Dental Images Research Articles

Application of Radiographic/Imaging Techniques: A Questionnaire Study Involving Private Practitioners in Malaysia

Abstract Background: A study was carried out to get an updated overview of the applications of radiographic/imaging techniques, types of dental X-ray machines, and radiation hygiene tendencies among private dental practitioners. Materials and Methods: A survey was carried out to obtain an overview of the application of radiographic techniques by sending a questionnaire (Google Forms) to more than 1000 private dental practitioners in all states of Malaysia. In addition, several questionnaires were also completed by visiting many dental clinics in person. Results: A total of 410 responses were received. Results indicated that a majority of the practitioners owned at least an intraoral radiographic machine (90.9%). A relatively high number had panoramic machines (76.1%) and cone-beam computed tomography (CBCT) machines (42.5%). Intraoral images were acquired by private dentists at a rate of 11–20 per month (34.3%, n = 116 respondents), with only 13.6% (n = 46 respondents) acquiring more than 50 per month. With regard to panoramic and CBCT imaging, most of them took between 1 and 30 panoramic images and 1–20 CBCT scans, respectively, in a month. Conclusion: General dental practitioners in Malaysia are very dependent on various dental imaging techniques that can be performed in their own clinics. The demographic status indicated that most of the advanced imaging machines were owned by young practitioners as they are better exposed to these imaging modalities. Moreover, although the respondents graduated from universities in different countries, they had a high level of knowledge of radiation protection (>80%) when practicing oral and maxillofacial radiography.

Opportunistic investigation of vascular calcification using 3-dimensional dental imaging.

Given the growing use of cone-beam computed tomography (CBCT) scans, this study assessed radiation exposure from these scans in the context of national guidelines and recommended dose limits. The current literature was reviewed to quantify the benefit of opportunistic diagnosis of carotid artery calcification relative to the potential risk of radiation-induced cancer. The average radiation from CBCT at its largest field of view and highest resolution possible amounts to a reasonable but still low ionizing radiation exposure. This exposure is comparable to 22 days of background radiation and is notably lower than the radiation exposure from medical CT scans. According to the risk assessment analysis, the risk of stroke events involving internal and external carotid artery calcification (CAC) was 202 and 67 per 100,000 individuals, respectively. In contrast, the estimated risk of radiation-induced cancer associated with CBCT was notably lower, at 0.6 per 100,000. The present study advocates for a comprehensive assessment of CBCT scans encompassing the areas of the internal and external carotid arteries by a knowledgeable professional, given the potential advantages of early detection of vascular abnormalities. Dental professionals who take scans involving these areas need to be mindful of reporting these findings and refer patients to their primary care physician for further investigation.

Method for evaluating partially generated data

Generative models, such as autoencoders, generative adversarial networks, and diffusion models, have become an integral part of innovation in various fields in recent years, including art, design, medicine, and more. Due to their ability to create new data samples, they open broad opportunities for automation and process improvement. However, assessing the quality of generated data remains a challenging task, as traditional methods do not always adequately reflect the diversity and realism of the generated samples. This is particularly true for partial data generation, where changes are applied only to specific parts of an image, significantly complicating the assessment of their quality. This work examines various approaches to evaluating generative models, including automatic metrics such as Inception Score and Fréchet Inception Distance, precision, recall, density, and coverage, as well as a human-in-the-loop method such as HYPE. While these metrics have proven effective in evaluating the results of traditional generation, their use in the case of partially generated data may be inappropriate due to their limitations. To address this issue, the paper proposes a new method for evaluating partially generated data that involves the human factor. This method is based on analysing transformed images by users, who identify the areas that have been altered, and evaluates their quality using precision, recall, and F1-score metrics by seeking intersections between actual altered areas and those selected by users using IoU. The proposed approach provides a more objective assessment of the realism and quality of generated image fragments during transformations. A practical example of applying the developed method is presented using a dataset of panoramic dental images, where the quality of three models was evaluated: 1) a GAN based on a U-generator; 2) the same model with post-processing of the output image and segmentation mask; and 3) a self-validated GAN. The evaluation was performed by 30 individuals. The average F1-scores for these models were 0,78, 0,27, and 0,20, respectively. Since lower F1-scores in this case indicate better results (the more accurately users identified the transformations, the worse the model performed), the best model by this metric is the self-validated GAN, which is also supported by subjective assessments mentioned in the authors’ work.

Dental Imaging Analysis with Artificial Intelligence

Dental Imaging Analysis with Artificial Intelligence

Proposed values for diagnostic reference levels in intraoral dental radiography in Serbia

Values for diagnostic reference levels are proposed for intraoral dental radiography in the Republic of Serbia. Proposed numbers for diagnostic reference levels were based on measurements on 119 intraoral units in clinical settings for an adult posterior bitewing X-ray. Values of 3.17 mGy, 3.11 mGy, and 1.58 mGy incident air kerma were found for image receptors film E class, charge-coupled device, and photostimulable phosphor plate, respectively. Similarly, 89.6 mGycm2, 88 mGycm2, and 44.6 mGycm2 air kerma-area products were found for the same detectors. All values are greater than those published in several other similar studies. This is especially true for charge-coupled device image receptors since this technology enables lower patient doses as reported before. This calls for urgent action to optimize intraoral dental imaging, so we present the radiographic techniques used and equipment description to help guide optimization actions.

Deep Learning-based Cavity Detection in Diverse Intraoral Images: A Web-based Tool for Accessible Dental Care

Dental cavities represent a widespread oral health issue on a global scale, impacting individuals across all age groups. The conventional approach to detecting cavities involves a visual examination by dentists, which is not only time-consuming but also subjective. Current methods for dental cavity detection heavily rely on subjective visual inspections, which may overlook early or concealed cavities. In this research paper, we present CatchCavity, a web application tool that utilizes deep learning for cavity detection in teeth. The diagnostic tool enables users to upload dental images, facilitating the assessment of dental cavity status. Furthermore, the web application functions as an online dental diagnostic service, providing the capability to securely store patients’ dental records and information in a dedicated database. The system is trained on a dataset of annotated images and employs a convolutional neural network (CNN) architecture for accurate cavity detection. We evaluate the system's performance using metrics such as accuracy and loss. Our results showcase that the proposed system attains a high level of accuracy and efficiency in detecting dental cavities, achieving an overall accuracy of 98.7%. Additionally, our system surpasses traditional cavity detection methods, highlighting the possibility of deep learning approaches to enhance oral health outcomes.

Influence of orthodontic bracket block-out materials on superimposition errors when substituting scanned dental imaging data onto computed tomography images

Influence of orthodontic bracket block-out materials on superimposition errors when substituting scanned dental imaging data onto computed tomography images

Deep learning to assess bone quality from panoramic radiographs: the feasibility of clinical application through comparison with an implant surgeon and cone-beam computed tomography.

Bone quality is one of the most important clinical factors for the primary stability and successful osseointegration of dental implants. This preliminary pilot study aimed to evaluate the clinical applicability of deep learning (DL) for assessing bone quality using panoramic (PA) radiographs compared with an implant surgeon's subjective tactile sense and cone-beam computed tomography (CBCT) values. In total, PA images of 2,270 edentulous sites for implant placement were selected, and the corresponding CBCT relative gray value measurements and bone quality classification were performed using 3-dimensional dental image analysis software. Based on the pre-trained and fine-tuned ResNet-50 architecture, the bone quality classification of PA images was classified into 4 levels, from D1 to D4, and Spearman correlation analyses were performed with the implant surgeon's tactile sense and CBCT values. The classification accuracy of DL was evaluated using a test dataset comprising 454 cropped PA images, and it achieved an area under the receiving characteristic curve of 0.762 (95% confidence interval [CI], 0.714-0.810). Spearman correlation analysis of bone quality showed significant positive correlations with the CBCT classification (r=0.702; 95% CI, 0.651-0.747; P<0.001) and the surgeon's tactile sense (r=0.658; 95% CI, 0.600-0.708, P<0.001) versus the DL classification. DL classification using PA images showed a significant and consistent correlation with CBCT classification and the surgeon's tactile sense in classifying the bone quality at the implant placement site. Further research based on high-quality quantitative datasets is essential to increase the reliability and validity of this method for actual clinical applications.

Age Identification System with Panoramic Image Processing Digital Molar Dental Radiograph with Adaptive Region Growing Approach Method

Forensics plays a crucial role in legal enforcement, particularly in cases where objects or human victims undergoing forensic identification have suffered significant damage. Teeth offer a robust solution in the identification process due to their resilience to various circumstances. Forensic odontology focuses on dental identification for judicial purposes. One crucial parameter in forensic odontology is age estimation. Generally, an individual's dental development is directly related to age, which can be observed through the dental pulp. The dental pulp tends to narrow or widen with increasing age. In this study, an image processing system using the Adaptive Region Growing Approach (ARGA) method was developed for dental pulp molar radiograph images. Subsequently, the dental pulp images were classified using the Support Vector Machine (SVM) method. The research process encompassed data collection, image processing, feature extraction, and molar dental pulp size classification. The results demonstrated an accuracy of over 80% in the system, using specific parameters such as an adjustment threshold of OTSU 1.15, a clip limit histogram Equalization of 0.1, a polynomial kernel type, and one against one coding type for data classification into four classes. This study concludes that the Adaptive Region Growing Approach (ARGA) method and Support Vector Machine (SVM) classification can be effectively implemented in age estimation using panoramic radiograph images. This has the potential for significant applications in forensic odontology, supporting victim identification in legal enforcement.

The effect of ionizing radiation from dental radiographic devices on dental pulp stem cells

Aim: This study aims to investigate the effects of exposure to different doses delivered by radiographic diagnostic tools on cell death pathways in isolated dental pulp stem cells on a molecular level using qRT-PCR data. Methodology: Seventy fully impacted mandibular third molars were used for the study. Extracted third molars were divided into seven groups (n = 10 each): A control group receiving no radiation, periapical (PER), panoramic (PAN), and dental tomography (CBCT) groups receiving one dose of radiation each, and periapical, panoramic, and CBCT groups receiving three consecutive doses of radiation each. Then, gene expressions in dental pulp stem cells were evaluated using the qRT-PCR this method. Results: A significant difference was found in the expression of the ULK1 gene in the dental pulp tissue samples from the PAN1 group; GABARAP, LAMP3, APAF1, BCL2, CASPASE2, and CASPASE7 genes from the PER1 group; the ULK1 gene from the PER3 group; and ATG12, ATG16L1, ATG4A ATG5, BECN1L1, GABARAP, LAMP1, LAMP3, MAP1LC3B, ULK1, APAF1, BCL2, CASPASE-2, CASPASE-3, CASPASE-7, and CASPASE-8 genes from the CBCT3 group. Conclusion: While the radiation doses we applied to the DPSC cell culture are considered low levels, there was an increase in cell death markers with increased exposure to radiation through multiple radiography procedures. Taking measures to prevent errors during radiography and avoiding repeated, unnecessary patient exposure to radiation would help minimize the damaging effects of radiation. How to cite this article: Kahraman OE, Karaman T, Talo Yıldırım T, Önalan E, Dündar S, Tektemur A. The effect of ionizing radiation from dental radiographic devices on dental pulp stem cells. Int Dent Res 2023;13(3):112-8 https://doi.org/10.5577/intdentres.426 Linguistic Revision: The English in this manuscript has been checked by at least two professional editors, both native speakers of English.

Exploring Unexpected Maxillary Sinus Abnormalities in Dental CBCT Scans

Background: Incidental maxillary sinus pathologies refer to unexpected findings of abnormalities within the maxillary sinuses discovered during routine dental imaging examinations. Objective: To determine the frequency of incidental maxillary sinus pathologies in dental patients on cone-beam computed tomographic (CBCT). Study Design: Cross sectional study. Settings: Department of Dentistry Multan Medical and Dental College, Multan Pakistan. Duration: From August 2022 to January 2023. Methods: This study included 132 adult patients presenting with cone-beam computed tomographic (CBCT) images for dental assessment. Exclusion criteria comprised maxillofacial trauma, previous surgery, or congenital anomalies. Patient demographics and radiographic findings were recorded, with two radiologists independently assessing CBCT images for incidental maxillary sinus pathologies. Descriptive statistics and subgroup analyses were performed in SPSS. Results: The mean age was 46.3±10.2 years. In gender distribution, 60 patients (45.5%) were male, while 72 patients (54.5%) were females. The overall prevalence of incidental maxillary sinus pathologies was present in 75 cases, accounting for 56.81% of the total. Among the pathologic findings, mucous retention cysts were the most common, present in 35 patients (63.6%), followed by polyps in 15 patients (27.3%), sinusitis in 10 patients (18.2%), and anatomical variations in 20 patients (36.4%). Conclusion: The study identified an overall prevalence of incidental maxillary sinus pathologies in 56.81% of the dental patient population, emphasizing the importance of comprehensive evaluation during routine dental assessments.

Artificial Intelligence for Caries and Tooth Detection in Dental Imaging: A Review

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.&#x0D; 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 interpretability in 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.

Artificial intelligence in dentistry: It’s applications, impact and challenges

In dentistry, artificial intelligence (AI) has shown great potential in improving diagnosis, treatment planning, and patient care. AI algorithms have been developed to analyze dental images, such as radiographs and intraoral scans, aiding in the detection of dental caries, periodontal diseases, and oral lesions. These algorithms can provide more accurate and efficient diagnoses, reducing the reliance on human interpretation. AI has also been utilized in treatment planning and helping dentists to determine the optimal approach for procedures such as dental implant placement and orthodontic treatment, and recently, AI has also been playing a significant role in forensic medicine as well as in forensic odontology. In addition, AI-based chatbots and virtual assistants have been developed to provide patients with personalized oral health information and guidance. Despite the numerous advantages, challenges remain in implementing AI in dentistry, such as ensuring data privacy and addressing ethical concerns. Nevertheless, AI has the potential to revolutionize dentistry by improving diagnosis, treatment planning, and patient care, ultimately leading to better oral health outcomes. This review provides an overview of the current applications of AI and its influence on dental practice, along with future prospects.

A novel approach for gingiva thickness measurements around lower anterior teeth by means of dental magnetic resonance imaging

ObjectiveThis diagnostic accuracy study aims to present the first measurements of gingiva thickness around lower anterior teeth using dental magnetic resonance imaging (MRI) and to compare these measurements with two established methods: (1) gingival phenotype assessment via periodontal probing, and (2) the superimposition of cone-beam computed tomography (CBCT) scans with intraoral scans of teeth and gums.Materials and methodsTen patients with substantial orthodontic treatment need and anterior mandibular crowding were consecutively included in this clinical case series. After periodontal probing, each patient underwent a CBCT scan, an intraoral scan of the mandible, and an MRI investigation using a novel mandibula 15-channel dental coil.ResultsThe mean gingiva thickness was 0.72 mm measured on MRI and 0.97 mm measured on CBCT, with a mean difference between the measurement methods of 0.17 ± 0.27 mm (p < 0.001). Measurement agreement between the index tests (MRI and CBCT) and the clinical reference standard (probing) yielded an overall percent agreement of 64.94% and 47.02% for MRI and CBCT, respectively. Teeth with thin phenotypes were associated with lower soft tissue dimensions in both free (MRI: 0.56 mm vs. CBCT: 0.79 mm) and supracrestal gingiva (MRI: 0.75 mm vs. CBCT: 1.03 mm) when compared to those with thick phenotypes. However, only the measurements obtained from MRI scans showed statistically significant differences between the two phenotypes.ConclusionDental MRI successfully visualizes delicate structures like the gingiva in the anterior mandible and achieves a high correlation with superimposed CBCT scans, with clinically acceptable deviations.Clinical relevanceThe present study helps to establish dental MRI as a radiation-free alternative to conventional radiographic methods.

The Use of Fine Arts to Enhance Visualization and Describing Skills in a First-Year Dental Anatomy Course: A Qualitative Study

(1) Background: In this qualitative study, we investigated the implementation of an art-based observation workshop as a tool to improve visualization and interpretation skills in a cohort of first-year dental students (N = 109) in a dental anatomy course. (2) Methods: The art workshop was held once for a total of 60 min in the pre-clinical simulation laboratory, which is the regular teaching setting for the dental anatomy course. Visualization and interpretation skills were assessed before (pre-test) and after the art-based observation workshop (post-test). The pre- and post-tests contained five images that guided students to describe dental anatomy images. The pre- and post-test had different but similar images. Dental students accessed the pre- and post-tests on CANVAS and recorded their answers. After that, the audio recording files were analyzed and compared to determine the frequency of use of dental anatomy-specific nomenclature while answering the pre- and post-test. (3) Results: Our results demonstrate that students used dental anatomy-specific nomenclature more frequently after the intervention. (4) Conclusions: we have concluded that students’ use of dental anatomy nomenclature in the first-year dental anatomy curriculum is enhanced following an art-based intervention in a regular dental simulation laboratory.

Deep learning for classifying the stages of periodontitis on dental images: a systematic review and meta-analysis

BackgroundThe development of deep learning (DL) algorithms for use in dentistry is an emerging trend. Periodontitis is one of the most prevalent oral diseases, which has a notable impact on the life quality of patients. Therefore, it is crucial to classify periodontitis accurately and efficiently. This systematic review aimed to identify the application of DL for the classification of periodontitis and assess the accuracy of this approach.MethodsA literature search up to November 2023 was implemented through EMBASE, PubMed, Web of Science, Scopus, and Google Scholar databases. Inclusion and exclusion criteria were used to screen eligible studies, and the quality of the studies was evaluated by the Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology with the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies) tool. Random-effects inverse-variance model was used to perform the meta-analysis of a diagnostic test, with which pooled sensitivity, specificity, positive likelihood ratio (LR), negative LR, and diagnostic odds ratio (DOR) were calculated, and a summary receiver operating characteristic (SROC) plot was constructed.ResultsThirteen studies were included in the meta-analysis. After excluding an outlier, the pooled sensitivity, specificity, positive LR, negative LR and DOR were 0.88 (95%CI 0.82–0.92), 0.82 (95%CI 0.72–0.89), 4.9 (95%CI 3.2–7.5), 0.15 (95%CI 0.10–0.22) and 33 (95%CI 19–59), respectively. The area under the SROC was 0.92 (95%CI 0.89–0.94).ConclusionsThe accuracy of DL-based classification of periodontitis is high, and this approach could be employed in the future to reduce the workload of dental professionals and enhance the consistency of classification.

Application of entire dental panorama image data in artificial intelligence model for age estimation

BackgroundAccurate age estimation is vital for clinical and forensic purposes. With the rapid advancement of artificial intelligence(AI) technologies, traditional methods relying on tooth development, while reliable, can be enhanced by leveraging deep learning, particularly neural networks. This study evaluated the efficiency of an AI model by applying the entire panoramic image for age estimation. The outcome performances were analyzed through supervised learning (SL) models.MethodsTotal of 27,877 dental panorama images from 5 to 90 years of age were classified by 2 types of grouping. In type 1 they were classified by each age and in type 2, applying heuristic grouping, the age over 20 years were classified by every 5 years. Wide ResNet (WRN) and DenseNet (DN) were used for supervised learning. In addition, the analysis with ± 3 years of deviation in both types were performed.ResultsFor the DN model, while the type 1 grouping achieved an accuracy of 0.1016 and F1 score of 0.058, the type 2 achieved an accuracy of 0.3146 and F1 score of 0.2027. Incorporating ± 3years of deviation, the accuracy of type 1 and 2 were 0.281, 0.7323 respectively; and the F1 score were 0.1768, 0.6583 respectively. For the WRN model, while the type 1 grouping achieved an accuracy of 0.1041 and F1 score of 0.0599, the type 2 achieved an accuracy of 0.3182 and F1 score of 0.2071. Incorporating ± 3years of deviation, the accuracy of type 1 and 2 were 0.2716, 0.7323 respectively; and the F1 score were 0.1709, 0.6437 respectively.ConclusionsThe application of entire panorama image data for supervised with classification by heuristics grouping with ± 3years of deviation for supervised learning models and demonstrated satisfactory outcome for the age estimation.

Imaging in Third Molar Surgery: A Clinical Update.

Third molar surgery is one of the most common surgical procedures performed in oral and maxillofacial surgery. Considering the patient's young age and the often-elective nature of the procedure, a comprehensive preoperative evaluation of the surgical site, relying heavily on preoperative imaging, is key to providing accurate diagnostic work-up, evidence-based clinical decision making, and, when appropriate, indication-specific surgical planning. Given the rapid developments of dental imaging in the field, the aim of this article is to provide a comprehensive, up-to-date clinical overview of various imaging techniques related to perioperative imaging in third molar surgery, ranging from panoramic radiography to emerging technologies, such as photon-counting computed tomography and magnetic resonance imaging. Each modality's advantages, limitations, and recent improvements are evaluated, highlighting their role in treatment planning, complication prevention, and postoperative follow-ups. The integration of recent technological advances, including artificial intelligence and machine learning in biomedical imaging, coupled with a thorough preoperative clinical evaluation, marks another step towards personalized dentistry in high-risk third molar surgery. This approach enables minimally invasive surgical approaches while reducing inefficiencies and risks by incorporating additional imaging modality- and patient-specific parameters, potentially facilitating and improving patient management.

Automatic detection of posterior superior alveolar artery in dental cone-beam CT images using a deeply supervised multi-scale 3D network.

This study aimed to develop a robust and accurate deep learning network for detecting the posterior superior alveolar artery (PSAA) in dental cone-beam CT (CBCT) images, focusing on the precise localization of the centre pixel as a critical centreline pixel. PSAA locations were manually labelled on dental CBCT data from 150 subjects. The left maxillary sinus images were horizontally flipped. In total, 300 datasets were created. Six different deep learning networks were trained, including 3D U-Net, deeply supervised 3D U-Net (3D U-Net DS), multi-scale deeply supervised 3D U-Net (3D U-Net MSDS), 3D Attention U-Net, 3D V-Net, and 3D Dense U-Net. The performance evaluation involved predicting the centre pixel of the PSAA. This was assessed using mean absolute error (MAE), mean radial error (MRE), and successful detection rate (SDR). The 3D U-Net MSDS achieved the best prediction performance among the tested networks, with an MAE measurement of 0.696 ± 1.552 mm and MRE of 1.101 ± 2.270 mm. In comparison, the 3D U-Net showed the lowest performance. The 3D U-Net MSDS demonstrated a SDR of 95% within a 2 mm MAE. This was a significantly higher result than other networks that achieved a detection rate of over 80%. This study presents a robust deep learning network for accurate PSAA detection in dental CBCT images, emphasizing precise centre pixel localization. The method achieves high accuracy in locating small vessels, such as the PSAA, and has the potential to enhance detection accuracy and efficiency, thus impacting oral and maxillofacial surgery planning and decision-making.

Use of Optical Coherence Tomography in Dentistry.

Optical coherence tomography (OCT) is an optics-based imaging technique, which may be called an "optical biopsy." It can be used to acquire structural information about a tissue at a resolution comparable to histopathology. OCT is based on the principle of low-coherence interferometry where near-infrared (NIR) light is shown on a tissue sample and then cross-sectional images are obtained based on backscattered light and echo time delay. Two main types of OCT are characterized as time-domain OCT (TD-OCT) and Fourier-domain OCT (FD-OCT). The applications of OCT in dentistry can be broadly divided into two groups, i.e., assessment of pathologies and assessment of surfaces and interfaces. Lately, OCT has made its transition from experimental laboratories to mainstream clinical applications. Starting from the short-term training courses, clinicians working in specialities like oral pathology, oral medicine, and oral implantology may find it a useful tool for their practices. It is now clear that OCT will be considered a gold standard diagnostic tool for the detection and characterization of several conditions and lesions of the orofacial region. However, the next challenge will be to incorporate it into the undergraduate and postgraduate curriculum and train dental healthcare staff in the use of these devices.