Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
(a) Representation of an incipient caries lesion, (b) bitewing image with incipient lesion highlighted, (c) representation of an advanced caries lesion, (d) bitewing image with advanced lesion highlighted.
Source publication
Dental caries is an extremely common problem in dentistry that affects a significant part of the population. Approximal caries are especially difficult to identify because their position makes clinical analysis difficult. Radiographic evaluation—more specifically, bitewing images—are mostly used in such cases. However, incorrect interpretations may...
Contexts in source publication
Context 1
... is also applicable for oral diseases, including dental caries. Nevertheless, due to the lack of early diagnosis, caries lesions are frequently detected in advanced stages (Figure 1d), in which restoration is the only effective treatment [1]. This is especially harmful in cases in which these restorative treatments demand general anesthesia, as for children and special needs patients [2,3], since the use of anesthesia increases the patient risk. ...
Context 2
... normal class consists of teeth with no lesion. The incipient class denotes teeth with superficial lesions affecting the enamel- Figure 1a,b. Finally, the advanced class refers to teeth with advanced lesions, affecting a considerable part of the tooth, expanding into the dentin and the pulp- ...
Citations
... ML can help dentists to improve diagnosis as a reliable second opinion [71]. Neural networks and image processing techniques were used to detect caries on proximal and occlusal surfaces of teeth [71,72]. Moutselos et al. utilized a dataset of 88 dental images for training a DL model (Mask R-CNN) to detect and classify caries specifically on the occlusal surfaces of teeth, where caries is most commonly found inside the pits and fissures. ...
Artificial intelligence (AI) has been recently introduced into clinical dentistry, and it has assisted professionals in analyzing medical data with unprecedented speed and an accuracy level comparable to humans. With the help of AI, meaningful information can be extracted from dental databases, especially dental radiographs, to devise machine learning (a subset of AI) models. This study focuses on models that can diagnose and assist with clinical conditions such as oral cancers, early childhood caries, deciduous teeth numbering, periodontal bone loss, cysts, peri-implantitis, osteoporosis, locating minor apical foramen, orthodontic landmark identification, temporomandibular joint disorders, and more. The aim of the authors was to outline by means of a review the state-of-the-art applications of AI technologies in several dental subfields and to discuss the efficacy of machine learning algorithms, especially convolutional neural networks (CNNs), among different types of patients, such as pediatric cases, that were neglected by previous reviews. They performed an electronic search in PubMed, Google Scholar, Scopus, and Medline to locate relevant articles. They concluded that even though clinicians encounter challenges in implementing AI technologies, such as data management, limited processing capabilities, and biased outcomes, they have observed positive results, such as decreased diagnosis costs and time, as well as early cancer detection. Thus, further research and development should be considered to address the existing complications.
... Multiple studies have explored lesion detection and classification [37,47,50,55,58]. These studies primarily employed deep neural networks to accurately detect and localize lesions by generating bounding boxes around them. ...
Dental caries occurs from the interaction between oral bacteria and sugars, generating acids that damage teeth over time. The importance of X-ray images for detecting oral problems is undeniable in dentistry. With technological advances, it is feasible to identify these lesions using techniques such as deep learning, machine learning, and image processing. Therefore, the survey and systematization of these methods are essential to determining the main computational approaches for identifying caries in X-ray images. In this systematic review, we investigated the primary computational methods used for classifying, detecting, and segmenting caries in X-ray images. Following the PRISMA methodology, we selected relevant studies and analyzed their methods, strengths, limitations, imaging modalities, evaluation metrics, datasets, and classification techniques. The review encompassed 42 studies retrieved from the Science Direct, IEEExplore, ACM Digital, and PubMed databases from the Computer Science and Health areas. The results indicate that 12% of the included articles utilized public datasets, with deep learning being the predominant approach, accounting for 69% of the studies. The majority of these studies (76%) focused on classifying dental caries, either in binary or multiclass classification. Panoramic imaging was the most commonly used radiographic modality, representing 29% of the cases studied. Overall, our systematic review provides a comprehensive overview of the computational methods employed in identifying caries in radiographic images and highlights trends, patterns, and challenges in this research field.
... The final database search yielded 935 unique citations. Of these, 62 potential references were identified, and 14 studies were included in the qualitative assessment (supplementary materials Appendix IV) [19][20][21][22][23][24][25][26][27][28][29][30][31][32]. There were several reasons for study exclusion as listed in Appendix V. ...
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.
... Bitewing radiographs are often used by dentists as an assistant tool to diagnose dental caries [25]. In some of the researches, caries diagnosis studies were performed on bitewing radiographs [19,20,26,27]. Correct detection and numbering of teeth during the examination can reduced the examination time and provide a better diagnosis [28]. ...
Objectives
The aim of this study was automatically detecting and numbering teeth in digital bitewing radiographs obtained from patients, and evaluating the diagnostic efficiency of decayed teeth in real time, using deep learning algorithms.
Methods
The dataset consisted of 1170 anonymized digital bitewing radiographs randomly obtained from faculty archives. After image evaluation and labeling process, the dataset was split into training and test datasets. This study proposed an end-to-end pipeline architecture consisting of three stages for matching tooth numbers and caries lesions to enhance treatment outcomes and prevent potential issues. Initially, a pre-trained convolutional neural network (CNN) utilized to determine the side of the bitewing images. Then, an improved CNN model YOLOv7 was proposed for tooth numbering and caries detection. In the final stage, our developed algorithm assessed which teeth have caries by comparing the numbered teeth with the detected caries, using the intersection over union value for the matching process.
Results
According to test results, the recall, precision, and F1-score values were 0.994, 0.987 and 0.99 for teeth detection, 0.974, 0.985 and 0.979 for teeth numbering, and 0.833, 0.866 and 0.822 for caries detection, respectively. For teeth numbering and caries detection matching performance; the accuracy, recall, specificity, precision and F1—Score values were 0.934, 0.834, 0.961, 0.851 and 0.842, respectively.
Conclusions
The proposed model exhibited good achievement, highlighting the potential use of CNNs for tooth detection, numbering, and caries detection, concurrently.
Clinical significance
CNNs can provide valuable support to clinicians by automating the detection and numbering of teeth, as well as the detection of caries on bitewing radiographs. By enhancing overall performance, these algorithms have the capacity to efficiently save time and play a significant role in the assessment process.
... Bayrakdar et al. [30] 2021 Detection of CLs Retrospective cohort 0 53 0 53 Lian et al. [31] 2021 Detection of CLs Cross-sectional 0 0 89 89 Moran et al. [32] 2021 Detection of CLs Cross-sectional 0 45 0 45 Mertens S et al. [33] 2021 Detection of CLs Randomized control trial 0 20 0 20 ...
... However, the dental panoramic radiographs used in this study were obtained from a single orthopantomograph, therefore, performance may vary using OPG from different manufacturers and Institutions. The CNN-based model studied by Moran et al. [32] showed promising results compared to the reference model (accuracy 0.73) suggesting potential application of the proposed method a supplementary resource for the dentist in the evaluation of bitewing images. Mertens et al. [33] focused on a CNN model that showed an AUC of 0.89 and a sensitivity of 0.81, with significant better Fig. 2 QUADAS-2 assessment of the individual risk of bias domains and applicability concerns results compared to five experienced dentists. ...
... For example, Bayrakdar et al. [30] demonstrated superior performance of the CNN algorithms under investigation, VGG-16 and U-Net, compared to experienced specialists in CLs detection. Similarly, the CNN-based models studied by Moran et al. [32] and Mertens et al. [33] reported significantly higher sensitivity and accuracy values compared to the reference test. As abovementioned, the model studied by Zhu et al. [40], also showed excellent performance using 124 orthopantomography examinations to train and validate the model. ...
Background
The aim of this systematic review is to evaluate the diagnostic performance of Artificial Intelligence (AI) models designed for the detection of caries lesion (CL).
Materials and methods
An electronic literature search was conducted on PubMed, Web of Science, SCOPUS, LILACS and Embase databases for retrospective, prospective and cross-sectional studies published until January 2023, using the following keywords: artificial intelligence (AI), machine learning (ML), deep learning (DL), artificial neural networks (ANN), convolutional neural networks (CNN), deep convolutional neural networks (DCNN), radiology, detection, diagnosis and dental caries (DC). The quality assessment was performed using the guidelines of QUADAS-2.
Results
Twenty articles that met the selection criteria were evaluated. Five studies were performed on periapical radiographs, nine on bitewings, and six on orthopantomography. The number of imaging examinations included ranged from 15 to 2900. Four studies investigated ANN models, fifteen CNN models, and two DCNN models. Twelve were retrospective studies, six cross-sectional and two prospective. The following diagnostic performance was achieved in detecting CL: sensitivity from 0.44 to 0.86, specificity from 0.85 to 0.98, precision from 0.50 to 0.94, PPV (Positive Predictive Value) 0.86, NPV (Negative Predictive Value) 0.95, accuracy from 0.73 to 0.98, area under the curve (AUC) from 0.84 to 0.98, intersection over union of 0.3–0.4 and 0.78, Dice coefficient 0.66 and 0.88, F1-score from 0.64 to 0.92. According to the QUADAS-2 evaluation, most studies exhibited a low risk of bias.
Conclusion
AI-based models have demonstrated good diagnostic performance, potentially being an important aid in CL detection. Some limitations of these studies are related to the size and heterogeneity of the datasets. Future studies need to rely on comparable, large, and clinically meaningful datasets.
Protocol
PROSPERO identifier: CRD42023470708
... AlexNet achieved an accuracy of 95.56%, making it a valuable tool for computer-aided diagnosis in dentistry. Moran et al. [15], utilized Inception and ResNet networks with three different learning rates (0.1, 0.01, 0.001), and after 2000 iterations, the Inception model with a 0.001 learning rate achieved the best results. The accuracy on the test set was 73.3%. ...
Background
Dental caries, also known as tooth decay, is a widespread and long-standing condition that affects people of all ages. This ailment is caused by bacteria that attach themselves to teeth and break down sugars, creating acid that gradually wears away at the tooth structure. Tooth discoloration, pain, and sensitivity to hot or cold foods and drinks are common symptoms of tooth decay. Although this condition is prevalent among all age groups, it is especially prevalent in children with baby teeth. Early diagnosis of dental caries is critical to preventing further decay and avoiding costly tooth repairs. Currently, dentists employ a time-consuming and repetitive process of manually marking tooth lesions after conducting radiographic exams. However, with the rapid development of artificial intelligence in medical imaging research, there is a chance to improve the accuracy and efficiency of dental diagnosis.
Methods
This study introduces a data-driven model for accurately diagnosing dental decay through the use of Bitewing radiology images using convolutional neural networks. The dataset utilized in this research includes 713 patient images obtained from the Samin Maxillofacial Radiology Center located in Tehran, Iran. The images were captured between June 2020 and January 2022 and underwent processing via four distinct Convolutional Neural Networks. The images were resized to 100 × 100 and then divided into two groups: 70% (4219) for training and 30% (1813) for testing. The four networks employed in this study were AlexNet, ResNet50, VGG16, and VGG19.
Results
Among different well-known CNN architectures compared in this study, the VGG19 model was found to be the most accurate, with a 93.93% accuracy.
Conclusion
This promising result indicates the potential for developing an automatic AI-based dental caries diagnostic model from Bitewing images. It has the potential to serve patients or dentists as a mobile app or cloud-based diagnosis service (clinical decision support system).
... The results showed an intersection over union (IoU) value of 0.785 and an accuracy and recall rate of 0.986 and 0.821, respectively [32] In a novel approach, researchers combined image processing techniques with Convolutional Neural Networks (CNNs) to identify and classify proximal dental caries in bitewing radiographic images. This groundbreaking method achieved an impressive accuracy rate of 73.3%, showcasing its potential to enhance the detection and categorization of dental caries, thus supporting early diagnosis and treatment planning [33]. Furthermore, another study [34] introduced an innovative classification and segmentation model specifically designed for endoscope images obtained from patients at the Department of Stomatology, People's Liberation Army General Hospital. ...
... The proposed method achieved impressive precision and recall values, highlighting its efficacy in accurately identifying dental structures and treatment patterns. A deep convolutional neural networkbased system was developed for analyzing dental periapical radiographs in this study [33]. The system showed potential in identifying different disease categories and severity levels based on periapical radiographs. ...
... The results showed an intersection over union (IoU) value of 0.785 and an accuracy and recall rate of 0.986 and 0.821, respectively [32] In a novel approach, researchers combined image processing techniques with Convolutional Neural Networks (CNNs) to identify and classify proximal dental caries in bitewing radiographic images. This groundbreaking method achieved an impressive accuracy rate of 73.3%, showcasing its potential to enhance the detection and categorization of dental caries, thus supporting early diagnosis and treatment planning [33]. Furthermore, another study [34] introduced an innovative classification and segmentation model specifically designed for endoscope images obtained from patients at the Department of Stomatology, People's Liberation Army General Hospital. ...
... The proposed method achieved impressive precision and recall values, highlighting its efficacy in accurately identifying dental structures and treatment patterns. A deep convolutional neural networkbased system was developed for analyzing dental periapical radiographs in this study [33]. The system showed potential in identifying different disease categories and severity levels based on periapical radiographs. ...
This review delves into the application of artificial intelligence (AI) and deep learning, particularly leveraging convolutional neural networks (CNNs), to enhance dental diagnostics and treatment planning. The primary focus is on the detection and classification of caries as well as the identification of teeth in diverse dental images. A thorough exploration was conducted across databases, including PubMed, IEEE Xplore, and arXiv.org, leading to the identification of 29 pertinent studies. These studies employ various neural network models, encompassing different dental image types and employing diverse performance metrics. The review succinctly outlines the key characteristics and outcomes of these studies, underscoring the remarkable accuracy and the promising potential of AI-driven approaches in the realms of caries detection and tooth identification.Acknowledging the existing limitations within the current body of research, such as small or non-representative datasets, variations in imaging techniques, and a lack of interpretabilityin deep learning models, the review emphasizes the need for future investigations. It suggests potential research directions aimed at overcoming these challenges, thereby facilitating the seamless integration of AI into routine dental practices.KeywordsArtificial intelligence,Caries detection,Tooth detection,Convolutional neural networks,Dental imaging.
... A literature review of Convolutional Neural Networks (CNNs) application in the segmentation of dental images is presented below. For Example, Moran et al. proposed a new method that merges image processing and conventional neural networks to detect caries using bitewing radiographs, achieving an accuracy of 73.3% [21]. Similarly, Lee et al. [22] evaluated the effectiveness of using a CNN algorithm to diagnose and detect caries on periapical radiographs, achieving an average accuracy of 86.3% for all testing types. ...
Dental radiographs, particularly bitewing radiographs, are widely used in dental diagnosis and treatment Dental image segmentation is difficult for various reasons, such as intricate structures, low contrast, noise, roughness, and unclear borders, resulting in poor image quality. Recent developments in deep learning models have improved performance in analyzing dental images. In this research, our primary objective is to determine the most effective segmentation technique for bitewing radiographs based on different metrics: accuracy, training time, and the number of training parameters as a reflection of architectural cost.
In this research, we employ several deep learning models, namely Resnet-18, Resnet-50, Xception, Inception Resnet v2, and Mobilenetv2, to segment bitewing radiographs. The process begins by importing the radiographs into MATLAB®(MathWorks Inc), where the images are first improved, then segmented using the graph cut method based on regions to produce a binary mask that distinguishes the background from the original X-ray.
The deep learning models were trained on 298 and 99 radiograph training and validation sets and were evaluated using 99 images from the testing set. We also compare the segmentation model using several criteria, including accuracy, speed, and size, to determine which network is superior. Furthermore, we compare our findings with prior research to provide a comprehensive understanding of the advancements made in dental image segmentation. The accurate segmentation achieved was 93.67% and 94.42% by the Resnet-18 and Resnet-50 models, respectively.
This research advances dental image analysis and facilitates more accurate diagnoses and treatment planning by determining the best segmentation technique. The outcomes of this study can guide researchers and practitioners in selecting appropriate segmentation methods for practical dental image analysis.
... Moran et al. evaluated the effectiveness of deep CNN algorithms for detecting and diagnosing dental caries on periapical radiographs. 13 Within 480 teeth images obtained, the CNN identified 18 incipient and 16 advanced lesions, with less experienced dentists reporting statistically indistinguishable results. Singh et al. developed a CNN-LSTM model using 1500 dental images as training data and 300 as testing data. ...
Objective
The objective of this study was to evaluate the effectiveness of deep learning methods in detecting dental caries from radiographic images.
Methods
A total of 771 bitewing radiographs were divided into two groups: adult (n = 554) and pediatric (n = 217). Two distinct semantic segmentation models were constructed for each group. They were manually labeled by general dentists for semantic segmentation. The inter-examiner reliability of the two examiners was also measured. Finally, the models were trained using transfer learning methodology along with computer science advanced tools, such as ensemble U-Nets with ResNet50, ResNext101, and Vgg19 as the encoders, which were all pretrained on ImageNet weights using a training dataset.
Results
Intersection over union (IoU) score was used to evaluate the outcomes of the deep learning model. For the adult dataset, the IoU averaged 98%, 23%, 19%, and 51% for zero, primary, moderate, and advanced carious lesions, respectively. For pediatric bitewings, the IoU averaged 97%, 8%, 17%, and 25% for zero, primary, moderate, and advanced caries, respectively. Advanced caries was more accurately detected than primary caries on adults and pediatric bitewings P < 0.05.
Conclusions
The proposed deep learning models can accurately detect advanced caries in permanent or primary bitewing radiographs. Misclassification mostly occurs between primary and moderate caries. Although the model performed well in correctly classifying the lesions, it can misclassify one as the other or does not accurately capture the depth of the lesion at this early stage.
