Images Of Teeth Research Articles

Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation.

Traditional dental prosthetics require a significant amount of work, labor, and time. To simplify the process, a method to convert teeth scan images, scanned using an intraoral scanner, into 3D images for design was developed. Furthermore, several studies have used deep learning to automate dental prosthetic processes. Tooth images are required to train deep learning models, but they are difficult to use in research because they contain personal patient information. Therefore, we propose a method for generating virtual tooth images using image-to-image translation (pix2pix) and contextual reconstruction fill (CR-Fill). Various virtual images can be generated using pix2pix, and the images are used as training images for CR-Fill to compare the real image with the virtual image to ensure that the teeth are well-shaped and meaningful. The experimental results demonstrate that the images generated by the proposed method are similar to actual images. In addition, only using virtual images as training data did not perform well; however, using both real and virtual images as training data yielded nearly identical results to using only real images as training data.

Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models

To overcome the limitation of a single classification model’s inability to simultaneously identify multiple lesion targets within periapical radiographs, This study proposes YoCNET (Yolov5 + ConvNeXt), a novel deep learning integrated model. YoCNET leverages the target detection capability of Yolov5 and the image classification capability of ConvNeXt to achieve automatic segmentation of individual teeth and concurrent detection of periapical lesions across multiple teeth. A dataset of 1,305 periapical radiographs was used to train and validate the ConvNeXt and ResNet34 models, with an 8:2 split for training and validation. Deciduous teeth were excluded from the dataset. Furthermore, 717 individual teeth images were extracted from 200 previously unused periapical radiographs for integrated model validation. Evaluation metrics included accuracy, precision, sensitivity, F1 score, AUC (Area Under Curve), and a confusion matrix.The YoCNET integrated model demonstrated values of 90.93%, 98.88%, 85.30%, 0.9159, and 0.9757 for accuracy, precision, sensitivity, F1 score, and AUC, respectively. These metrics were superior to those achieved by the YoRNET (Yolov5 + ResNet34) integrated model, which recorded 80.47%, 83.78%, 82.16%, 0.8296, and 0.8822. The integrated model achieved high accuracy and efficiency in automatic teeh segmentation by Yolov5 and in automatically detecting multiple periapical lesions by ConvNeXt. YoCNET exhibited superior overall data performance, making it a more suitable deep learning integrated model for clinical applications.

Volumetric correlation of periapical lesion with Orstavik’s periapical index: A retrospective cone-beam computed tomographic study

Abstract Aim: To assess the correlation among cone-beam computed tomographic periapical volume index (CBCTPAVI) and periapical lesion volume with Orstavik’s periapical index (PAI). Methodology: Seventy-six cone-beam computed tomographic (CBCT) and periapical radiographic images of single-rooted teeth presenting with apical periodontitis from 42 patients were obtained from a period of March 2023 to April 2024. Two observers evaluated the periapical radiographs and assigned PAI scores. CBCTPAVI was allocated based on the volume of the lesion, which was computed using ITK-SNAP software. Spearman’s correlation coefficient was employed to evaluate the association between CBCTPAVI and lesion volume with PAI. Results: A significant and moderate positive relationship between PAI and lesion volume (ρ = 0.553, P < 0.001) as well as between PAI and CBCTPAVI (ρ = 0.506; P < 0.001) was observed. Conclusion: The risk of under/overestimation of results on two-dimensional periapical radiographs exists, despite a favorable connection with volumetric assessment of CBCT images.

A lightweight detection algorithm for tooth cracks in optical images

ObjectivesCracked tooth syndrome (CTS) is one of the major causes of tooth loss, presents the problem of early microcrack symptoms that are difficult to distinguish. This paper aims to investigate the practicality and feasibility of an improved object detection algorithm for automatically detecting cracks in dental optical images. MethodsA total of 286 teeth were obtained from Sun Yat-sen University and Guangdong University of Technology, and simulated cracks were generated using thermal expansion and contraction. Over 3000 images of cracked teeth were collected, including 360 real clinical images. To make the model more lightweight and better suited for deployment on embedded devices, this paper improves the YOLOv8 model for detecting tooth cracks through model pruning and backbone replacement. Additionally, the impact of image enhancement modules and coordinate attention modules on optimizing our model was analyzed. ResultsThrough experimental validation, we conclude that that model pruning reduction maintains performance better than replacing a lightweight backbone network on a tooth crack detection task. This approach achieved a reduction in parameters and GFLOPs by 16.8 % and 24.3 %, respectively, with minimal impact on performance. These results affirm the effectiveness of the proposed method in identifying and labeling tooth fractures. In addition, this paper demonstrated that the impact of image enhancement modules and coordinate attention mechanisms on YOLOv8's performance in the task of tooth crack detection was minimal. ConclusionsAn improved object detection algorithm has been proposed to reduce model parameters. This lightweight model is easier to deploy and holds potential for assisting dentists in identifying cracks on tooth surfaces.

Registration of thermal images of dead teeth to identify odontogenic infection foci

Infrared thermal imaging (IRT) remotely and contactless maps the temperature on the examined surface, recording the distribution of infrared radiation emitted by each body whose temperature is higher than absolute zero. The aim of the study was to evaluate the usefulness of thermography in the assessment of asymptomatic infection foci in patients with high systemic infection. The 150 cases diagnosed based on roentgenograms, divided into 6 groups of diagnosed odontogenic lesions, along with a control group. Thermal imaging was performed with a FLIR Systems T1020 thermal camera. Thermal image analysis was performed using ThermaCAM Researcher Pro 2.10, MS Office Excel 2022 and Statistica 10. The periapical areas of selected dead teeth were selected as areas of interest. The Mann Whitney’s U test showed statistically significant (p < 0.001) differences in average temperature between each patient’s and healthy group. Depper’s analysis showed statistical significance also between the ZM and BZ groups (p = 0.004). Moreover, obtained results may also suggest that thermal imaging can be useful in identify odontogenic infection foci. The thermal asymmetry of periapical tissues of teeth differentiates dead from living teeth, as well as individual pathologies related to the process of gangrenous pulp decay. Thermographic mapping is a promising diagnostic technique that can detect asymptomatic inflammations that carry the risk of infection of the entire body.

CRML-Net: Cross-Modal Reasoning and Multi-Task Learning Network for tooth image segmentation

Data from a single modality may suffer from noise, low contrast, or other imaging limitations that affect the model’s accuracy. Furthermore, due to the limited amount of data, most models trained on single-modality data tend to overfit the training set and perform poorly on out-of-domain data. Therefore, in this paper, we propose a network named Cross-Modal Reasoning and Multi-Task Learning Network (CRML-Net), which combines cross-modal reasoning and multi-task learning, aiming to leverage the complementary information between different modalities and tasks to enhance the model’s generalization ability and accuracy. Specifically, CRML-Net consists of two stages. In the first stage, our network extracts a new morphological information modality from the original image and then performs cross-modal fusion with the original modality image, aiming to leverage the morphological information to enhance the model’s robustness to out-of-domain datasets. In the second stage, based on the output of the previous stage, we introduce a multi-task learning mechanism, aiming to improve the model’s performance on unseen data by sharing surface detail information from auxiliary tasks. We validated our method on a publicly available tooth cone beam computed tomography dataset. Our evaluation demonstrates that our method outperforms state-of-the-art approaches.

Ex vivo human teeth imaging with various photoacoustic imaging systems.

Dental caries cause pain and if not diagnosed, it may lead to the loss of teeth in extreme cases. Dental X-ray imaging is the gold standard for caries detection; however, it cannot detect hidden caries. In addition, the ionizing nature of X-ray radiation is another concern. Hence, other alternate imaging modalities like photoacoustic (PA) imaging are being explored for dental imaging. Here, we demonstrate the feasibility of acoustic resolution photoacoustic microscopy (ARPAM) to image a tooth with metal filling, circular photoacoustic computed tomography (cPACT) to acquire images of teeth with caries and pigmentation, and linear array-based photoacoustic imaging (lPACT) of teeth with caries and pigmentation. The cavity measured with lPACT imaging is compared with the X-ray computed tomography image. The metal filling and its boundaries are clearly seen in the ARPAM image. cPACT images at 1064 nm were a better representative of the tooth surface compared to the images acquired at 532 nm. It was possible to detect the cavities present in the dentine when lPACT imaging was used. The PA signal from the pigmented caries on the lateral surface (occlusion view) of the tooth was high when imaged using the lPACT system.

Precision Medicine for Apical Lesions and Peri-Endo Combined Lesions Based on Transfer Learning Using Periapical Radiographs.

An apical lesion is caused by bacteria invading the tooth apex through caries. Periodontal disease is caused by plaque accumulation. Peri-endo combined lesions include both diseases and significantly affect dental prognosis. The lack of clear symptoms in the early stages of onset makes diagnosis challenging, and delayed treatment can lead to the spread of symptoms. Early infection detection is crucial for preventing complications. PAs used as the database were provided by Chang Gung Memorial Medical Center, Taoyuan, Taiwan, with permission from the Institutional Review Board (IRB): 02002030B0. The tooth apex image enhancement method is a new technology in PA detection. This image enhancement method is used with convolutional neural networks (CNN) to classify apical lesions, peri-endo combined lesions, and asymptomatic cases, and to compare with You Only Look Once-v8-Oriented Bounding Box (YOLOv8-OBB) disease detection results. The contributions lie in the utilization of database augmentation and adaptive histogram equalization on individual tooth images, achieving the highest comprehensive validation accuracy of 95.23% with the ConvNextv2 model. Furthermore, the CNN outperformed YOLOv8 in identifying apical lesions, achieving an F1-Score of 92.45%. For the classification of peri-endo combined lesions, CNN attained the highest F1-Score of 96.49%, whereas YOLOv8 scored 88.49%.

Exploring the CIEDE2000 thresholds for lightness, chroma, and hue differences in dentistry

ObjectiveTo evaluate the perceptibility and acceptability CIEDE2000 (KL:KC:KH) thresholds for lightness, chroma and hue differences in dentistry. MethodA Python-based program was developed to conduct a psychophysical experiment based on visual assessments of computer-simulated images of human teeth. The experiment was performed on a calibrated display. A 40-observer panel: dentists and laypersons (male and female; n=10), evalu- ated three subsets of simulated human teeth: the lightness subset (%∆L00 ≥ 98 %), the chroma subset (%∆C00 ≥ 98 %) and the hue subset (%∆H00 ≥ 98 %), using ∆E00 ≥ 5 units. A Takagi-Sugeno-Kang Fuzzy Approximation model was used as fitting procedure, and 50:50 % lightness, chroma and hue CIEDE2000 (1:1:1) and CIEDE2000 (2:1:1) perceptibility (PT00) and accept- ability (AT00) thresholds were calculated. Data was statistically analyzed using t-test (p < 0.05). ResultsThe 50:50 % PT00 for KL=1 were ∆L00=1.04, ∆C00=1.58 and ∆E00=1.01; and for KL=2 were ∆L00=0.51, ∆C00=1.58 and ∆E00=0.71. The 50:50 % AT00 for KL=1 were ∆L00=2.82, ∆C00=3.04 and ∆E00=2.66; and for KL=2 were ∆L00=1.40, ∆C00=3.04 and ∆E00=1.78. PT00 and AT00 ∆H00 may be considered no computable. A significant difference was found between CIEDE2000(1:1:1) and CIEDE2000(2:1:1), between lightness and chroma metrics, and between observer groups. No differences for lightness and chroma PT00 were found between male and female groups. ConclusionsIt is important to use PT00 and AT00 for lightness, chroma and hue specific to evaluate perceptual sensitivity for color changes in the tooth color space. AT00 for lightness and chroma are influenced by the observer's experience and gender. Males and laypersons show more tolerance for changes in chroma (∆C00) and in lightness (∆L00). SignificanceHue and chroma mismatch are more difficult to be accepted in dental color space.

Influence of sex and timing of mixed dentition on discrepancies between chronological age and dental age in Taiwanese children

Background/purposeThe aim of this study was to determine the effects of age and sex on the difference between chronological age (CA) and dental age (DA) predicted using the Demirjian and Willems methods in Taiwanese children. Materials and methodsA total of 232 periapical X-ray images were obtained from children aged 5–12 years in Taiwan. Among them, 119 were boys, and 113 were girls. DA was calculated on the basis of the X-ray images of permanent teeth by using the aforementioned methods. The children were stratified by age (5–9 years [early mixed dentition period] vs. 10–12 years [late mixed dentition period]) and sex (boys vs. girls). Statistical analyses were performed to investigate potential age- and sex-based differences in the correlation between CA and DA. ResultsNo significant difference was observed between the mean CA and DA predicted using the Willems method in children with late mixed dentition and in girls. However, the correlation between CA and DA was stronger in children with early mixed dentition than in those with late mixed dentition and also stronger in boys than in girls. ConclusionFor children in mid-Taiwan, age and sex influence the development of permanent teeth. In addition, the correlation between DA and CA is relatively strong for boys in the early mixed dentition period.

Augmented Reality Improved Knowledge and Efficiency of Root Canal Anatomy Learning: A Comparative Study

Teaching root canal anatomy has traditionally been reliant on static methods, but recent studies have explored the potential of advanced technologies like augmented reality (AR) to enhance learning and address the limitations of traditional training methods, such as the requirement for spatial imagination and the inability to simulate clinical scenarios fully. This study evaluated the potential of AR as a tool for teaching root canal anatomy in preclinical training in endodontics for predoctoral dental students. Six cone beam computed tomography (CBCT) images of teeth were selected. Board-certified endodontist and radiologist recorded the tooth type and classification of root canals. Then, STereoLithography (STL) files of the same images were imported into a virtual reality (VR) application and viewed through a VR head-mounted display. Forty-three third-year dental students were asked questions about root canal anatomy based on the CBCT images, and then, after the AR model. The time to respond to each question and feedback was recorded. Student responses were paired, and the difference between CBCT and AR scores was examined using a paired-sample t-test and set to p = 0.05. Students demonstrated a significant improvement in their ability to answer questions about root canal anatomy after utilizing the AR model (p &lt; 0.05). Female participants demonstrated significantly higher AR scores compared to male participants. However, gender did not significantly influence overall test scores. Furthermore, students required significantly less time to answer questions after using the AR model (M = 4.09, SD = 3.55) compared to the CBCT method (M = 15.21, SD = 8.01) (p &lt; 0.05). This indicates that AR may improve learning efficiency alongside comprehension. In a positive feedback survey, 93% of students reported that the AR simulation led to a better understanding of root canal anatomy than traditional CBCT interpretation. While this study highlights the potential of AR in learning root canal anatomy, further research is needed to explore its long-term impact and efficacy in clinical settings.

Age Estimation Using the Pulp-to-Tooth Area Ratio in an Indian Population Using Cone-Beam Computerised Tomography (CBCT): A Retrospective Study.

Age estimation, whether for living or deceased individuals, is crucial in forensic sciences. Traditionally, the pulp-to-tooth area ratio determined from periapical radiographs has been employed as a non-invasive method for estimating age. Cone-beam computed tomography (CBCT) represents a newer technique, providing three-dimensional images of teeth in living individuals. This study aims to estimate age using the pulp-to-tooth area ratio of four teeth (the permanent maxillary central incisor, lateral incisor, canine, and first premolar. The study included ninety subjects ranging in age from 18 to 70 years. This study concluded that the correlation between actual age and estimated age varied across different tooth types. There was a strong positive correlation between the maxillary right central incisor and maxillary right canine tooth, while the maxillary left canine tooth exhibited a slightly weaker but still positive correlation. This indicates that the maxillary right central incisor and maxillary right canine tooth are the most reliable for estimating age. Additionally, the study found that the linear regression results for estimating age based on the pulp-to-tooth area ratio, categorised by sex and each type of tooth, showed strong associations between age and the ratio for the maxillary left central incisor and maxillary left canine teeth in males, and for the maxillary left central incisor in females.

Head of Zebu cattle (Bos Taurus indicus): sectional anatomy and 3D computed tomography

The research was designed to use computed tomography (CT) with 3D-CT reconstruction imaging techniques and the various anatomical sections—plana transversalia, frontalis, and dorsalia—to describe the anatomical architecture of the Zebu cattle head. Our study used nine mature heads. The CT bone window created detailed images of cranial bones, mandibles, teeth, and hyoid bones. All of the head cavities were evaluated, including the cranial, orbital, oral, auricular, and nasal cavities with their paranasal and conchal sinuses. The septum nasi, attached to the vomer and maxillary bones, did not reach the nasal cavity floor caudally at the level of the second premolar teeth, resulting in a single median channel from the choanae to the nasopharynx. The positions, boundaries, and connections of the paranasal sinuses were clearly identified. There were four nasal conchal sinuses (that were named the dorsal, middle, ethmoidal, and ventral) and five paranasal sinuses that were described as the following: sinus frontalis, maxillaris, palatinorum, and lacrimalis, as defined in the different anatomical sections and computed tomographic images. The complicated sinus frontalis caused the pneumatization of all bones that surrounded the cranial cavity, with the exception of the ethmoidal and body of basisphenoid bones. The sinus maxillaris was connected to the sinus lacrimalis and palatinorum through the maxillolacrimal and palatomaxillary openings, and to the middle nasal meatus through the nasomaxillary opening. Our findings provide a detailed anatomical knowledge for disease diagnosis to internal medicine veterinarians and surgeons by offering a comprehensive atlas of the Zebu cattle anatomy.

Quality of different obturation techniques to fill perforating internal root resorption: a micro-computed tomographic study

BackgroundThis study aimed to assess the quality of various obturation techniques to fill perforation caused by internal root resorption using Micro-computed Tomography.MethodsCone-beam computed tomography images of a maxillary central incisor tooth with perforating internal resorptive defect were used to create a 3D printed model of the affected tooth. The replicas were divided into four groups based on the obturation technique used. The techniques included Group 1: a polydimethylsiloxane-based sealer (GuttaFlow-2) with gutta-percha. Group 2: same as Group 1 except for using a pre-mixed Bioceramic-based sealer (NeoSEALER Flo). Group 3: the defect was filled entirely using the NeoSealer Flo Bioceramic-based sealer. Group 4: the samples were obturated using the warm vertical compaction technique with a resin-based sealer (ADSeal). The resin models were then scanned a micro-computed scanner to evaluate the percentage of voids in each group.ResultsThe results showed that NeoSEALER Flo groups had significantly the highest volume of voids while GuttaFlow-2 and warm vertical compaction groups had the lowest void volume.ConclusionsGuttaFlow-2 and warm vertical compaction techniques performed best in filling the internal resorptive defect.

Caries lesions diagnosis with deep convolutional neural network in intraoral QLF images by handheld device

ObjectivesThis study investigated the effectiveness of a deep convolutional neural network (CNN) in diagnosing and staging caries lesions in quantitative light-induced fluorescence (QLF) images taken by a self-manufactured handheld device.MethodsA small toothbrush-like device consisting of a 400 nm UV light-emitting lamp with a 470 nm filter was manufactured for intraoral imaging. A total of 133 cases with 9,478 QLF images of teeth were included for caries lesion evaluation using a CNN model. The database was divided into development, validation, and testing cohorts at a 7:2:1 ratio. The accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) were calculated for model performance.ResultsThe overall caries prevalence was 19.59%. The CNN model achieved an AUC of 0.88, an accuracy of 0.88, a specificity of 0.94, and a sensitivity of 0.64 in the validation cohort. They achieved an overall accuracy of 0.92, a sensitivity of 0.95 and a specificity of 0.55 in the testing cohort. The model can distinguish different stages of caries well, with the best performance in detecting deep caries followed by intermediate and superficial lesions.ConclusionsCaries lesions have typical characteristics in QLF images and can be detected by CNNs. A QLF-based device with CNNs can assist in caries screening in the clinic or at home.Trial registrationThe clinical trial was registered in the Chinese Clinical Trial Registry (No. ChiCTR2300073487, Date: 12/07/2023).

Insights into Predicting Tooth Extraction from Panoramic Dental Images: Artificial Intelligence vs. Dentists

ObjectivesTooth extraction is one of the most frequently performed medical procedures. The indication is based on the combination of clinical and radiological examination and individual patient parameters and should be made with great care. However, determining whether a tooth should be extracted is not always a straightforward decision. Moreover, visual and cognitive pitfalls in the analysis of radiographs may lead to incorrect decisions. Artificial intelligence (AI) could be used as a decision support tool to provide a score of tooth extractability.Material and methodsUsing 26,956 single teeth images from 1,184 panoramic radiographs (PANs), we trained a ResNet50 network to classify teeth as either extraction-worthy or preservable. For this purpose, teeth were cropped with different margins from PANs and annotated. The usefulness of the AI-based classification as well that of dentists was evaluated on a test dataset. In addition, the explainability of the best AI model was visualized via a class activation mapping using CAMERAS.ResultsThe ROC-AUC for the best AI model to discriminate teeth worthy of preservation was 0.901 with 2% margin on dental images. In contrast, the average ROC-AUC for dentists was only 0.797. With a 19.1% tooth extractions prevalence, the AI model's PR-AUC was 0.749, while the dentist evaluation only reached 0.589.ConclusionAI models outperform dentists/specialists in predicting tooth extraction based solely on X-ray images, while the AI performance improves with increasing contextual information.Clinical relevanceAI could help monitor at-risk teeth and reduce errors in indications for extractions.

Evaluation of Dental Plaque Area with Artificial Intelligence Model

Objectives: This study aims to assess the diagnostic accuracy of an artificial intelligence (AI) system employing deep learning for identifying dental plaque, utilizing a dataset comprising photographs of permanent teeth. Materials and Methods: In this study, photographs of 168 teeth belonging to 20 patients aged between 10 and 15 years, who met our criteria, were included. Intraoral photographs were taken of the patients in two stages, before and after the application of the plaque staining agent. To train the AI system to identify plaque on teeth with dental plaque that is not discolored, plaque and teeth were marked on photos with exposed dental plaque. One hundred forty teeth were used to construct the training group, while 28 teeth were used to create the test group. Another dentist reviewed images of teeth with dental plaque that was not discolored, and the effectiveness of AI in detecting plaque was evaluated using pertinent performance indicators. To compare the AI model and the dentist’s evaluation outcomes, the mean intersection over union (IoU) values were evaluated by the Wilcoxon test. Results: The AI system showed higher performance in our study with a precision of 82% accuracy, 84% sensitivity, 83% F1 score, 87% accuracy, and 89% specificity in plaque detection. The area under the curve (AUC) value was found to be 0.922, and the IoU value was 76%. Subsequently, the dentist’s plaque diagnosis performance was also evaluated. The IoU value was 0.71, and the AUC was 0.833. The AI model showed statistically significantly higher performance than the dentist (P &lt; 0.05). Conclusions: The AI algorithm that we developed has achieved promising results and demonstrated clinically acceptable performance in detecting dental plaque compared to a dentist.

Biomechanical impact of different isthmus positions in mandibular first molar root canals: a finite element analysis.

This study used image-based finite element analysis (FEA) to assess the biomechanical changes in mandibular first molars resulting from alterations in the position of the root canal isthmus. A healthy mandibular first molar, characterized by two intact root canals and a cavity-free surface, was selected as the subject. A three-dimensional model for the molar was established using scanned images of the patient's mandibular teeth. Subsequently, four distinct finite element models were created, each representing varied root canal morphologies: non-isthmus (Group A), isthmus located at the upper 1/3 of the root (Group B), middle 1/3 of the root (Group C), and lower 1/3 of the root (Group D). A static load of 200 N was applied along the tooth's longitudinal axis on the occlusal surface to simulate regular chewing forces. The biomechanical assessment was conducted regarding the mechanical stress profile within the root dentin. The equivalent stress (Von Mises stress) was used to assess the biomechanical features of mandibular teeth under mechanical loading. In Group A (without an isthmus), the maximum stress was 22.2MPa, while experimental groups with an isthmus exhibited higher stresses, reaching up to 29.4MPa. All maximum stresses were concentrated near the apical foramen. The presence of the isthmus modified the stress distribution in the dentin wall of the tooth canal. Notably, dentin stresses at specific locations demonstrated differences: at 8mm from the root tip, Group B: 13.6MPa vs. Group A: 11.4MPa; at 3mm from the root tip, Group C: 14.2MPa vs. Group A: 4.5MPa; at 1mm from the root tip, Group D: 25.1MPa vs. Group A: 10.3MPa. The maximum stress in the root canal dentin within the isthmus region was located either at the top or bottom of the isthmus. A root canal isthmus modifies the stress profile within the dentin. The maximum stress occurs near the apical foramen and significantly increases when the isthmus is located closer to the apical foramina.

Establishment and evaluation of a deep learning-based tooth wear severity grading system using intraoral photographs

Background/purposeArtificial intelligence (AI) can assist in medical diagnosis owing to its high accuracy and efficiency. This study aimed to develop a diagnostic system for automatically determining the degree of tooth wear (TW) using intraoral photographs with deep learning. Materials and methodsThe study included 388 intraoral photographs. A tooth segmentation model was first established using the Mask R-CNN architecture, which incorporated U-Net and SGE attention mechanisms. Subsequently, 2774 individual tooth images output from the segmentation model were included into the classification task, labeled and randomized into training, validation, and test sets with 6.0:2.0:2.0 ratio. A vision transformer model optimized using a mask mechanism was constructed for TW degree classification. The models were evaluated using the accuracy, precision, recall, and F1-score metrics. The time required for AI analysis was calculated. ResultsThe accuracy of the tooth segmentation model was 0.95. The average accuracy, precision, recall, and F1-score in the classification task were 0.93, 0.91, 0.88, and 0.89, respectively. The F1-score differed in different grades (0.97 for grade 0, 0.90 for grade 1, 0.88 for grade 2, and 0.82 for grade 3). No significant difference was observed in the accuracy between different surfaces. The AI system reduced the time required to grade an individual tooth surface to 0.07 s, compared to the 2.67 s required by clinicians. ConclusionThe developed system provides superior accuracy and efficiency in determining TW degree using intraoral photographs. It might assist clinicians in the decision-making for TW treatment and help patients perform self-assessments and disease follow-ups.

CBCT ANALYSIS OF PULP CHAMBER THICKNESS AND MORPHOLOGY IN PRIMARY MOLARS: AN OBSERVATIONAL STUDY

Objective: To evaluate the thickness of pulp chamber and morphologic characteristics in order to plan the treatment ofdeciduous molars using cone beam computed tomography. Material and Methods: Cross-Sectional study is done with CBCT images of primary teeth of children. Evaluation of Pulp chamber thickness and morphology of each maxillary right primary second molar was done through CBCT. Data were analyzed and sent for statistical analysis. Results: Total 50 teeth i.e., right maxillary primary second molars of children age group 4-10 years were analyzed. Male shows the horizontal and vertical Mean (SD) values 4.5 (0.76) and 1.7(0.58) respectively greater than females. Mesial and Distal pulp horns were also greater in height for males with Mean (SD) 3.1(0.51) and 2.5(0.52) respectively. Conclusion:General variations might be involved however, when preparing a course of treatment for a childit is important to take note of gender differences in the mesiobuccal pulp horn. Even small restorations have a significant effect on pulp size. Probably it becomes exposed when the cavity is being prepared.