Automatic recognition of teeth and periodontal bone loss measurement in digital radiographs using deep-learning artificial intelligence.

Background/purpose: Artificial Intelligence (AI) can optimize treatment approaches in dental healthcare due to its high level of accuracy and wide range of applications. This study seeks to propose a new deep learning (DL) ensemble model based on deep Convolutional Neural Network (CNN) algorithms to predict tooth position, detect shape, detect remaining interproximal bone level, and detect radiographic bone loss (RBL) using periapical and bitewing radiographs. Materials and methods: 270 patients from January 2015 to December 2020, and all images were deidentified without private information for this study. A total of 8000 periapical radiographs with 27,964 teeth were included for our model. AI algorithms utilizing the YOLOv5 model and VIA labeling platform, including VGG-16 and U-Net architecture, were created as a novel ensemble model. Results of AI analysis were compared with clinicians' assessments. Results: DL-trained ensemble model accuracy was approximately 90% for periapical radiographs. Accuracy for tooth position detection was 88.8%, tooth shape detection 86.3%, periodontal bone level detection 92.61% and radiographic bone loss detection 97.0%. AI models were superior to mean accuracy values from 76% to 78% when detection was performed by dentists. Conclusion: The proposed DL-trained ensemble model provides a critical cornerstone for radiographic detection and a valuable adjunct to periodontal diagnosis. High accuracy and reliability indicate model's strong potential to enhance clinical professional performance and build more efficient dental health services.

Marginal Bone Loss around Implant-Retaining Overdentures versus Implant-Supported Fixed Prostheses 12-Month Follow-Up: A Retrospective Study.

Few studies have compared marginal bone loss (MBL) around implant-retaining overdentures (IODs) vs. implant-supported fixed prostheses (FPs). This study evaluated the mean MBL and radiographic bone-implant interface contact (r-BIIC) around IODs and implant-supported FPs. We also investigated osseointegration and MBL around non-submerged dental implants. We measured the changes between the MBL in the mesial and distal sites immediately after prosthetic delivery and after one year. The mean MBL and its changes in the IOD group were significantly higher. The mean percentage of r-BIIC was significantly higher in the FP group. MBL and its changes in males were significantly higher in the IOD group. The percentage of r-BIIC was significantly higher in the FP group. MBL in the lower site in the IOD group was significantly higher. Regarding MBL, the location of the implant was the only significant factor in the IOD group, while gender was the only significant predictor in the FP group. Regarding the r-BIIC percentage, gender was a significant factor in the FP group. We concluded that non-submerged dental implants restored with FPs and IODs maintained stable bone remodeling one year after prosthetic delivery.

Effect of Opposite Tooth Condition on Marginal Bone Loss around Submerged Dental Implants: A Retrospective Study with a 3-Year Follow-Up.

BACKGROUND: The objective of this study was to evaluate the effects of opposite tooth conditions on change in marginal bone level (MBL) around submerged dental implants. MATERIALS AND METHODS: The study included healthy patients with one or two implants. Structures opposite implants were either natural teeth (NT) or fixed restorations (FRs). MBLs were measured on digital periapical radiographs at the mesial and distal aspects of each implant. RESULTS: Sixty implants were inserted by the 3-year follow-up. Mean MBLs for NT were 0.21 ± 0.33 mm before prosthetic loading and 0.30 ± 0.41 mm 3 years later (p = 0.001). Mean MBLs with FRs were 0.36 ± 0.45 mm before loading and 0.53 ± 0.50 mm 3 years later (p < 0.001). Changes in mean MBL from the 6-month follow-up to the 1- and 3-year follow-ups were statistically significant (p < 0.01) for implants opposite NT. However, changes in mean MBL from the 6-month follow-up to the 1-year (p = 0.161) and 3-year follow-ups (p = 1.000) were not significant for implants opposite FRs. Between baseline and the 3-year follow-up, MBL change was relatively small and did not differ regarding NT and FRs. CONCLUSION: Bone loss was greater if submerged dental implants were opposed by FRs. MBLs around submerged implants continued to change after 3 years if NT opposed implants.

Guided Tissue Regeneration Treatment Yields Better Results in Class II Furcations in the Mandible Than in the Maxilla: A Retrospective Study.

Absorbable porcine collagen membrane with a bovine bone graft can be considered for regenerative treatment in periodontal class II furcation defects. We evaluated the clinical efficacy of guided tissue regeneration (GTR) treatment with bovine bone xenograft and a porcine collagen membrane in molars with class II furcations. Probing depth (PD), clinical attachment level (CAL), and bone level (BL) were recorded at baseline and at 3, 6, and 9 months postoperatively. Thirty class II furcation defects from the lower and upper molars were assessed. Significant improvements in PD and CAL were observed from baseline to 9 months in all groups (p < 0.01). BL improved in all groups except group A in the upper molars in radiographic assessment (p < 0.05). The lower and upper molars showed PD reduction of 50.5% ± 7.44% and 46.2% ± 11.2%, respectively, at 9 months (p = 0.044). In furcations of 1-3 mm, the lower and upper molars showed PD reductions of 51.2% ± 4.49% and 36.5% ± 16.14%, respectively (p = 0.035). The lower and upper molars showed a CAL gain of 51.1% ± 4.64% and 33.6% ± 18.8%, respectively (p = 0.037). Thus, GTR with bovine bone graft and porcine collagen membrane yielded good results in class II furcations, with better results in the lower than in the upper molars.

Evaluation of the Peri-Implant Bone Level around Platform-Switched Dental Implants: A Retrospective 3-Year Radiographic Study.

OBJECTIVE: To describe remodeling of the mesial and distal marginal bone level around platform-switched (PS) and platform-matched (PM) dental implants that were sandblasted with large grit and etched with acid over a three-year period. MATERIALS AND METHODS: Digital periapical radiographs were obtained at the following time-points: during Stage I of the surgical placement of dental implants, before loading, immediately after loading (baseline), and one, three, six, 12, and 36 months after loading for measuring the horizontal and vertical marginal bone levels. RESULTS: Sixty implants were successfully osseointegrated during the overall observation period. Vertical marginal bone levels for the PS and PM dental implants were 0.78 ± 0.77 and 0.98 ± 0.81 mm, respectively, whereas the horizontal marginal bone levels for the PS and PM implants were 0.84 ± 0.45 and 0.98 ± 0.68 mm, respectively. During the time leading up to the procedure until 36 months after the procedure, the average vertical marginal bone level resulted in less bone loss for the PS and PM groups-0.96 ± 1.28 and 0.30 ± 1.15 mm, respectively (p < 0.05). The mean levels of the horizontal marginal bone also showed increases of 0.48 ± 1.01 mm in the PS and 0.37 ± 0.77 mm in the PM groups from the time before loading until 36 months after the procedure. However, these increases were not statistically significant (p > 0.05). CONCLUSION: PS dental implants appeared to be more effective than PM implants for minimizing the mean marginal vertical and horizontal marginal bone loss during the three-year period. Regardless of which abutment connection was used, the dental implant in the present retrospective investigation exhibited minimal marginal bone remodeling, thus indicating long-term stability.

Dental Implant Surrounding Marginal Bone Level Evaluation: Platform Switching versus Platform Matching-One-Year Retrospective Study.

The benefits and feasibility of platform switching have been discussed in several studies, reporting lesser crestal bone loss in platform-switched implants than in platform-matched implants. Objective. The aim of the present study was to observe the changes in vertical and horizontal marginal bone levels in platform-switched and platform-matched dental implants. Materials and Methods. 51 patients received 60 dental implants in the present study over a 1-year period. Measurement was performed between the implant shoulder and the most apical and horizontal marginal defect by periapical radiographs to examine the changes of peri-implant alveolar bone before and 12 months after prosthodontic restoration delivery. Results. These marginal bone measurements showed a bone gain of 0.23 ± 0.58 mm in the vertical gap and 0.22 ± 0.53 mm in the horizontal gap of platform matching, while in platform switching a bone gain of 0.93 ± 1 mm (P < 0.05) in the vertical gap and 0.50 ± 0.56 mm in the horizontal gap was found. The average vertical gap reduction from the baseline until 12 months was 0.92 ± 1.11 mm in platform switching and 0.29 ± 0.85 mm in platform matching (P < 0.05). Conclusions. Within the limitations of the present study, platform switching seemed to be more effective for a better peri-implant alveolar bone vertical and horizontal gap reduction at 1 year.