Determining the peri-implant marginal bone level on radiographs is challenging because the boundaries of the bones around implants are often unclear or the heights of the buccal and lingual bone levels are different. Therefore, a deep convolutional neural network (CNN) was evaluated for detecting the marginal bone level, top, and apex of implants on dental periapical radiographs. An automated assistant system was proposed for calculating the bone loss percentage and classifying the bone resorption severity. A modified region-based CNN (R-CNN) was trained using transfer learning based on Microsoft Common Objects in Context dataset. Overall, 708 periapical radiographic images were divided into training (n = 508), validation (n = 100), and test (n = 100) datasets. The training dataset was randomly enriched by data augmentation. For evaluation, average precision, average recall, and mean object keypoint similarity (OKS) were calculated, and the mean OKS values of the model and a dental clinician were compared. Using detected keypoints, radiographic bone loss was measured and classified. No statistically significant difference was found between the modified R-CNN model and dental clinician for detecting landmarks around dental implants. The modified R-CNN model can be utilized to measure the radiographic peri-implant bone loss ratio to assess the severity of peri-implantitis.

Myagmar G, et al. J Adv Prosthodont. 2021 Jun;13(3):144-151. https://doi.org/10.4047/jap.2021.13.3.144

Research on whether the number or location of missing teeth affects the accuracy of intraoral scanners in partial edentulous patients is scarce. This study aimed to evaluate the precision of complete-arch scan data of various partial edentulous arches acquired by intraoral scanners. Five different maxillary models were scanned using Carestream CS3600 and Medit i500 scanners. The models employed here were control: Fully dentate; Case 1: Missing a right second premolar and a first molar; Case 2: Missing a right second premolar, a first molar, both left premolars, and a left first molar; Case 3: Missing four incisors and a right canine; and Case 4: Missing four incisors, a left second premolar, and a first molar. Six scans per group were performed and the resulting two datasets were paired to analyze the precision of each group (n = 15). Two-way ANOVA was performed (α = 0.05). The root mean square (RMS) error values in Cases 2, 3, and 4 were significantly higher than those in Case 1 and control. The RMS values of the two intraoral scanners were not significantly different. Scanning precision was significantly lower for both devices when used for scanning dental arches with ≥5 missing teeth.