Integrating Structured Digital Tools with the Traditional Hands-on Puzzle Method for Teaching Tooth Morphology: A Comparative Study of Educational Outcomes.

The study of tooth morphology is a critical component of the dental curriculum, highlighting the importance for dental students to acquire comprehensive and detailed knowledge of the complex structure of teeth. This study compared the educational outcomes of two student cohorts in a tooth morphology course, using traditional methods for the control group and additional digital video-based resources for the experimental group. We hypothesized that early integration of digital resources would significantly reduce the learning time. We retrospectively analyzed two groups of Master of Dentistry students. The control group (42 students) was taught using the traditional 'tooth puzzle' method, while the experimental group (42 students) supplemented traditional teaching with digital video-based tools developed by our department. Both groups' curricula culminated in a practical post-course test requiring the identification of 40 teeth, along with a mid-course test to track the students' learning progression. The number and type of incorrectly identified teeth were recorded. The mid-course test showed significant performance differences. The control group had a median (Q1, Q3) value of faults of 12.0 (7.8, 20.5), whereas the respective value for the experimental group was 4.0 (0.0, 8.0) (p < 0.001). In the control group, none achieved faultless results, with only two students (4.8%) having at most two faults, and six students (14.3%) having no more than four faults. The control group averaged 13.5 faults per student, with 19 students (45.2%) failing the test. Conversely, the experimental group showed improved performance: 12 students (28.6%) had no faults, and 25 students (59.5%) had four or fewer faults. The experimental group averaged 5.2 faults per student, with only four students (9.5%) failing. By the end of the course, both groups achieved commendable results on the practical tooth identification test. The experimental group slightly outperformed the control group, though the difference was not significant. The median (Q1, Q3) values were 0.0 (0.0, 2.5) and 1.0 (0.0, 4.5) for the experimental and control groups, respectively (p = 0.372). The students using both traditional and structured digital video-based tools showed greater learning advancement than those using only the traditional 'tooth puzzle' method.

[Tooth segmentation and identification on cone-beam computed tomography with convolutional neural network based on spatial embedding information].

OBJECTIVE: To propose a novel neural network to achieve tooth instance segmentation and recognition based on cone-beam computed tomography (CBCT) voxel data. METHODS: The proposed methods included three different convolutional neural network models. The architecture was based on the Resnet module and built according to the structure of "Encoder-Decoder" and U-Net. The CBCT image was de-sampled and a fixed-size region of interest (ROI) containing all the teeth was determined. ROI would first through a two-branch "encoder and decoder" structure of the network, the network could predict each voxel in the input data of the spatial embedding. The post-processing algorithm would cluster the prediction results of the relevant spatial location information according to the two-branch network to realize the tooth instance segmentation. The tooth position identification was realized by another U-Net model based on the multi-classification segmentation task. According to the predicted results of the network, the post-processing algorithm would classify the tooth position according to the voting results of each tooth instance segmentation. At the original spatial resolution, a U-Net network model for the fine-tooth segmentation was trained using the region corresponding to each tooth as the input. According to the results of instance segmentation and tooth position identification, the model would process the correspon-ding positions on the high-resolution CBCT images to obtain the high-resolution tooth segmentation results. In this study, CBCT data of 59 cases with simple crown prostheses and implants were collected for manual labeling as the database, and statistical indicators were evaluated for the prediction results of the algorithm. To assess the performance of tooth segmentation and classification, instance Dice similarity coefficient (IDSC) and the average Dice similarity coefficient (ADSC) were calculated. RESULTS: The experimental results showed that the IDSC was 89.35%, and the ADSC was 84. 74%. After eliminating the data with prostheses artifacts, the database of 43 samples was generated, and the performance of the training network was better, with 90.34% for IDSC and 87.88% for ADSC. The framework achieved excellent performance on tooth segmentation and identification. Voxels near intercuspation surfaces and fuzzy boundaries could be separated into correct instances by this framework. CONCLUSIONS: The results show that this method can not only successfully achieve 3D tooth instance segmentation but also identify all teeth notation numbers accurately, which has clinical practicability.

Traditional Hands-On Puzzle Method versus Fully Digital Approach in Teaching Tooth Morphology: A Comparative Study of Educational Outcomes.

OBJECTIVE: Tooth morphology education is a critical component of dental curricula, providing a foundational understanding of the intricate structural anatomy of teeth. This study evaluates the learning outcomes in relation to tooth morphology of two student cohorts from different academic terms, comparing the traditional 'tooth puzzle' method to an alternative fully digital approach. MATERIALS AND METHODS: Two groups of Master of Dentistry students were retrospectively analyzed. The control group (55 students) was taught via the 'tooth puzzle' method in 2021, while the experimental group (55 students) underwent a fully digital course in 2020 due to COVID-19 restrictions. Both groups completed a digital examination involving the identification of 40 teeth, presented as images and videos. RESULTS: In the control group of 55 students, nearly half (49.1%) achieved faultless results, while 65.5% had at most two faults, and 74.5% had no more than four faults. The group had a total of 163 faults, averaging 3.0 per student, with only one student (1.8%) failing the test. In stark contrast, the experimental group had no students without faults, 9.1% had four or fewer faults, and a significant 61.8% made 10 or more faults, with 29.1% failing their first test attempt by exceeding 12 faults. Overall, the experimental group registered 582 faults, averaging 10.6 per student. CONCLUSIONS: The 'tooth puzzle' method, with its interactive and tactile elements, proved more effective in teaching tooth morphology than the digital-only approach. The increased number of faults and failed tests in the experimental group suggest that while digital tools offer meaningful support in learning tooth morphology, their main advantage is seen when coupled with traditional hands-on techniques, not unassisted and independently.

Application of deep learning in isolated tooth identification.

BACKGROUND: Teeth identification has a pivotal role in the dental curriculum and provides one of the important foundations of clinical practice. Accurately identifying teeth is a vital aspect of dental education and clinical practice, but can be challenging due to the anatomical similarities between categories. In this study, we aim to explore the possibility of using a deep learning model to classify isolated tooth by a set of photographs. METHODS: A collection of 5,100 photographs from 850 isolated human tooth specimens were assembled to serve as the dataset for this study. Each tooth was carefully labeled during the data collection phase through direct observation. We developed a deep learning model that incorporates the state-of-the-art feature extractor and attention mechanism to classify each tooth based on a set of 6 photographs captured from multiple angles. To increase the validity of model evaluation, a voting-based strategy was applied to refine the test set to generate a more reliable label, and the model was evaluated under different types of classification granularities. RESULTS: This deep learning model achieved top-3 accuracies of over 90% in all classification types, with an average AUC of 0.95. The Cohen's Kappa demonstrated good agreement between model prediction and the test set. CONCLUSIONS: This deep learning model can achieve performance comparable to that of human experts and has the potential to become a valuable tool for dental education and various applications in accurately identifying isolated tooth.

Different Methods of Teaching and Learning Dental Morphology.

Dental anatomy education is traditionally structured into theoretical and practical modules to foster both cognitive and psychomotor development. The theoretical module typically involves didactic lectures where educators elucidate dental structures using visual aids. In contrast, practical modules utilize three-dimensional illustrations, extracted and plastic teeth, and tooth carving exercises on wax or soap blocks, chosen for their cost, ease of handling, and fidelity in replication. However, the efficacy of these traditional methods is increasingly questioned. The criticism in this concern is that oversized carving materials may distort students' understanding of anatomical proportions, potentially affecting the development of necessary skills for clinical practice. Lecture-driven instruction, on the other hand, is also criticized for its limitations in fostering interactive learning, resulting in a gap between pre-clinical instruction and practical patient care. In this study, we review the various educational strategies that have emerged to enhance traditional dental anatomy pedagogy by describing the effectiveness of conventional didactic lectures, wax carving exercises, the use of real and artificial teeth, the flipped classroom model, and e-learning tools. Our review aims to assess each method's contribution to improving clinical applicability and educational outcomes in dental anatomy, with a focus on developing pedagogical frameworks that align with contemporary educational needs and the evolving landscape of dental practice. We suggest that the optimal approach for teaching tooth morphology would be to integrate the digital benefits of the flipped classroom model with the practical, hands-on experience of using extracted human teeth. To address the challenges presented by this integration, the creation and standardization of three-dimensional tooth morphology educational tools, complemented with concise instructional videos for a flipped classroom setting, appears to be a highly effective strategy.

Identifying teeth and tooth fragments from digital 3D models.

Dental anatomy is an essential skill for human identification in forensic odontology. With the advent of technology enabling virtual autopsies, there is scope for virtual consultation by forensic odontologists especially when the expertise is unavailable but needed in zones of conflict or disasters. This study aimed to investigate potential benefits and challenges of identifying intact and damaged teeth from 3D scanned digital models. Ten 3D tooth models - nine permanent and deciduous human teeth and one animal tooth were uploaded on a hosting platform. A 3-part survey was circulated among 60 forensic odontologists with questions about demography (P1), tooth identification of the scanned 3D models (P2) and the perceived usefulness of 3D models for tooth identification (P3). This was the first time that a survey required the identification of individual human teeth (intact or not) and animal tooth combined. The response rate for study participation was 58%. Substantial agreement among participants was seen in the determination of tooth classification (i.e., molars, premolars) or non-human and tooth within the same tooth class (i.e., lateral incisors, second molar) (both k=0.61). The least agreement (k=0.21) was seen in identification of tooth according to the FDI notation with a mean accuracy of 0.34. While most responders correctly identified the animal tooth, most incorrect responses were seen in the identification of the intact third molar. While 3D-scanned teeth have the potential to be identified virtually, forensic odontologists should continuously test their skills in tooth morphology and dental anatomy of humans (damaged or not) and animals.

Deep learning for tooth identification and enumeration in panoramic radiographs.

Background: Dentists begin the diagnosis by identifying and enumerating teeth. Panoramic radiographs are widely used for tooth identification due to their large field of view and low exposure dose. The automatic numbering of teeth in panoramic radiographs can assist clinicians in avoiding errors. Deep learning has emerged as a promising tool for automating tasks. Our goal is to evaluate the accuracy of a two-step deep learning method for tooth identification and enumeration in panoramic radiographs. Materials and Methods: In this retrospective observational study, 1007 panoramic radiographs were labeled by three experienced dentists. It involved drawing bounding boxes in two distinct ways: one for teeth and one for quadrants. All images were preprocessed using the contrast-limited adaptive histogram equalization method. First, panoramic images were allocated to a quadrant detection model, and the outputs of this model were provided to the tooth numbering models. A faster region-based convolutional neural network model was used in each step. Results: Average precision (AP) was calculated in different intersection-over-union thresholds. The AP50 of quadrant detection and tooth enumeration was 100% and 95%, respectively. Conclusion: We have obtained promising results with a high level of AP using our two-step deep learning framework for automatic tooth enumeration on panoramic radiographs. Further research should be conducted on diverse datasets and real-life situations.

Collaborative deep learning model for tooth segmentation and identification using panoramic radiographs.

Panoramic radiographs are an integral part of effective dental treatment planning, supporting dentists in identifying impacted teeth, infections, malignancies, and other dental issues. However, screening for anomalies solely based on a dentist's assessment may result in diagnostic inconsistency, posing difficulties in developing a successful treatment plan. Recent advancements in deep learning-based segmentation and object detection algorithms have enabled the provision of predictable and practical identification to assist in the evaluation of a patient's mineralized oral health, enabling dentists to construct a more successful treatment plan. However, there has been a lack of efforts to develop collaborative models that enhance learning performance by leveraging individual models. The article describes a novel technique for enabling collaborative learning by incorporating tooth segmentation and identification models created independently from panoramic radiographs. This collaborative technique permits the aggregation of tooth segmentation and identification to produce enhanced results by recognizing and numbering existing teeth (up to 32 teeth). The experimental findings indicate that the proposed collaborative model is significantly more effective than individual learning models (e.g., 98.77% vs. 96% and 98.44% vs.91% for tooth segmentation and recognition, respectively). Additionally, our models outperform the state-of-the-art segmentation and identification research. We demonstrated the effectiveness of collaborative learning in detecting and segmenting teeth in a variety of complex situations, including healthy dentition, missing teeth, orthodontic treatment in progress, and dentition with dental implants.

Individual tooth detection and identification from dental panoramic X-ray images via point-wise localization and distance regularization.

Dental panoramic X-ray imaging is a popular diagnostic method owing to its very small dose of radiation. For an automated computer-aided diagnosis system in dental clinics, automatic detection and identification of individual teeth from panoramic X-ray images are critical prerequisites. In this study, we propose a point-wise tooth localization neural network by introducing a spatial distance regularization loss. The proposed network initially performs center point regression for all the anatomical teeth (i.e., 32 points), which automatically identifies each tooth. A novel distance regularization penalty is employed on the 32 points by considering L2 regularization loss of Laplacian on spatial distances. Subsequently, teeth boxes are individually localized using a multitask neural network on a patch basis. A multitask offset training is employed on the final output to improve the localization accuracy. Our method successfully localizes not only the existing teeth but also missing teeth; consequently, highly accurate detection and identification are achieved. The experimental results demonstrate that the proposed algorithm outperforms state-of-the-art approaches by increasing the average precision of teeth detection by 15.71 % compared to the best performing method. The accuracy of identification achieved a precision of 0.997 and recall value of 0.972. Moreover, the proposed network does not require any additional identification algorithm owing to the preceding regression of the fixed 32 points regardless of the existence of the teeth.

Tooth identification puzzle: A method of teaching and learning tooth morphology.

INTRODUCTION: The present report outlines a method of teaching/learning tooth morphology by tooth identification puzzle. MATERIALS AND METHODS: Students are presented with sets of extracted human teeth comprising complete dentitions except deciduous incisors and canines. The task is to place the teeth in correct positions in a schematic dentition diagram. The course, including 2-3 introductory lectures and a final test of one hour, has a time frame of 14-16 hours. A total of 506 2nd year students from several years participated. RESULTS: The course is much appreciated by the students who experience a marked progress in skills. In the final test, 51.8% of the students had no faults, whilst 3% failed (more than 12 faults). The average number of faults per student was 2.3. Of the 20 240 positioned teeth 5.7% were misplaced. The most frequently misplaced teeth were mandibular central incisors, maxillary second premolars and mandibular first premolars. The most common type of fault was inside determination. DISCUSSION: The course is cost-effective and facilitates learning through its multifaceted activity with involvement of many senses. An important asset is the appreciation of variations in tooth morphology. The course provides an arena for close and positive interaction between students and teachers.