Dental Images Research Articles

Composite Feature Set Based Dental Image Segmentation Framework through Unsupervised Learning

Composite Feature Set Based Dental Image Segmentation Framework through Unsupervised Learning

Comparison of subjective image analysis and effective dose between low-dose cone-beam computed tomography machines.

To compare the cone-beam computed tomography (CBCT) image quality and effective dose between low-dose scanning and standard manufacturer-recommended protocols among different CBCT units. Three human-equivalent phantoms were scanned using the ultra-low-dose (ULD), low dose (LD), and standard dose (STD) modes of ProMax 3D Mid (Planmeca Oy, Helsinki, Finland) and Orthophos SL (Sirona, Bensheim, German) for the CBCT images. The quality of the dental anatomical images was assessed by four experienced oral and maxillofacial radiologists using a 5-point Likert scale. OnDemand3D (Cybermed Co., Seoul, Korea) was used as the third-party software for viewing. The percentage of absolute agreement was calculated to determine intra- and interrater agreements among the observers. The effective doses for all CBCT scanning protocols were also calculated. The STD protocol yielded a higher image quality than did the ULD and LD protocols in both ProMax 3D Mid and Orthophos SL. The ULD and LD protocols demonstrated an "acceptable-to-good" sense of visual perception of the CBCT images. The visibility scores significantly differed between the ULD and LD and the STD protocols in ProMax 3D Mid and Orthophos SL, except for the 120-kVp setting in ProMax 3D Mid. The average intra- and interrater agreement scores ranged from 0.63 to 0.89 and from 0.44 to 0.76, respectively. The ULD and LD protocols reduced the radiation dose sixfold compared with the STD protocol. High-tube-voltage protocols could remarkably reduce the imaging dose without degrading the image quality. Specifically, ULD and LD CBCT protocols may be adopted as routine practice for diagnosis and treatment planning.

Dental Microstructural Imaging: From Conventional Radiology to In Vivo Confocal Microscopy

The innovative perspectives of the modern medical era aim to reach the highest performance and accuracy of therapeutic processes carried out for the evolution of diagnostic pathways. Digital planning and real-time diagnosis represent the hottest topics for researchers and clinicians in dentistry and oral medicine. To date, radiology is the gold-standard method for caries detection in the clinical setting. However, radiology poses a series of clinical limitations due to the use of ionizing radiation and its incapacity to recognize and detect enamel defects or early caries. In addition, radiology also presents issues surrounding its responsiveness to remineralizing agents and the microscopic gaps between the tooth and restorative treatments. To date, the evaluation of these conditions is only permitted ex vivo, with common methods in clinical practice not being applicable for establishing the actual condition of every case in every single patient. This work aims to develop state-of-the-art knowledge on conventional and unconventional innovative dental imaging techniques, focusing on those that not only promise to pursue the early and less invasive detection of dental disorders but also those that could be applied in clinical practice, with a particular interest in real-time in vivo confocal microscopy.

Maxillofacial imaging in dentistry- A reappraisal

Maxillofacial imaging in dentistry- A reappraisal - IJMI- Print ISSN No: - 2581-382X Online ISSN No:- 2581-3838 Article DOI No:- 10.18231/j.ijmi.2022.019, IP International Journal of Maxillofacial Imaging-IP Int J Maxillofac Imaging

FORENSIC ODONTOLOGY AND ITS PREVAILLING ADVANCEMENT

Forensic odontology is a branch of dentistry which deals with proper handling, examination and evaluation of dental evidence, with proper presentation of dental findings in the interest of justice. Tooth is the hardest tissue in the body and is most resistant to post-mortem deterioration. Dental pattern for each individual is distinct and helps in identification of victims during mass disasters, abuse and crimes. Conventional methods used in identification are dental record maintenance, dental imaging, bite marks analysis, Cheiloscopy and Rugoscopy. In addition, recent concepts have been introduced such as facial reconstruction, denture identification, DNA profiling, tongue prints and comparison microscopy. DNA analysis is a technique which involves DNA which is either mitochondrial DNA or genomic DNA.The common methods used in DNA analysis are PCR, restrictions fragments length polymorphism method, short tandem repeats typing, etc.

Iterative tomographic reconstruction with TV prior for low-dose CBCT dental imaging

Objective. Cone-beam computed tomography is becoming more and more popular in applications such as 3D dental imaging. Iterative methods compared to the standard Feldkamp algorithm have shown improvements in image quality of reconstruction of low-dose acquired data despite their long computing time. An interesting aspect of iterative methods is their ability to include prior information such as sparsity-constraint. While a large panel of optimization algorithms along with their adaptation to tomographic problems are available, they are mainly studied on 2D parallel or fan-beam data. The issues raised by 3D CBCT and moreover by truncated projections are still poorly understood. Approach. We compare different carefully designed optimization schemes in the context of realistic 3D dental imaging. Besides some known algorithms, SIRT-TV and MLEM, we investigate the primal-dual hybrid gradient (PDHG) approach and a newly proposed MLEM-TV optimizer. The last one is alternating EM steps and TV-denoising, combination not yet investigated for CBCT. Experiments are performed on both simulated data from a 3D jaw phantom and data acquired with a dental clinical scanner. Main results. With some adaptations to the specificities of CBCT operators, PDHG and MLEM-TV algorithms provide the best reconstruction quality. These results were obtained by comparing the full-dose image with a low-dose image and an ultra low-dose image. Significance. The convergence speed of the original iterative methods is hampered by the conical geometry and significantly reduced compared to parallel geometries. We promote the pre-conditioned version of PDHG and we propose a pre-conditioned version of the MLEM-TV algorithm. To the best of our knowledge, this is the first time PDHG and convergent MLEM-TV algorithms are evaluated on experimental dental CBCT data, where constraints such as projection truncation and presence of metal have to be jointly overcome.

Environmental sustainability practices in portuguese dental clinics

Objectives: To study the implementation of environmental sustainability practices at Portuguese dental clinics, the importance given by clinical directors to these practices, and the barriers felt in their applicability. Methods: This cross-sectional study’s target population was clinical directors (Dentists or Stomatologists) working in Portugal. Data was collected through an online questionnaire shared in several groups of clinicians on social networks, published in digital journals, and sent by email through medical associations. It was available between February and April 2021. The questionnaire collected information about the implementation of environmental sustainability practices in dental clinics within six categories of management: devices and equipment, dental amalgam, imaging, paper, energy, and water. There were also questions about the importance of these practices and the barriers felt. Descriptive statistics of all variables were performed. Results: The sample included 245 clinical directors, of which 65.5% were female and 43.7% were between 40 and 49 years old. There was a high degree of implementation of environmental sustainability practices related to imaging (82.6%), dental amalgam (80.7%), water (67.5%), energy (67.4%), paper (63.4%), and devices and equipment (62.9%). Almost all respondents (96%) considered that environmental sustainability practices are important or very important, and the more frequently referred barriers to implementation were costs (44.6%) and lack of training/information (16.3%). Conclusions: Clinical directors showed good environmental awareness and satisfactory implementation of environmental sustainability practices in dental clinics. Costs were the most reported barrier to the implementation of further practices.

Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR.

The segmentation of medical and dental images is a fundamental step in automated clinical decision support systems. It supports the entire clinical workflow from diagnosis, therapy planning, intervention, and follow-up. In this paper, we propose a novel tool to accurately process a full-face segmentation in about 5 minutes that would otherwise require an average of 7h of manual work by experienced clinicians. This work focuses on the integration of the state-of-the-art UNEt TRansformers (UNETR) of the Medical Open Network for Artificial Intelligence (MONAI) framework. We trained and tested our models using 618 de-identified Cone-Beam Computed Tomography (CBCT) volumetric images of the head acquired with several parameters from different centers for a generalized clinical application. Our results on a 5-fold cross-validation showed high accuracy and robustness with a Dice score up to 0.962±0.02. Our code is available on our public GitHub repository.

Clinical tooth segmentation based on local enhancement.

The tooth arrangements of human beings are challenging to accurately observe when relying on dentists’ naked eyes, especially for dental caries in children, which is difficult to detect. Cone-beam computer tomography (CBCT) is used as an auxiliary method to measure patients’ teeth, including children. However, subjective and irreproducible manual measurements are required during this process, which wastes much time and energy for the dentists. Therefore, a fast and accurate tooth segmentation algorithm that can replace repeated calculations and annotations in manual segmentation has tremendous clinical significance. This study proposes a local contextual enhancement model for clinical dental CBCT images. The local enhancement model, which is more suitable for dental CBCT images, is proposed based on the analysis of the existing contextual models. Then, the local enhancement model is fused into an encoder–decoder framework for dental CBCT images. At last, extensive experiments are conducted to validate our method.

Dental arch definition in computed tomographs using two semi-automatic methods

Computed tomography is a widely used image examination in dental imaging that provides an accurate location of oral structures and features, including the dental arch, which is an important anatomical feature. This study proposes two new semi-automatic methods for arch definition in CTs, with minimal user effort. This study includes 25 CT examinations. The first method is based on the teeth pulps, and the second one is based on the whole mandible. The methods use thresholding and morphological operations to obtain the arches. The evaluation process includes two different metrics DTW and IoU. For both metrics, the initial results of M1 were very low, but the average performance of M2 can be considered high. The analysis showed that changing the input improves the M1 results substantially. The promising results presented here suggest that these methods can be used as auxiliary tools for the proposed task.

REVOLUTIONIZING DENTAL DIAGNOSTICS: ADVANCEMENTS AND CHALLENGES IN AI-POWERED IMAGING SYSTEMS

This study explores AI-powered dental imaging systems in detail, emphasizing how they are revolutionizing diagnoses. These systems analyze radiographs, cone-beam computed tomography (CBCT) scans, and magnetic resonance imaging (MRI) scans with efficiency thanks to machine learning algorithms. We give a summary of their potential for automated interpretation, treatment suggestions, and dental disease prognosis. Reviews from academic institutions highlight how much better they are at identifying dental decay and creating individualized treatment plans than older techniques. Furthermore, the effectiveness of computer vision methods—in particular, convolutional neural networks (CNNs)—in identifying dental caries is emphasized. Issues with interpretability, ethical issues, and workflow integration still exist despite their promise. In order to overcome these obstacles and optimize the advantages of AI in dentistry, we stress the significance of interdisciplinary cooperation, which will eventually improve patient care and results.

Penetration Estimation in SEM, EDAX Dental Imaging Systems for Desensitization Application

Background: In the dental field, many people undergo an extreme fear of injections, which is referred to as trypanophobia. The medical procedures that involve injections in the dental field to create numbness raises a certain level of discomfort to all of the patients to an extent that the patients avoid treating their teeth or show an anxious or avoidance behavior. Hence, needle phobia is one of the more common phobias amongst people but was not officially recognized as a phobia in dentistry for a long time. In rural areas, some patients, mainly elderly people, might go away without treating their damaged tooth due to fear of injections. Aim: Thus, setting this as the major point of consideration, the researchers have put forth a new concept of dental treatment of creating desensitization without injections rather by adopting a new concept as “iontophoresis”, which causes the ions of specific charges to penetrate the semipermeable membrane, which helps in performing surgeries in the dental field. In the present manuscript, the ‘iontophoresis’ method, along with the imaging systems, was adopted and 45 tooth samples were taken and tested with four different ionic gels that are used in the dental field, and the results were analyzed using the imaging systems of SEM and EDAX for clear analysis. Results: The results through these imaging systems show that the ions have penetrated the tooth, which causes a desensitizing effect in the tooth and makes it numb, so that dental operations can be performed easier and with more perfection. The process of performing dental surgery with a needless process is that the patient to be treated by the dentist is exposed to a gel with electrodes wherein the ions penetrate the tooth, which causes numbness. Conclusion: The incorporation of needle-free injection through the concept of iontophoresis and imaging systems in the dental field introduces a new era in the field of dentistry, making the process simple.

Incisor Malocclusion Using Cut-out Method and Convolutional Neural Network

Malocclusion is a condition of misaligned teeth or irregular occlusion of the upper and lower jaws. This condition leads to poor performance of vital functions such as chewing. A common procedure in orthodontic treatment for malocclusion is a conventional diagnostic procedure where a dental health professional takes dental x-rays to examine the teeth to diagnose malocclusion. However, the manual orthodontic diagnostic procedure by dental experts to identify malocclusion is time-consuming and vulnerable to expert bias that results in delayed treatment completion time. Recently, artificial intelligence technology in imageprocessing has gained attention in orthodontics treatment, accelerating the diagnosis and treatment process. However, several issues concerning the dental images as input of the classification model may affect the accuracy of the classification. In addition, unstructured images with varying sizes and the problem of a machine learning algorithm that does not focus on the region of interest (ROI) for incisor features bring challenges in delivering the treatment. This study has developed a malocclusion classification model using the cut-out method and Convolutional Neural Network (CNN). The cut-out method restructures the input images by standardising the sizes and highlighting the incisor sections of the images which assisted the CNN in accurately classifying the malocclusion. From the results, the implementation of the cut-out method generates higher accuracy across all classes of malocclusion compared to the non-implementation of the cut-out method.

The Awareness of Iraqi Women, who are Studying or Working in A Medical Context, of The Use of Dental Imaging During Pregnancy

The Awareness of Iraqi Women, who are Studying or Working in A Medical Context, of The Use of Dental Imaging During Pregnancy

Deep Learning Models for Classification of Dental Diseases Using Orthopantomography X-ray OPG Images.

The teeth are the most challenging material to work with in the human body. Existing methods for detecting teeth problems are characterised by low efficiency, the complexity of the experiential operation, and a higher level of user intervention. Older oral disease detection approaches were manual, time-consuming, and required a dentist to examine and evaluate the disease. To address these concerns, we propose a novel approach for detecting and classifying the four most common teeth problems: cavities, root canals, dental crowns, and broken-down root canals, based on the deep learning model. In this study, we apply the YOLOv3 deep learning model to develop an automated tool capable of diagnosing and classifying dental abnormalities, such as dental panoramic X-ray images (OPG). Due to the lack of dental disease datasets, we created the Dental X-rays dataset to detect and classify these diseases. The size of datasets used after augmentation was 1200 images. The dataset comprises dental panoramic images with dental disorders such as cavities, root canals, BDR, dental crowns, and so on. The dataset was divided into 70% training and 30% testing images. The trained model YOLOv3 was evaluated on test images after training. The experiments demonstrated that the proposed model achieved 99.33% accuracy and performed better than the existing state-of-the-art models in terms of accuracy and universality if we used our datasets on other models.

Jordanian women’s (studying or working in medical fields) awareness in terms of the use of dental imaging during pregnancy

BackgroundThe anxiety among pregnant women about the imaging of teeth during pregnancy may have an adverse effect on the oral health of both the mother and the fetus too. This research study was conducted to evaluate women’s knowledge of the utilization of dental imaging during pregnancy.MethodsIn this research, structured questionnaires were distributed electronically through social media. The questionnaires contained questions focused on the women’s (studying or working in medical fields) awareness regarding the ionizing radiation protection that takes place during dental imaging, the safest period for dental imaging, the sort of radiographs that can be required, and the chance of radiation-induced malignant tumor and malformation of the fetal as a result of dental imaging.ResultsOverall, 984 participants completed questionnaires that were analyzed after being received. Most of the participants (n = 637; 64.7%) were < 30 years of age. The greater number of the participants (66.8%) had fair knowledge of dental imaging. 25.4% mentioned that pregnant women are able to do dental imaging during the first trimester. And approximately half of the participants thought that cone-beam computed tomography and panoramic images must not be carried out during pregnancy. Moreover, nearly the same percentage of them also believed that the risk of inborn malformation is high due to dental imaging.ConclusionsThe results refer to a low awareness among people who have medical knowledge regarding dental radiograph protection during pregnancy. This needs to be paid attention to among students, graduates, and workers in medical fields by focusing on the courses and lectures related to dental imaging protection during pregnancy.

Significance of Calcifications in Projection of Carotid Arteries on Orthopantomography for Detection of Carotid Artery Stenosis.

Orthopantomography is amongst the most commonly used dental imaging modalities. Calcifications in the projection of carotids on orthopantomographs are found in 3-15% of general population and commonly represent calcified atherosclerotic plaques. Carotid atherosclerotic changes are one of the most frequent causes of stroke, which is the second most common cause of death and the leading cause of disability globally. Our aim was to determine the relationship between calcifications in the projection of carotids on orthopantomographs, carotid stenosis and stroke, and the correlation between stroke risk factors, calcifications on orthopantomographs and the degree of carotid stenosis. Doppler ultrasound and brain MRI were performed in 41 patients with unilateral or bilateral calcifications on orthopantomographs. Anamnestic data relevant to stroke risk were gathered. Significant stenosis >50% was found in almost 15% of our patients. There was a significant correlation between hypertension and carotid calcifications. No statistically significant correlation between calcifications and significant stenosis was found. Patients with previous stroke were approximiately 5 years older than those without stroke. Preliminary results show no statistically significant correlation between calcifications on orthopantomography and significant carotid stenosis, but further investigation is needed.

Recognition of Digital Dental X-ray Images Using a Convolutional Neural Network.

Digital dental X-ray images are an important basis for diagnosing dental diseases, especially endodontic and periodontal diseases. Conventional diagnostic methods depend on the experience of doctors, so they are highly subjective and consume more energy than other approaches. The current computer-aided interpretation technology has low accuracy and poor lesion classification. This study proposes an efficient and accurate method for identifying common lesions in digital dental X-ray images by a convolutional neural network (CNN). In total, 188 digital dental X-ray images that were previously diagnosed as periapical periodontitis, dental caries, periapical cysts, and other common dental diseases by dentists in Qilu Hospital of Shandong Universitywere collected and augmented. The images and labels were inputted into four CNN models for training, including visual geometry group (VGG)-16, InceptionV3, residual network (ResNet)-50, and densely connected convolutional networks (DenseNet)-121. The average classification accuracy of the four trained network models on the test set was 95.9%, while the classification accuracy of the trained DenseNet-121 network model reached 99.5%. It is demonstrated that the use of CNNs to interpret digital dental X-ray images is an efficient and accurate way to conduct auxiliary diagnoses of dental diseases.

Periapical dental X-ray image classification using deep neural networks.

This paper studies the problem of detection of dental diseases. Dental problems affect the vast majority of the world's population. Caries, RCT (Root Canal Treatment), Abscess, Bone Loss, and missing teeth are some of the most common dental conditions that affect people of all ages all over the world. Delayed or incorrect diagnosis may result in mistreatment, affecting not only an individual's oral health but also his or her overall health, thereby making it an important research area in medicine and engineering. We propose a pipelined Deep Neural Network (DNN) approach to detect healthy and non-healthy periapical dental X-ray images. Even a minor enhancement or improvement in existing techniques can go a long way in providing significant health benefits in the medical field. This paper has made a successful attempt to contribute a different type of pipelined approach using AlexNet in this regard. The approach is trained on a large dataset of 16,000 dental X-ray images, correctly identifying healthy and non-healthy X-ray images. We use an optimized Convolutional Neural Networks and three state-of-the-art DNN models, namely Res-Net-18, ResNet-34, and AlexNet for disease classification. In our study, the AlexNet model outperforms the other models with an accuracy of 0.852. The precision, recall and F1 scores of AlexNet also surpass the other models with a score of 0.850 across all metrics. The area under ROC curve also signifies that both the false-positive rate and false-negative rate are low. We conclude that even with a big data set and raw X-ray pictures, the AlexNet model generalizes effectively to previously unseen data and can aid in the diagnosis of a variety of dental diseases.

MRI in implant planning: A future towards radiation free imaging

Since the past few years, dental implants have gained popularity as best treatment option for missing teeth. Accurate diagnosis and treatment planning plays a key role in successful implant placements. Radiography is the most widely used method for assessing quality and quantity of bone in implant site. Selection of proper diagnostic imaging modality and their adequate interpretation is very important in implant planning. With the evolution of different imaging techniques ranging from two dimensional radiography to sophisticated three dimensional imaging modalities, proper selection of technique has become a challenge for the clinicians. However, cone beam computed tomography is the most commonly used technique for implant planning. But the serious effects caused by its radiation dose are also a concern. This article gives a short review about the uses of dental magnetic resonance imaging over cone beam computed tomography in implant planning.