Performance evaluation of deep learning models for the classification and identification of dental implants.

STATEMENT OF PROBLEM: Dental implant systems can be identified using image classification deep learning. However, investigations on the accuracy of classifying and identifying implant design through an object detection model are lacking. PURPOSE: The purpose of this study was to evaluate the performance of an object detection deep learning model for classifying the implant designs of 103 types of implants. MATERIAL AND METHODS: From panoramic radiographs, 14 037 implant images were extracted. Implant designs were subdivided into 10 classes in the coronal, 13 in the middle, and 10 in the apical third. Classes with fewer than 50 images were excluded from the training dataset. Among the images, 80% were used as training data, and the remaining 20% as test data; the data were generated 3 times for 3-fold cross-validation (implant datasets 1, 2, and 3). Versions 5 and 7 of you only look once (YOLO) algorithm were used to train the model, and the mean average precision (mAP) was evaluated. Subsequently, data augmentation was performed using image processing and a real-enhanced super-resolution generative adversarial network, and the accuracy was re-evaluated using YOLOv7. RESULTS: The mAP of YOLOv7 in the 3 datasets was 0.931, 0.984, and 0.884, respectively, which were higher than the mAP of YOLOv5. After image processing in implant dataset-1, the mAP improved to 0.986 and, with the real-enhanced super-resolution generative adversarial network, to 0.988 and 0.986 at magnification ×2 and ×4, respectively. CONCLUSIONS: The object detection model for classifying implant designs found a high accuracy for 26 classes. The mAP of the model differed depending on the type of algorithm, image processing process, and detailed implant design.

Classification of dental implant systems using cloud-based deep learning algorithm: an experimental study.

BACKGROUND: This study aimed to evaluate the accuracy and clinical usability of implant system classification using automated machine learning on a Google Cloud platform. METHODS: Four dental implant systems were selected: Osstem TSIII, Osstem USII, Biomet 3i Os-seotite External, and Dentsply Sirona Xive. A total of 4,800 periapical radiographs (1,200 for each implant system) were collected and labeled based on electronic medical records. Regions of interest were manually cropped to 400×800 pixels, and all images were uploaded to Google Cloud storage. Approximately 80% of the images were used for training, 10% for validation, and 10% for testing. Google automated machine learning (AutoML) Vision automatically executed a neural architecture search technology to apply an appropriate algorithm to the uploaded data. A single-label image classification model was trained using AutoML. The performance of the mod-el was evaluated in terms of accuracy, precision, recall, specificity, and F1 score. RESULTS: The accuracy, precision, recall, specificity, and F1 score of the AutoML Vision model were 0.981, 0.963, 0.961, 0.985, and 0.962, respectively. Osstem TSIII had an accuracy of 100%. Osstem USII and 3i Osseotite External were most often confused in the confusion matrix. CONCLUSION: Deep learning-based AutoML on a cloud platform showed high accuracy in the classification of dental implant systems as a fine-tuned convolutional neural network. Higher-quality images from various implant systems will be required to improve the performance and clinical usability of the model.

Identification of 130 Dental Implant Types Using Ensemble Deep Learning.

Purpose: To evaluate the accuracy and clinical usability of an identification model using ensemble deep learning for 130 dental implant types. Materials and Methods: A total of 28,112 panoramic radiographs were obtained from 30 domestic and foreign dental clinics. From these panoramic radiographs, 45,909 implant fixture images were extracted and labeled based on electronic medical records. Dental implants were classified into 130 types according to the manufacturer, the manufacturer's implant system, and the diameter and length of the implant fixture. Regions of interest were manually cropped, and data augmentation was performed. According to the minimum number of images collected per implant type, the datasets were classified into three sets: an overall total of 130 and two subsets that consisted of 79 and 58 types. EfficientNet and Res2Next algorithms were used for image classification in deep learning. After testing the performance of the two models, the ensemble learning technique was applied to improve accuracy. The top-1 accuracy, top-5 accuracy, precision, recall, and F1 scores were calculated according to algorithms and datasets. Results: For the 130 types, the top-1 accuracy, top-5 accuracy, precision, recall, and F1 scores were 75.27, 95.02, 78.84, 75.27, and 74.89, respectively. In all cases, the ensemble model performed better than EfficientNet and Res2Next. When using the ensemble model, the accuracy increased as the number of types decreased. Conclusion: The ensemble deep learning model for the identification of 130 types of dental implants showed higher accuracy than the existing algorithms. To further improve the performance and clinical usability of the model, images with higher quality and fine-tuned algorithms optimized for implant identification are required.

Marginal and internal fit of 3D printed provisional crowns according to build directions.

PURPOSE: This study aimed to fabricate provisional crowns at varying build directions using the digital light processing (DLP)-based 3D printing and evaluate the marginal and internal fit of the provisional crowns using the silicone replica technique (SRT). MATERIALS AND METHODS: The prepared resin tooth was scanned and a single crown was designed using computer-aided design (CAD) software. Provisional crowns were printed using a DLP-based 3D printer at 6 directions (120°, 135°, 150°, 180°, 210°, 225°) with 10 crowns in each direction. In total, sixty crowns were printed. To measure the marginal and internal fit, a silicone replica was fabricated and the thickness of the silicone impression material was measured using a digital microscope. Sixteen reference points were set and divided into the following 4 groups: marginal gap (MG), cervical gap (CG), axial gap (AG), and occlusal gap (OG). The measurements were statistically analyzed using one-way ANOVA and Dunnett T3. RESULTS: MG, CG, and OG were significantly different by build angle groups (P<.05). The MG and CG were significantly larger in the 120° group than in other groups. OG was the smallest in the 150° and 180° and the largest in the 120° and 135° groups. CONCLUSION: The marginal and internal fit of the 3D-printed provisional crowns can vary depending on the build angle and the best fit was achieved with build angles of 150° and 180°.

The Use of Computer-Guided Surgery to Avoid Severe Buccal Defect and Lingual Concavity in Mandibular Implant Placement.

Dental implant treatment planning has traditionally been accomplished using 2-dimensional radiographs and stone models. Although historically this method has been used with success, there are limitations. Two-dimensional radiographs and stone models may not allow for accurate diagnosis of ridge defects or the presence of a mandibular lingual concavity. The use of cone-beam computed tomography (CBCT) can help the dental practitioner identify such structures. Computer-generated surgical guides allow the dental surgeon to safely place implants in a minimally invasive manner. This case report describes the utilization of CBCT and computer-generated surgical guides to help facilitate mandibular dental implant placement in the presence of a buccal ridge defect and lingual concavity.