental caries.

ORCA-EFCD consensus report on clinical recommendation for caries diagnosis. Paper I: caries lesion detection and depth assessment

OBJECTIVES

The aim of the present consensus paper was to provide recommendations for clinical practice considering the use of visual examination, dental radiography and adjunct methods for primary caries detection.

MATERIALS AND METHODS

The executive councils of the European Organisation for Caries Research (ORCA) and the European Federation of Conservative Dentistry (EFCD) nominated ten experts each to join the expert panel. The steering committee formed three work groups that were asked to provide recommendations on (1) caries detection and diagnostic methods, (2) caries activity assessment and (3) forming individualised caries diagnoses. The experts responsible for "caries detection and diagnostic methods" searched and evaluated the relevant literature, drafted this manuscript and made provisional consensus recommendations. These recommendations were discussed and refined during the structured process in the whole work group. Finally, the agreement for each recommendation was determined using an anonymous Delphi survey.

RESULTS

Recommendations (N = 8) were approved and agreed upon by the whole expert panel: visual examination (N = 3), dental radiography (N = 3) and additional diagnostic methods (N = 2). While the quality of evidence was found to be heterogeneous, all recommendations were agreed upon by the expert panel.

CONCLUSION

Visual examination is recommended as the first-choice method for the detection and assessment of caries lesions on accessible surfaces. Intraoral radiography, preferably bitewing, is recommended as an additional method. Adjunct, non-ionising radiation methods might also be useful in certain clinical situations.

CLINICAL RELEVANCE

The expert panel merged evidence from the scientific literature with practical considerations and provided recommendations for their use in daily dental practice.

Comparison of artificial intelligence vs. junior dentists' diagnostic performance based on caries and periapical infection detection on panoramic images

Background

There is information missing in the literature about the comparison of dentists vs. artificial intelligence (AI) based on diagnostic capability. The aim of this study is to evaluate the diagnostic performance based on radiological diagnoses regarding caries and periapical infection detection by comparing AI software with junior dentists who have 1 or 2 years of experience, based on the valid determinations by specialist dentists.

Methods

In the initial stage of the study, 2 specialist dentists evaluated the presence of caries and periapical lesions on 500 digital panoramic radiographs, and the detection time was recorded in seconds. In the second stage, 3 junior dentists and an AI software performed diagnoses on the same panoramic radiographs, and the diagnostic results and durations were recorded in seconds.

Results

The AI and the three junior dentists, respectively, detected dental caries at a sensitivity (SEN) of 0.907, 0.889, 0.491, 0.907; a specificity (SPEC) of 0.760, 0.740, 0.454, 0.696; a positive predictive value (PPV) of 0.693, 0.470, 0.155, 0.666; a negative predictive value (NPV) of 0.505, 0.415, 0.275, 0.367 and a F1-score of 0.786, 0.615, 0.236, 0.768. The AI and the three junior dentists respectively detected periapical lesions at an SEN of 0.973, 0.962, 0.758, 0.958; a SPEC of 0.629, 0.421, 0.404, 0.621; a PPV of 0.861, 0.651, 0.312, 0.648; a NPV of 0.689, 0.673, 0.278, 0.546 and an F1-score of 0.914, 0.777, 0.442, 0.773. The AI software gave more accurate results, especially in detecting periapical lesions. On the other hand, in caries detection, the underdiagnosis rate was high for both AI and junior dentists.

Conclusions

Regarding the evaluation time needed, AI performed faster, on average.

Current Approaches to Diagnosis of Early Proximal Carious Lesion: A Literature Review

Integrating technological tools with clinical visual examination for caries detection and diagnosis can improve preventative measures in dentistry, resulting in decreased treatment expenses and reduced time and costs associated with testing potential anticaries agents. This article provides an overview of the conventional and new emerging modern technologies that can assist dental professionals in the early detection and diagnosis of dental caries. These technologies aid in assessing the progression of carious lesions and monitoring them quantitatively or qualitatively over time. Traditional techniques (visual, tactile, and radiographic) have limitations in diagnosing early proximal caries accurately. Novel methods like fluorescence and transillumination, as well as advanced tools like OCT (optical coherence tomography), laser fluorescence, and QLF (quantitative light-induced fluorescence), are effective for early caries detection. Optical methods like fluorescence and transillumination are particularly successful in identifying initial caries stages. Moreover, this review highlights the clinical relevance of these methods and discusses potential future technologies like terahertz imaging and artificial intelligence (AI)-based approaches.

Assessment of some incipient caries risk factors in adolescents

Relevance. Risk assessment of carious lesion onset remains relevant due to the high incidence rate. The article presents the data on the impact of permanent dental enamel functional condition and microbial factor on incipient caries onset in adolescents.Purpose: The study aimed to investigate the etiology and pathogenesis risk characteristics of incipient caries onset in adolescents.Material and methods. The study included 90 adolescents aged 11-17 y.o. from Penza city. At the clinical stage, we studied adolescents’ permanent teeth vulnerability to caries; then, we formed the study groups according to WHO criteria (Group 1 – moderate, Group 2 – high, Group 3 – the very high intensity of caries) and Group 4 included children of the same age without caries. Vital staining and electric pulp testing with the “DentEst” device (Geosoft, Russia) detected white spot lesions. The OHI-S and enamel acid resistance test (TER-test) evaluated the level of oral hygiene. The laboratory stage determined the number of mixed saliva cells contaminated with bacterial microflora (microflora contamination coefficient) to define the bacterial load in the mixed saliva of the examined adolescents.Results. Besides high clinical rate of white spot lesions (intensity rate 3.10 ± 0.05 and demineralization degree 5.90 ± 0.08 μA) linked to poor oral hygiene level according to OHI-S (2.80 ± 0.13), the examined children of Group 3 (very high caries intensity) revealed a decrease in enamel acid resistance (TER-test 6.50 ± 0.22) and increased bacterial load of mixed saliva – microflora contamination coefficient (48.12 ± 0.80%). Differences with the same parameters in Group 4 (without caries) were statistically significant (P < 0.05). The study of the statistical relationship between enamel demineralization degree and the level of mixed saliva bacterial load (microflora contamination coefficient) detected a positive correlation between the studied parameters of moderate and high power and received the following correlation coefficient values in Group 1 (R = 0.46), 2 and 3 (R = 0.73 and R = 0.78) respectively.Conclusion. Assessment of some risk factors for white spot lesion onset and monitoring of changes may include the analysis of clinical and laboratory data on the hard-dental-tissue condition and mixed saliva bacterial load determination (microflora contamination coefficient).

Intraoral optical coherence tomography and angiography combined with autofluorescence for dental assessment

There remains a clinical need for an accurate and non-invasive imaging tool for intraoral evaluation of dental conditions. Optical coherence tomography (OCT) is a potential candidate to meet this need, but the design of current OCT systems limits their utility in the intraoral examinations. The inclusion of light-induced autofluorescence (LIAF) can expedite the image collection process and provides a large field of view for viewing the condition of oral tissues. This study describes a novel LIAF-OCT system equipped with a handheld probe designed for intraoral examination of microstructural (via OCT) and microvascular information (via OCT angiography, OCTA). The handheld probe is optimized for use in clinical studies, maintaining the ability to detect and image changes in the condition of oral tissue (e.g., hard tissue damage, presence of dental restorations, plaque, and tooth stains). The real-time LIAF provides guidance for OCT imaging to achieve a field of view of approximately 6.9 mm × 7.8 mm, and a penetration depth of 1.5 mm to 3 mm depending on the scattering property of the target oral tissue. We demonstrate that the proposed system is successful in capturing reliable depth-resolved images from occlusal and palatal surfaces and offers added design features that can enhance its usability in clinical settings.

Visual or visual-tactile examination to detect and inform the diagnosis of enamel caries

BACKGROUND

The detection and diagnosis of caries at the initial (non-cavitated) and moderate (enamel) levels of severity is fundamental to achieving and maintaining good oral health and prevention of oral diseases. An increasing array of methods of early caries detection have been proposed that could potentially support traditional methods of detection and diagnosis. Earlier identification of disease could afford patients the opportunity of less invasive treatment with less destruction of tooth tissue, reduce the need for treatment with aerosol-generating procedures, and potentially result in a reduced cost of care to the patient and to healthcare services.

OBJECTIVES

To determine the diagnostic accuracy of different visual classification systems for the detection and diagnosis of non-cavitated coronal dental caries for different purposes (detection and diagnosis) and in different populations (children or adults).

SEARCH METHODS

Cochrane Oral Health's Information Specialist undertook a search of the following databases: MEDLINE Ovid (1946 to 30 April 2020); Embase Ovid (1980 to 30 April 2020); US National Institutes of Health Ongoing Trials Register (ClinicalTrials.gov, to 30 April 2020); and the World Health Organization International Clinical Trials Registry Platform (to 30 April 2020). We studied reference lists as well as published systematic review articles.

SELECTION CRITERIA

We included diagnostic accuracy study designs that compared a visual classification system (index test) with a reference standard (histology, excavation, radiographs). This included cross-sectional studies that evaluated the diagnostic accuracy of single index tests and studies that directly compared two or more index tests. Studies reporting at both the patient or tooth surface level were included. In vitro and in vivo studies were considered. Studies that explicitly recruited participants with caries into dentine or frank cavitation were excluded. We also excluded studies that artificially created carious lesions and those that used an index test during the excavation of dental caries to ascertain the optimum depth of excavation.

DATA COLLECTION AND ANALYSIS

We extracted data independently and in duplicate using a standardised data extraction and quality assessment form based on QUADAS-2 specific to the review context. Estimates of diagnostic accuracy were determined using the bivariate hierarchical method to produce summary points of sensitivity and specificity with 95% confidence intervals (CIs) and regions, and 95% prediction regions. The comparative accuracy of different classification systems was conducted based on indirect comparisons. Potential sources of heterogeneity were pre-specified and explored visually and more formally through meta-regression.

MAIN RESULTS

We included 71 datasets from 67 studies (48 completed in vitro) reporting a total of 19,590 tooth sites/surfaces. The most frequently reported classification systems were the International Caries Detection and Assessment System (ICDAS) (36 studies) and Ekstrand-Ricketts-Kidd (ERK) (15 studies). In reporting the results, no distinction was made between detection and diagnosis. Only two studies were at low risk of bias across all four domains, and 15 studies were at low concern for applicability across all three domains. The patient selection domain had the highest proportion of high risk of bias studies (49 studies). Four studies were assessed at high risk of bias for the index test domain, nine for the reference standard domain, and seven for the flow and timing domain. Due to the high number of studies on extracted teeth concerns regarding applicability were high for the patient selection and index test domains (49 and 46 studies respectively). Studies were synthesised using a hierarchical bivariate method for meta-analysis. There was substantial variability in the results of the individual studies: sensitivities ranged from 0.16 to 1.00 and specificities from 0 to 1.00. For all visual classification systems the estimated summary sensitivity and specificity point was 0.86 (95% CI 0.80 to 0.90) and 0.77 (95% CI 0.72 to 0.82) respectively, diagnostic odds ratio (DOR) 20.38 (95% CI 14.33 to 28.98). In a cohort of 1000 tooth surfaces with 28% prevalence of enamel caries, this would result in 40 being classified as disease free when enamel caries was truly present (false negatives), and 163 being classified as diseased in the absence of enamel caries (false positives). The addition of test type to the model did not result in any meaningful difference to the sensitivity or specificity estimates (Chi²(4) = 3.78, P = 0.44), nor did the addition of primary or permanent dentition (Chi²(2) = 0.90, P = 0.64). The variability of results could not be explained by tooth surface (occlusal or approximal), prevalence of dentinal caries in the sample, nor reference standard. Only one study intentionally included restored teeth in its sample and no studies reported the inclusion of sealants. We rated the certainty of the evidence as low, and downgraded two levels in total for risk of bias due to limitations in the design and conduct of the included studies, indirectness arising from the in vitro studies, and inconsistency of results.

AUTHORS' CONCLUSIONS

Whilst the confidence intervals for the summary points of the different visual classification systems indicated reasonable performance, they do not reflect the confidence that one can have in the accuracy of assessment using these systems due to the considerable unexplained heterogeneity evident across the studies. The prediction regions in which the sensitivity and specificity of a future study should lie are very broad, an important consideration when interpreting the results of this review. Should treatment be provided as a consequence of a false-positive result then this would be non-invasive, typically the application of fluoride varnish where it was not required, with low potential for an adverse event but healthcare resource and finance costs. Despite the robust methodology applied in this comprehensive review, the results should be interpreted with some caution due to shortcomings in the design and execution of many of the included studies. Studies to determine the diagnostic accuracy of methods to detect and diagnose caries in situ are particularly challenging. Wherever possible future studies should be carried out in a clinical setting, to provide a realistic assessment of performance within the oral cavity with the challenges of plaque, tooth staining, and restorations, and consider methods to minimise bias arising from the use of imperfect reference standards in clinical studies.