Current status of dental caries diagnosis using cone beam computed tomography

AI-Assisted Detection of Interproximal, Occlusal, and Secondary Caries on Bite-Wing Radiographs: A Single-Shot Deep Learning Approach

Tooth decay is a common oral disease worldwide, but errors in diagnosis can often be made in dental clinics, which can lead to a delay in treatment. This study aims to use artificial intelligence (AI) for the automated detection and localization of secondary, occlusal, and interproximal (D1, D2, D3) caries types on bite-wing radiographs. The eight hundred and sixty bite-wing radiographs were collected from the School of Dentistry database. Pre-processing and data augmentation operations were performed. Interproximal (D1, D2, D3), secondary, and occlusal caries on bite-wing radiographs were annotated by two oral radiologists. The data were split into 80% for training, 10% for validation, and 10% for testing. The AI-based training process was conducted using the YOLOv8 algorithm. A clinical decision support system interface was designed using the Python PyQT5 library, allowing for the use of dental caries detection without the need for complex programming procedures. In the test images, the average precision, average sensitivity, and average F1 score values for secondary, occlusal, and interproximal caries were obtained as 0.977, 0.932, and 0.954, respectively. The AI-based dental caries detection system yielded highly successful results in the test, receiving full approval from dentists for clinical use. YOLOv8 has the potential to increase sensitivity and reliability while reducing the burden on dentists and can prevent diagnostic errors in dental clinics.

Dental Caries Detection and Classification in CBCT Images Using Deep Learning

OBJECTIVES

This study aimed to investigate the accuracy of deep learning algorithms to diagnose tooth caries and classify the extension and location of dental caries in cone beam computed tomography (CBCT) images. To the best of our knowledge, this is the first study to evaluate the application of deep learning for dental caries in CBCT images.

METHODS

The CBCT image dataset comprised 382 molar teeth with caries and 403 noncarious molar cases. The dataset was divided into a development set for training and validation and test set. Three images were obtained for each case, including axial, sagittal, and coronal. The test dataset was provided to a multiple-input convolutional neural network (CNN). The network made predictions regarding the presence or absence of dental decay and classified the lesions according to their depths and types for the provided samples. Accuracy, sensitivity, specificity, and F1 score values were measured for dental caries detection and classification.

RESULTS

The diagnostic accuracy, sensitivity, specificity, and F1 score for caries detection in carious molar teeth were 95.3%, 92.1%, 96.3%, and 93.2%, respectively, and for noncarious molar teeth were 94.8%, 94.3%, 95.8%, and 94.6%. The CNN network showed high sensitivity, specificity, and accuracy in classifying caries extensions and locations.

CONCLUSIONS

This research demonstrates that deep learning models can accurately identify dental caries and classify their depths and types with high accuracy, sensitivity, and specificity. The successful application of deep learning in this field will undoubtedly assist dental practitioners and patients in improving diagnostic and treatment planning in dentistry.

CLINICAL SIGNIFICANCE

This study showed that deep learning can accurately detect and classify dental caries. Deep learning can provide dental caries detection accurately. Considering the shortage of dentists in certain areas, using CNNs can lead to broader geographic coverage in detecting dental caries.

Comparison of accuracy cone-beam computed tomography and digital bitewing radiography for detection of recurrent caries under various restorative materials: in vitro study

OBJECTIVE

The aim of this study was to compare and evaluate diagnostic accuracy of two different CBCT scan modes and digital bitewing radiography for detection of recurrent caries under five different restorative materials, and determine the relationship between the types of restorative materials.

MATERIALS AND METHODS

In this in vitro study, 200 caries-free upper and lower premolars and molars were selected. A standard deep Class II cavities was created in the middle of the mesial surface of all teeth. In 100 teeth of the experimental and control groups, secondary caries was artificially demineralized. All teeth were filled with five types of restorative material including two types of conventional composite resins, flow composite resin, glass ionomer and amalgam. The teeth were imaged with high resolution (HIRes) and standard CBCT scan modes and digital bitewing. The AUC, sensitivity, specificity and areas under the ROC curve were calculated and verified through SPSS.

RESULTS

CBCT technique was the best option in diagnosing recurrent caries. The diagnostic accuracy and specificity of HIRes CBCT scan mode was significantly higher than standard mode (P = 0.031) and bitewing (P = 0.029) for detection of recurrent caries, especially under composite group. There were no significant differences in accuracy value of bitewing and standard CBCT scan mode.

CONCLUSION

CBCT showed higher accuracy and specificity on the detection of recurrent caries which was more accurate than bitewing radiography. The HIRes CBCT scan mode achieved the highest accuracy and performed the best in recurrent caries detection.

Micro-computed tomography in preventive and restorative dental research: A review

Purpose

The use of micro-computed tomography (micro-CT) scans in biomedical and dental research is growing rapidly. This study aimed to explore the scientific literature on approaches and applications of micro-CT in restorative dentistry.

Materials and Methods

An electronic search of publications from January 2009 to March 2021 was conducted using ScienceDirect, PubMed, and Google Scholar. The search included only English-language articles. Therefore, only studies that addressed recent advances and the potential uses of micro-CT in restorative and preventive dentistry were selected.

Results

Micro-CT is a tool that enables 3-dimensional imaging on a small scale with very high resolution. In this method, there is no need for sample preparation or slicing. Therefore, it is possible to examine the internal structure of tissue and the internal adaptation of materials to surfaces without destroying them. Due to these advantages, micro-CT has been recommended as a standard imaging tool in dental research for many applications such as tissue engineering, endodontics, restorative dentistry, and research on the mineral density of hard tissues and bone growth. However, the high costs of micro-CT, the time necessary for scanning and reconstruction, computer expertise requirements, and the enormous volume of information are drawbacks.

Conclusion

The potential of micro-CT as an emerging, accurate, non-destructive approach is clear, and the valuable research findings reported in the literature provide an impetus for researchers to perform future studies focusing on employing this method in dental research.

Applying synthetic radiography to intraoral tomosynthesis: a step towards achieving 3D imaging in the dental clinic

OBJECTIVES

A practical approach to three-dimensional (3D) intraoral imaging would have many potential applications in clinical dentistry. Stationary intraoral tomosynthesis (sIOT) is an experimental 3D imaging technology that holds promise. The purpose of this study was to explore synthetic radiography as a tool to improve the clinical utility of the images generated by an sIOT scan.

METHODS

Extracted tooth specimens containing either caries adjacent to restorations (CAR) or vertical root fractures (VRF) were imaged by sIOT and standard dental radiography devices. Qualitative assessments were used to compare the conspicuity of these pathologies in the standard radiographs and in a set of multi-view synthetic radiographs generated from the information collected by sIOT.

RESULTS

The sIOT-based synthetic 2D radiographs contained less artefact than the image slices in the reconstructed 3D stack, which is the conventional approach to displaying information from a tomosynthesis scan. As a single sIOT scan can be used to generate synthetic radiographs from multiple viewing angles, the interproximal space was less likely to be obscured in the synthetic images compared to the standard radiograph. Additionally, the multi-view synthetic radiographs can potentially improve the display of CAR and VRFs as compared to a single standard radiograph.

CONCLUSIONS

This preliminary experience combining synthetic radiography and sIOT in extracted tooth models is encouraging and supports the ongoing study of this promising approach to 3D intraoral imaging with many potential applications.

Relationship between CNR and visibility of anatomical structures of cone-beam computed tomography images under different exposure parameters

OBJECTIVES

The purpose of this study was to investigate the image quality of cone beam CT (CBCT) under different exposure parameters and the relationship between contrast-to-noise and visibility of eight anatomical structures.

METHODS

CBCT images for the evaluation of subjective image quality were acquired on an anthropopathic phantom containing a human skeleton embedded in soft tissue equivalent materials using 25 exposure protocols. Visibility of eight anatomical structures was evaluated by five independent observers. Using the SEDENTEXCT IQ Image Quality phantom, the contrast-to-noise ratio (CNR) was calculated by ImageJ software.

RESULTS

A reduction on the visibility of anatomical structures was seen under lower exposure parameters. However, for 84% of the protocols, visibility of anatomical structures remained acceptable even under some lower parameter settings. As CNR increased, the visibility of anatomical structures also increased correspondingly. A change point could be found in the CNR interval 29.42-36.51 after which the visibility of anatomical structures no longer increases with the increase of CNR.

CONCLUSIONS

Although CNR decrease under a lower exposure parameter, the image quality often remained acceptable at exposure levels below the manufacture's recommended settings. It is possible to standardize subjective image quality by physical factors. Currently, it is not possible to predetermine a change point CNR value due to different CBCT machine and variation of diagnostic tasks.

Imaging of Odontogenic Infections

Odontogenic infections represent a common clinical problem in patients of all ages. The presence of teeth enables the direct spread of inflammatory products from dental caries, trauma, and/or periodontal disease into the maxilla and mandible. The radiographic changes seen depend on the type and duration of the inflammatory process and host body response. Imaging plays a central role in identifying the source of infection and the extent of the disease spread and in detecting any complications. Many different imaging modalities can be used. The radiographic features associated with acute and chronic inflammatory processes are discussed.

Comparison of cone beam computed tomography and digital intraoral radiography performance in the detection of artificially induced recurrent caries-like lesions

OBJECTIVES

The aim of this study was to compare the performance of cone beam computed tomography (CBCT) and digital radiography in the detection of artificial recurrent caries-like lesions under amalgam and composite fillings.

STUDY DESIGN

The study included class II cavities in 30 molars that had been filled with amalgam. Fifteen of those molars had the restoration-enamel interface artificially demineralized. Phantoms were prepared, and CBCT images were acquired with 2 units in 3 voxel sizes (K9000, 0.076 mm; i-CAT, 0.2 mm and 0.4 mm). Intraoral radiographs were obtained with 3 systems (Digora, VistaScan, and RVG-6100). Amalgam fillings were then replaced by composite, and new images were obtained. Three examiners assessed all of the images. Sensitivity, specificity, accuracy, and receiver operating characteristic curve were calculated and verified through analysis of variance and the Tukey test.

RESULTS

There were no significant differences in sensitivity and specificity when the same restorative material was present or when the restorative materials were compared with the imaging technique as a constant. As for accuracy and receiver operating characteristic curve, there were statistically significant differences when the 2 materials were compared, and there were differences in the amalgam group when the imaging modalities were compared.

CONCLUSIONS

CBCT performed similarly to intraoral radiography in detecting demineralization under restorations. However, the voxel size and the type of restorative material influenced its performance.

Ex vivo evaluation of new 2D and 3D dental radiographic technology for detecting caries

OBJECTIVES

Proximal dental caries remains a prevalent disease with only modest detection rates by current diagnostic systems. Many new systems are available without controlled validation of diagnostic efficacy. The objective of this study was to evaluate the diagnostic efficacy of three potentially promising new imaging systems.

METHODS

This study evaluated the caries detection efficacy of Schick 33 (Sirona Dental, Salzburg, Austria) intraoral digital detector images employing an advanced sharpening filter, Planmeca ProMax(®) (Planmeca Inc., Helsinki, Finland) extraoral "panoramic bitewing" images and Sirona Orthophos XG3D (Sirona Dental) CBCT images with advanced artefact reduction. Conventional photostimulable phosphor images served as the control modality. An ex vivo study design using extracted human teeth, ten expert observers and micro-CT ground truth was employed.

RESULTS

Receiver operating characteristic analysis indicated similar diagnostic efficacy of all systems (ANOVA p > 0.05). The sensitivity of the Schick 33 images (0.48) was significantly lower than the other modalities (0.53-0.62). The specificity of the Planmeca images (0.86) was significantly lower than Schick 33 (0.96) and XG3D (0.97). The XG3D showed significantly better cavitation detection sensitivity (0.62) than the other modalities (0.48-0.57).

CONCLUSIONS

The Schick 33 images demonstrated reduced caries sensitivity, whereas the Planmeca panoramic bitewing images demonstrated reduced specificity. XG3D with artefact reduction demonstrated elevated sensitivity and specificity for caries detection, improved depth accuracy and substantially improved cavitation detection. Care must be taken to recognize potential false-positive caries lesions with Planmeca panoramic bitewing images. Use of CBCT for caries detection must be carefully balanced with the presence of metal artefacts, time commitment, financial cost and radiation dose.

Optimization of dental CBCT exposures through mAs reduction

OBJECTIVES

To investigate the effect of tube current-exposure time (mAs) reduction on clinical and technical image quality for different CBCT scanners, and to determine preliminary minimally acceptable values for the mAs and contrast-to-noise ratio (CNR) in CBCT.

METHODS

A polymethyl methacrylate (PMMA) phantom and an anthropomorphic skull phantom, containing a human skeleton embedded in polyurethane, were scanned using four CBCT devices, including seven exposure protocols. For all protocols, the mAs was varied within the selectable range. Using the PMMA phantom, the CNRAIR was measured and corrected for voxel size. Eight axial slices and one coronal slice showing various anatomical landmarks were selected for each CBCT scan of the skull phantom. The slices were presented to six dentomaxillofacial radiologists, providing scores for various anatomical and diagnostic parameters.

RESULTS

A hyperbolic relationship was seen between CNRAIR and mAs. Similarly, a gradual reduction in clinical image quality was seen at lower mAs values; however, for several protocols, image quality remained acceptable for a moderate or large mAs reduction compared with the standard exposure setting, depending on the clinical application. The relationship between mAs, CNRAIR and observer scores was different for each CBCT device. Minimally acceptable values for mAs were between 9 and 70, depending on the criterion and clinical application.

CONCLUSIONS

Although noise increased at a lower mAs, clinical image quality often remained acceptable at exposure levels below the manufacturer's recommended setting, for certain patient groups. Currently, it is not possible to determine minimally acceptable values for image quality that are applicable to multiple CBCT models.

An in vitro comparison of diagnostic accuracy of cone beam computed tomography and phosphor storage plate to detect simulated occlusal secondary caries under amalgam restoration

BACKGROUND

This study was aimed to compare the diagnostic accuracy and feasibility of cone beam computed tomography (CBCT) with phosphor storage plate (PSP) in detection of simulated occlusal secondary caries.

MATERIALS AND METHODS

In this in vitro descriptive-comparative study, a total of 80 slots of class I cavities were prepared on 80 extracted human premolars. Then, 40 teeth were randomly selected out of this sample and artificial carious lesions were created on these teeth by a round diamond bur no. 1/2. All 80 teeth were restored with amalgam fillings and radiographs were taken, both with PSP system and CBCT. All images were evaluated by three calibrated observers. The area under the receiver operating characteristic curve was used to compare the diagnostic accuracy of two systems. SPSS (SPSS Inc., Chicago, IL, USA) was adopted for statistical analysis. The difference between Az value of bitewing and CBCT methods were compared by pairwise comparison method. The inter- and intra-operator agreement was assessed by kappa analysis (P < 0.05).

RESULTS

The mean Az value for bitewings and CBCT was 0.903 and 0.994, respectively. Significant differences were found between PSP and CBCT (P = 0.010). The kappa value for inter-observer agreement was 0.68 and 0.76 for PSP and CBCT, respectively. The kappa value for intra-observer agreement was 0.698 (observer 1, P = 0.000), 0.766 (observer 2, P = 0.000) and 0.716 (observer 3, P = 0.000) in PSP method, and 0.816 (observer 1, P = 0.000), 0.653 (observer 2, P = 0.000) and 0.744 (observer 3, P = 0.000) in CBCT method.

CONCLUSION

This in vitro study, with a limited number of samples, showed that the New Tom VGI Flex CBCT system was more accurate than the PSP in detecting the simulated small secondary occlusal caries under amalgam restoration.

The occurrence of dental caries is associated with atherosclerosis

OBJECTIVE

Previous studies have suggested that marginal periodontitis is a risk factor for developing atherosclerosis. The objective of this study was to determine whether caries may also be associated with atherosclerosis.

METHODS

The computed tomography data sets of 292 consecutive patients, 137 women and 155 men with a mean age of 54.1±17.3 years, were analyzed. Caries were quantified based on the number of decayed surfaces of all the teeth, and periodontitis was quantified on the basis of the horizontal bone loss in the jaw. The presence of chronic apical periodontitis (CAP) was assessed, and the aortic atherosclerotic burden was quantified using a calcium scoring method.

RESULTS

The patients with <1 caries surfaces/tooth had a lower atherosclerotic burden (0.13±0.61 mL) than patients with ≥1 caries surfaces/tooth. The atherosclerotic burden was greater in patients with a higher number of lesions with pulpal involvement and more teeth with chronic apical periodontitis. In the logistical regression models, age (Wald 49.3), number of caries per tooth (Wald 26.4), periodontitis (Wald 8.6), and male gender (Wald 11) were found to be independent risk factors for atherosclerosis. In the linear regression analyses, age and the number of decayed surfaces per tooth were identified as influencing factors associated with a higher atherosclerotic burden, and the number of restorations per tooth was associated with a lower atherosclerotic burden.

CONCLUSION

Dental caries, pulpal caries, and chronic apical periodontitis are associated positively, while restorations are associated inversely, with aortic atherosclerotic burden. Prospective studies are required to confirm these observations and answer the question of possible causality.

Evaluation of Cone Beam Computed Tomography (CBCT) System: Comparison with Intraoral Periapical Radiography in Proximal Caries Detection

Background and aims

With the introduction of Cone Beam Computed Tomography (CBCT) in dentistry, a question has been raised whether the technique significantly increases the diagnostic accuracy in comparison with other techniques or not. Therefore, the present study was undertaken to assess the accuracy of CBCT modality in detecting proximal carious lesions as compared to conventional periapical radiographs.

Materials and methods

This diagnostic study was carried out on 84 human extracted molars and premolars. The teeth were mounted and divided in 28 blocks of 3 teeth. Periapical and CBCT images of teeth were obtained. Five observers scored the images for the detection of proximal carious lesions using a 2-point scale (caries, present; caries, absent). The gold standard was determined by histopathologic sections. Sensitivity, specificity, PPV, NPV and receiver operating charac-teristics (ROC) curves were traced for observers in both systems. The results were analyzed by paired t-test.

Results

The area under the ROC curve, sensitivity, specificity, accuracy, positive and negative predictive values of CBCT images were 0.568, 0.835, 0.637, 0.714, 0.598 and 0.856, respectively. These parameters were 0.432, 0.837, 0.722, 0.77, 0.687 and 0.858 for the periapical conventional technique, respectively.

Conclusion

The CBCT images did not enhance detection of proximal caries in comparison with periapical images.