Multi-Task Deep Learning Model for Classification of Dental Implant Brand and Treatment Stage Using Dental Panoramic Radiograph Images.
Ontology highlight
ABSTRACT:
SUBMITTER: Sukegawa S
PROVIDER: S-EPMC8226505 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Attention mechanism, which is a means of determining which part of the forced data is emphasized, has attracted attention in various fields of deep learning in recent years. The purpose of this study was to evaluate the performance of the attention branch network (ABN) for implant classification using convolutional neural networks (CNNs). The data consisted of 10191 dental implant images from 13 implant brands that cropped the site, including dental implants as pretreatment, from digital panoramic radiographs of patients who underwent surgery at Kagawa Prefectural Central Hospital between 2005 and 2021. ResNet 18, 50, and 152 were evaluated as CNN models that were compared with and without the ABN. We used accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristics curve as performance metrics. We also performed statistical and effect size evaluations of the 30-time performance metrics of the simple CNNs and the ABN model. ResNet18 with ABN significantly improved the dental implant classification performance for all the performance metrics. Effect sizes were equivalent to "Huge" for all performance metrics. In contrast, the classification performance of ResNet50 and 152 deteriorated by adding the attention mechanism. ResNet18 showed considerably high compatibility with the ABN model in dental implant classification (AUC = 0.9993) despite the small number of parameters. The limitation of this study is that only ResNet was verified as a CNN; further studies are required for other CNN models.
| S-EPMC9328496 | biostudies-literature
Project description:BackgroundDental implant failure is a critical condition that can seriously compromise therapeutic efficacy. Insufficient bone volume, unfavorable bone quality, periodontal bone loss, and systemic conditions, including osteopenia/osteoporosis and diabetes mellitus, have been associated with implant failure. Early indicators of potential implant failure could help mitigate the risk of severe complications. This study aimed to develop an effective implant outcome prediction model using dental periapical and panoramic films.MethodsA total of 248 patients (89 with failed implants and 159 with successful implants) were examined. A total of 529 periapical images and 551 panoramic images were collected from the patients for a deep learning-based model. Based on radiographic peri-implant alveolar bone pattern, implant outcome was divided into three categories: implant failure with marginal bone loss, implant failure without marginal bone loss, and implant success. We extracted features using a deep convolutional neural network (CNN) and built a hybrid model to combine periapical and panoramic images. A comparison among three categories of receiver operating characteristic (ROC) curves was performed. The diagnostic accuracy, precision, recall and F1-score of the dataset were assessed.ResultsOur model achieved an AUC (area under the ROC curve) of 0.972 for failure with marginal bone loss, 0.947 for failure without marginal bone loss and 0.975 for success. In all conditions, for periapical images alone, the diagnostic accuracy was 78.6%; the precision was 0.84, recall was 0.73, and F1-score was 0.75. For panoramic images alone, the diagnostic accuracy was 78.7%; the precision was 0.87, recall was 0.63, and F1-score was 0.66. Both periapical and panoramic images were used in our novel method, and the prediction accuracy was 87%. The precision was 0.85, recall was 0.88, and F1-score was 0.85.ConclusionsThe deep learning model used features from periapical and panoramic images to effectively predict the occurrence of implant failure and might facilitate early clinical intervention for potential dental implant failures.
| S-EPMC9929426 | biostudies-literature
Project description:In this study, we used panoramic X-ray images to classify and clarify the accuracy of different dental implant brands via deep convolutional neural networks (CNNs) with transfer-learning strategies. For objective labeling, 8859 implant images of 11 implant systems were used from digital panoramic radiographs obtained from patients who underwent dental implant treatment at Kagawa Prefectural Central Hospital, Japan, between 2005 and 2019. Five deep CNN models (specifically, a basic CNN with three convolutional layers, VGG16 and VGG19 transfer-learning models, and finely tuned VGG16 and VGG19) were evaluated for implant classification. Among the five models, the finely tuned VGG16 model exhibited the highest implant classification performance. The finely tuned VGG19 was second best, followed by the normal transfer-learning VGG16. We confirmed that the finely tuned VGG16 and VGG19 CNNs could accurately classify dental implant systems from 11 types of panoramic X-ray images.
| S-EPMC7407934 | biostudies-literature
Project description:ObjectivesThis study aimed to investigate the accuracy of deep learning algorithms to diagnose tooth caries and classify the extension and location of dental caries in cone beam computed tomography (CBCT) images. To the best of our knowledge, this is the first study to evaluate the application of deep learning for dental caries in CBCT images.MethodsThe CBCT image dataset comprised 382 molar teeth with caries and 403 noncarious molar cases. The dataset was divided into a development set for training and validation and test set. Three images were obtained for each case, including axial, sagittal, and coronal. The test dataset was provided to a multiple-input convolutional neural network (CNN). The network made predictions regarding the presence or absence of dental decay and classified the lesions according to their depths and types for the provided samples. Accuracy, sensitivity, specificity, and F1 score values were measured for dental caries detection and classification.ResultsThe diagnostic accuracy, sensitivity, specificity, and F1 score for caries detection in carious molar teeth were 95.3%, 92.1%, 96.3%, and 93.2%, respectively, and for noncarious molar teeth were 94.8%, 94.3%, 95.8%, and 94.6%. The CNN network showed high sensitivity, specificity, and accuracy in classifying caries extensions and locations.ConclusionsThis research demonstrates that deep learning models can accurately identify dental caries and classify their depths and types with high accuracy, sensitivity, and specificity. The successful application of deep learning in this field will undoubtedly assist dental practitioners and patients in improving diagnostic and treatment planning in dentistry.Clinical significanceThis study showed that deep learning can accurately detect and classify dental caries. Deep learning can provide dental caries detection accurately. Considering the shortage of dentists in certain areas, using CNNs can lead to broader geographic coverage in detecting dental caries.
| S-EPMC10988262 | biostudies-literature
Project description:BackgroundIn dentistry, the reporting of panoramic radiographs is particularly challenging, as many structures are depicted in one image and pathologies need to be identified completely. To enhance the learning process for these interpretations, the advantages of the increasingly popular education method of mobile learning could be used. Therefore, this study aimed to determine the effectiveness of learning to report panoramic radiographs using an application (app) on a mobile device.MethodsThe existing e-learning programme 'PantoDict' was further developed into a mobile app with a new training section. Participants of a dental radiology course were divided into two groups, one of which additionally had the chance to practise reporting panoramic radiographs using the app. A test to assess the knowledge gained was conducted at the end of the semester; the course and the app were also evaluated.ResultsThe group that used the app showed significantly better results in the test than the control group (p < 0.05). Although the app group approved a high satisfaction using the app as an additional supplement to the course, this did not result in a higher overall satisfaction with the course. Further, these students observed that the traditional face-to-face seminar could not be replaced by the app.ConclusionBy using the PantoDict app, students were offered better training options for writing reports on panoramic radiographs, which resulted in significantly better test results than the results of the control group. Therefore, the mobile app is a useful supplement to classical education formats within the context of a blended learning approach.
| S-EPMC8411548 | biostudies-literature
Project description:PurposeTo answer the following clinical research question: "Among patients with multiple basal cell carcinomas (mBCCs), can panoramic radiograph (PaR) facilitate the diagnosis of Gorlin-Goltz syndrome (GGS)?"MethodsThis retrospective study enrolled mBCCs subjects who presented to a German tertiary care center between 1 January 2015 and 31 December 2021. The primary predictor was presence of syndromic mBCCs, and the main outcomes were jaw cysts and odontogenic keratocysts (OKCs). Descriptive, bi- and multivariate statistics, diagnostic test evaluation, and number needed to screen (NNS) were computed at α = 95%.ResultsThe sample comprised 527 mBCCs patients (36.1% females; 6.8% GGS; 5.5% OKCs; mean age, 74.5 ± 15.8 years [range, 15-102]). There was a significant association between syndromic mBCCs and jaw cysts (P < .0001; NNS = 2 [95% CI, CI, 1.1 to 1.4]). In the adjusted logistic model, PaR identified GGS via radiographic diagnosis of jaw cysts in case of 1) age ≤ 35 years, 2) ≥ 5 BCCs, and 3) ≥ 1 high-risk BCCs. Nearly every jaw cyst identified by PaR was OKCs (P = .01; 95% CI, 3.1 to 3,101.4; NNS = 1.3 [95% CI, .9 to 2]). The post hoc power was 100%.ConclusionsDental screening with the use of PaR for mBCCs patients, especially those aged ≤35 years, or with ≥5 BCCs, or ≥1 high-risk BCCs, may be helpful in detection and identification of GGS through recognition of OKCs.
| S-EPMC9729970 | biostudies-literature
Project description:This study investigated two artificial intelligence (AI) methods for automatically classifying dental implant diameter and length based on periapical radiographs. The first method, deep learning (DL), involved utilizing the pre-trained VGG16 model and adjusting the fine-tuning degree to analyze image data obtained from periapical radiographs. The second method, clustering analysis, was accomplished by analyzing the implant-specific feature vector derived from three key points coordinates of the dental implant using the k-means++ algorithm and adjusting the weight of the feature vector. DL and clustering model classified dental implant size into nine groups. The performance metrics of AI models were accuracy, sensitivity, specificity, F1-score, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC-ROC). The final DL model yielded performances above 0.994, 0.950, 0.994, 0.974, 0.952, 0.994, and 0.975, respectively, and the final clustering model yielded performances above 0.983, 0.900, 0.988, 0.923, 0.909, 0.988, and 0.947, respectively. When comparing the AI model before tuning and the final AI model, statistically significant performance improvements were observed in six out of nine groups for DL models and four out of nine groups for clustering models based on AUC-ROC. Two AI models showed reliable classification performances. For clinical applications, AI models require validation on various multicenter data.
| S-EPMC10558577 | biostudies-literature
Project description:The radiographic anatomy on dental panoramic images is essential knowledge for proper diagnosis and treatment planning purposes. No prior study has examined the content of YouTube videos with regard to radiographic anatomy on panoramic radiography. The objective of this study was to provide a content analysis on these videos. The initial search string was: (panoramic anatomy). An additional search was performed with the search string: (OPG landmarks). By screening the resultant videos and their related videos (recommended by YouTube as a list on the right of the screen), a total of 62 videos were screened. Videos were excluded if they were irrelevant (e.g., focusing on radiographic errors without covering the anatomy), elaborating mainly with drawings without showing the landmarks on panoramic images, duplicate videos, and non-English speaking. Finally, 38 videos were included and analyzed. Most of them showed clear panoramic images and had clear tracing or delineation of the anatomical landmarks. On average, each video described 26 landmarks, including 12.3 from the midfacial region, 8.2 from the mandible, and 5.2 from soft tissue/air space/others. The videos were of good quality in general, with some frequent shortcomings being lack of visual aid with skull and schematic diagrams, and lack of discussion on clinical relevance. The maxillary sinus was the structure mostly involved in wrong information, particularly the wrong delineation of its posterior wall.
| S-EPMC9332186 | biostudies-literature
Project description:Convolutional Neural Networks (CNNs) such as U-Net have been widely used for medical image segmentation. Dental restorations are prominent features of dental radiographs. Applying U-Net on the panoramic image is challenging, as the shape, size and frequency of different restoration types vary. We hypothesized that models trained on smaller, equally spaced rectangular image crops (tiles) of the panoramic would outperform models trained on the full image. A total of 1781 panoramic radiographs were annotated pixelwise for fillings, crowns, and root canal fillings by dental experts. We used different numbers of tiles for our experiments. Five-times-repeated three-fold cross-validation was used for model evaluation. Training with more tiles improved model performance and accelerated convergence. The F1-score for the full panoramic image was 0.7, compared to 0.83, 0.92 and 0.95 for 6, 10 and 20 tiles, respectively. For root canals fillings, which are small, cone-shaped features that appear less frequently on the radiographs, the performance improvement was even higher (+294%). Training on tiles and pooling the results thereafter improved pixelwise classification performance and reduced the time to model convergence for segmenting dental restorations. Segmentation of panoramic radiographs is biased towards more frequent and extended classes. Tiling may help to overcome this bias and increase accuracy.
| S-EPMC9221749 | biostudies-literature
Project description:Background and aimsOral health could potentially be a modifiable risk factor for adverse outcomes in chronic kidney disease (CKD) patients transitioning from predialysis treatment to maintenance dialysis and transplantation. We aimed to study the association between an index of radiographically assessed oral health, Panoramic Tomographic Index (PTI), and cardiovascular and all-cause mortality, major adverse cardiovascular events (MACEs) and episodes of bacteremia and laboratory measurements during a three-year prospective follow-up in CKD stage 4-5 patients not on maintenance dialysis at baseline.MethodsAltogether 190 CKD stage 4-5 patients without maintenance dialysis attended panoramic dental radiographs in the beginning of the study. The patients were followed up for three years or until death. MACEs and episodes of bacteremia were recorded during follow-up. Laboratory sampling for C-reactive protein and leukocytes was repeated tri-monthly.ResultsPTI was not associated with baseline laboratory parameters or C-reactive protein or leukocytes examined as repeated measures through the 3-year follow-up. During follow-up, 22 patients had at least one episode of bacteremia, but only 2 of the bacteremias were considered to be of oral origin. PTI was not associated with incident bacteremia during follow-up. Thirty-six patients died during follow-up including 17 patients due to cardiovascular causes. During follow-up 42 patients were observed with a MACE. PTI was independently associated with all-cause (HR 1.074 95% CI 1.029-1.122, p = 0.001) and cardiovascular (HR 1.105, 95% CI 1.057-1.157, p<0.0001) mortality, as well as, incident MACEs (HR 1.071 95% CI 1.031-1.113, p = 0.0004) in the multivariable Cox models adjusted for age and kidney transplantation or CKD treatment modality during follow-up.ConclusionsRadiographically assessed dental health is independently associated with all-cause and cardiovascular mortality and MACEs but not with the incidence of bacteremia in CKD stage 4-5 patients transitioning to maintenance dialysis and renal transplantation during follow-up.
| S-EPMC8483312 | biostudies-literature