Digital Dentistry

Introduction: Thanks to the great development of digital technology, viaCAD (computer-aided design) and CAM (computer-aided manufacturing) systems, digital models canbe used as an aid for orthodontic planning decision-making processes as there are numerous studies in the literature that support the validity ofthe digital model measurements of anterior teeth and the total coefficient of Bolton analysis. The aim of the present study isto compare the average length value of the current upper and lower arches with that of a hypothetical nickel–titanium wire and to confirm the reliability and accuracy of digitally taken measurements of the anterior and total Bolton coefficients.In this retrospective study, dental casts of 138 Caucasian adolescent patients were scanned with an extraoral scanner, and Ortho3Shape software was adopted for the following dental cast measurements: actual and ideal lengths of the lower arches and anterior and total Bolton coefficients.In the present study, we found that the mean value of the anterior coefficients of the Bolton index was compatible with those of previous studies, confirming the reliability of digital measurements.Therefore, digital CAD/CAM models may be a viable alternative to plaster models, as they can facilitate model preservation and recovery. For future studies, it would be better to use intraoral scanners (IOSs) to ensure greater accuracy, since they only require one step and allow obtaining better results for the patients. Full article

In addition to their recognized value for obtaining 3D digital dental models, intraoral scanners (IOSs) have recently been proven to be promising tools for oral health diagnostics. In this work, the most recent literature on IOSs was reviewed with a focus on their applications as detection systems of oral cavity pathologies. Those applications of IOSs falling in the general area of detection systems for oral health diagnostics (e.g., caries, dental wear, periodontal diseases, oral cancer) were included, while excluding those works mainly focused on 3D dental model reconstruction for implantology, orthodontics, or prosthodontics. Three major scientific databases, namely Scopus, PubMed, and Web of Science, were searched and explored by three independent reviewers. The synthesis and analysis of the studies was carried out by considering the type and technical features of the IOS, the study objectives, and the specific diagnostic applications. From the synthesis of the twenty-five included studies, the main diagnostic fields where IOS technology applies were highlighted, ranging from the detection of tooth wear and caries to the diagnosis of plaques, periodontal defects, and other complications. This shows how additional diagnostic information can be obtained by combining the IOS technology with other radiographic techniques. Despite some promising results, the clinical evidence regarding the use of IOSs as oral health probes is still limited, and further efforts are needed to validate the diagnostic potential of IOSs over conventional tools. Full article

Background: The implementation of artificial intelligence brings with it a great change in health care, however, there is a discrepancy about the perceptions and attitudes that dental students present towards these new technologies. Methods: The study design was observational, descriptive, and cross-sectional. A total of 200 dental students who met the inclusion criteria were surveyed online. For the qualitative variables, descriptive statistical measures were obtained, such as absolute and relative frequencies. For the comparison of the main variables with the type of educational institution, sex and level of education, the chi-square test or Fisher′s exact test was used according to the established assumptions with a level of statistical significance of p < 0.05 and a confidence level of 95%. Results: The results indicated that 86% of the students surveyed agreed that artificial intelligence will lead to great advances in dentistry. However, 45% of the participants disagreed that artificial intelligence would replace dentists in the future. In addition, the respondents agreed that the use of artificial intelligence should be part of undergraduate and postgraduate studies with 67% and 72% agreement rates respectively. Conclusion: The attitudes and perceptions of the students indicate that 86% agreed that artificial intelligence will lead to great advances in dentistry. This suggests a bright future for the relationship between dentists and artificial intelligence. Full article

The current study aimed to implement and validate an automation system to detect carious lesions from smartphone images using different one-stage deep learning techniques. 233 images of carious lesions were captured using a smartphone camera system at 1432 × 1375 pixels, then classified and screened according to a visual caries classification index. Following data augmentation, the YOLO v5 model for object detection was used. After training the model with 1452 images at 640 × 588 pixel resolution, which included the ones that were created via image augmentation, a discrimination experiment was performed. Diagnostic indicators such as true positive, true negative, false positive, false negative, and mean average precision were used to analyze object detection performance and segmentation of systems. YOLO v5X and YOLO v5M models achieved superior performance over the other models on the same dataset. YOLO v5X’s mAP was 0.727, precision was 0.731, and recall was 0.729, which was higher than other models of YOLO v5, which generated 64% accuracy, with YOLO v5M producing slightly inferior results. Overall mAPs of 0.70, precision of 0.712, and recall of 0.708 were achieved. Object detection through the current YOLO models was able to successfully extract and classify regions of carious lesions from smartphone photographs of in vitro tooth specimens with reasonable accuracy. YOLO v5M was better fit to detect carious microcavitations while YOLO v5X was able to detect carious changes without cavitation. No single model was capable of adequately diagnosing all classifications of carious lesions. Full article

The present study explores the efficacy of Machine Learning and Artificial Neural Networks in age assessment using the root length of the second and third molar teeth. A dataset of 1000 panoramic radiographs with intact second and third molars ranging from 12 to 25 years was archived. The length of the mesial and distal roots was measured using ImageJ software. The dataset was classified in three ways based on the age distribution: 2–Class, 3–Class, and 5–Class. We used Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression models to train, test, and analyze the root length measurements. The mesial root of the third molar on the right side was a good predictor of age. The SVM showed the highest accuracy of 86.4% for 2–class, 66% for 3–class, and 42.8% for 5–Class. The RF showed the highest accuracy of 47.6% for 5–Class. Overall the present study demonstrated that the Deep Learning model (fully connected model) performed better than the Machine Learning models, and the mesial root length of the right third molar was a good predictor of age. Additionally, a combination of different root lengths could be informative while building a Machine Learning model. Full article

Background. The inaccurate maxillomandibular relationship of virtual casts following alignment by the vestibular scan may result in intersection (intermesh penetration) between opposing dental arch surfaces. Intersection occurs at short interocclusal distances in the occlusal contact area (OCA) and may result in infra-occluded definitive restorations. The purpose of this clinical study was to compare initial (by the proprietary scanner software) and new alignments (by a standalone 3D software) of virtual casts regarding OCA and intersection failure. New alignments aimed to rectify intersections by refinement of occlusal contacts. Material and Methods. The virtual casts of 30 patients following digital and conventional impression-taking were analyzed, which were acquired for single implant restoration in the posterior site. Digital impressions were performed by both IOS 1 (3M True Definition) and IOS 2 (TRIOS 3), either as complete- or partial-arch scans, respectively. Mounted gypsum casts were digitized as complete-arch by a laboratory scanner (LS) in enabled and disabled mode to avoid intersection [LS (+)/LS (−)]. All virtual casts were newly aligned by a 3D software. The difference of the OCA and the area of intersection were calculated for initial and new alignments, using interocclusal distance ranges of 0–100 μm, 0–10 μm or <0 μm (=intersection). The difference of the OCA was compared using a linear mixed model. The distribution of occlusal contact points per modality and alignment was assessed independently by three observers and estimated by inter- and intraclass correlation (ICC) coefficients. Results. Virtual casts following initial alignment demonstrated intersections irrespective of the modality. The mean area of the intersection was most for IOS 2 (79.23 mm²), followed by IOS 1 (48.28 mm²), LS (−) (2.77 mm²), and LS (+) (2.01 mm²) in partial-arch scans. Complete-arch scans demonstrated an area of intersection of 70.63 mm² for IOS 1 followed by 65.52 mm² (IOS 2), 6.13 mm² [LS (−)] and 2.76 mm² [LS (+)]. Newly aligned scans showed no intersections. The overall distribution of occlusal contact points demonstrated moderate reliability (ICC 0.63). Good reliability could be observed (ICC 0.9) for LS (−) scans. Conclusions. Intersections in the area of occlusal contact points are a phenomenon restricted to virtual casts, which should be considered in CAD/CAM. Initial alignments of LS are less affected by this virtual phenomenon, and contact points may be more distinct according to their anatomic region compared to IOS. Furthermore, intersections can be rectified in a 3D software by adjustment of the maxillomandibular relationship. Full article

Dental task trainer simulators using haptics (virtual touch) offers a cost-effective method of teaching certain clinical skills. The purpose of this study is to evaluate students’ performance in removing artificial caries after training with either a haptic dental chair simulator with virtual reality or a traditional dental chair simulator with a mannequin head. Cluster Randomized Controlled Trials in two cohorts, both Year 1 dental students. Students taught using traditional dental chair simulators were compared with students taught using haptic-based simulators on their ability to cut a cavity in a plastic tooth following training. Across both cohorts, there was no difference in the quality of cavity cut, though students’ technique differed across the two simulator groups in some respects. No difference was seen across both cohorts in the quality of cavity cut for a simple preparation, though students in the haptic condition performed less well in the more demanding task. Moreover, students in the haptic group were also less likely to be perceived to be ‘holding the instrument appropriately’. These findings suggest further investigation is needed into the differences in handling of instruments and level of clinical task difficulty between the simulators. Full article

The pattern of expansion of endodontic lesions in the jaws has been less commonly addressed in the literature. For this reason, the aim of this study is to assess the pattern of endodontic lesions of maxillary and mandibular posterior teeth using cone-beam computed tomography (CBCT). This cross-sectional study was conducted on 317 endodontic lesions of posterior teeth on CBCT scans retrieved from a radiology center in Qazvin, Iran, from 2020 to 2022. Endodontic lesions were assessed on sagittal, coronal, and axial sections by an endodontist and dental student using the Romexis software. The largest lesion diameter was measured occluso-apically, mesiodistally, and buccolingually. Lesion size was analyzed based on age, gender, jaw, tooth type, and presence/absence of root filling by independent samples t-tests and a one-way Analysis Of Variannce (ANOVA). The largest diameter of lesions in the maxilla and mandible was recorded in the occluso-apical dimension followed by buccolingual and mesiodistal dimensions (p > 0.05). The pattern of lesions was the same in teeth with and without endodontic treatment, but it was significantly different in maxillary and mandibular endodontically treated teeth in the occluso-apical and buccolingual dimensions (p < 0.05). No significant correlation was noted with tooth type or jaw except for maxillary and mandibular first molar lesions, which were significantly different in the occluso-apical dimension (p < 0.05). Lesion size in all three dimensions was significantly greater in males than females (p < 0.05), and was the highest in the occluso-apical dimension in both genders. In the maxilla, the mean lesion size significantly decreased in the mesiodistal dimension with age (p < 0.05). In conclusion, the largest lesion diameter in the maxilla and mandible was found in the occluso-apical dimension, indicating the role of bone density in the pattern of lesions. Full article

Background: The objective of this study was to propose a method that combines a maxilla-based coordinate system and mandibular voxel-based superimposition for an accurate evaluation of mandibular structural and positional changes and a direct comparison between maxillary and mandibular structural changes with the same 3D vectors. Methods: Mandibular voxel-based superimposition was firstly performed to reorient the mandibles and eliminate the mandibular positional changes. Then, a maxilla-based coordinate system was constructed with four maxillary skeletal landmarks (ANS, PNS, OrL and OrR). After settling the reoriented mandibles into this coordinate system, the mandibular structural changes were accurately evaluated. To assess the accuracy and reproducibility of this method, CBCT images of a skull specimen before and after orthodontic treatment (which was simulated by rearranging the skull and the mandible) were collected. Five mandibular skeletal landmarks, three mandibular dental landmarks and two mandibular measurement planes of this skull were used to evaluate the linear and angular changes in the mandibular structures. Results: There were significant differences in the linear and angular measurements of the mandibular structures of the skull (p ˂ 0.05), which indicated mandibular positional changes after orthodontic treatment. After mandibular voxel-based superimposition, there were no significant differences in the linear and angular measurements of mandibular structures, which indicated that the mandibular positional changes were eliminated. The intraclass correlation coefficient (ICC) value of the inter- and intra-observer agreement of all measurements was 0.99. Conclusions: This method has proven advantages in terms of accuracy, reproducibility and validity; with this method, mandibular structural and positional changes can be accurately evaluated and maxillary and mandibular structural changes can be directly compared with same 3D vectors. Full article