To develop and verify an automatic classification method using artificial intelligence deep learning to determine the bone mineral density level of the implant site in oral implant surgery from radiographic data obtained from cone beam computed tomography (CBCT) images. Seventy patients with mandibular dentition defects were scanned using CBCT. These Digital Imaging and Communications in Medicine data were cut into 605 training sets, and then the data were processed with data standardization, and the Hounsfiled Unit (HU) value level was determined as follows: Type 1, 1000–2000; type 2, 700–1000; type 3, 400–700; type 4, 100–400; and type 5, − 200–100. Four trained dental implant physicians manually identified and classified the area of the jaw bone density level in the image using the software LabelMe. Then, with the assistance of the HU value generated by LabelMe, a physician with 20 years of clinical experience confirmed the labeling level. Finally, the HU mean values of various categories marked by dental implant physicians were compared to the mean values detected by the artificial intelligence model to assess the accuracy of artificial intelligence classification. After the model was trained on 605 training sets, the statistical results of the HU mean values of various categories in the dataset detected by the model were almost the same as the HU grading interval on the data annotation. This new classification provides a more detailed solution to guide surgeons to adjust the drilling rate and tool selection during preoperative decision-making and intraoperative hole preparation for oral implant surgery.
The Qinghai–Tibet Plateau is a proven essential water conservation region in Asia. However, various factors, such as anthropogenic activities, climate, and vegetation significantly affect its water conservation. Along these lines, a deep understanding of the spatiotemporal patterns of water conservation for this plateau and relevant influencing elements is considered of great importance. This paper calculates the water conservation on the Qinghai–Tibet Plateau based on the InVEST model, and given that the evapotranspiration data are an important parameter of the InVEST model, this study selects the mainstream evapotranspiration data to compare the accuracy of the simulated water yield, and also selects the most accurate remote sensing evapotranspiration data examined in the study to carry out the study of water conservation on the Qinghai–Tibet Plateau. Due to the large area of the Qinghai–Tibet Plateau and the various types of climate and ecological zones, this paper analyzes the spatial and temporal variations of water conservation on the Qinghai–Tibet Plateau in each ecological zone and climate zone division and detects the factors affecting water conservation on the Qinghai–Tibet Plateau by using the geo-detector method. From our analysis, the following outcomes are proven: on the Qinghai–Tibet Plateau, (1) the overall water conservation decreased from southeast to northwest; (2) the water conservation of the studied plateau in 1990, 2000, 2010, and 2020 was 656.56, 590.85, 597.4, and 651.85 mm, respectively; (3) precipitation, evapotranspiration, and NDVI exhibited a positive relationship with water conservation; (4) the precipitation factor had the biggest impact on the spatial distinctions of the water resource governance; (5) the above factors are combined with the slope factor and the interaction of each factor to improve water conservation. Our work provides valuable insights for the further implementation of ecological projects with a view to enhancing water resource management methods.
Objective To develop and verify an automatic classification method using artificial intelligence deep learning to determine the bone mineral density level of the implant site in oral implant surgery from radiographic data obtained from cone beam computed tomography (CBCT) images.Materials and Methods Seventy patients with mandibular dentition defects were scanned using CBCT. These Digital Imaging and Communications in Medicine (DICOM) data were cut into 605 training sets, and then the data were processed with data standardization, and the Hounsfiled Unit (HU) value level was determined as follows: Type 1, 1000–2000; type 2, 700–1000; type 3, 400–700; type 4, 100–400; and type 5, −200–100. Four trained dental implant physicians manually identified and classified the area of the jaw bone density level in the image using the software LabelMe. Then, with the assistance of the HU value generated by LabelMe, a physician with 20 years of clinical experience confirmed the labeling level. Finally, the HU mean values of various categories marked by dental implant physicians were compared to the mean values detected by the artificial intelligence model to assess the accuracy of artificial intelligence classification.Results After the model was trained on 605 training sets, the statistical results of the HU mean values of various categories in the dataset detected by the model were almost the same as the HU grading interval on the data annotation.Conclusion This new classification provides a more detailed solution to guide surgeons to adjust the drilling rate and tool selection during preoperative decision-making and intraoperative hole preparation for oral implant surgery.
Objective: To investigate the correlation between peri-implant BMD and initial stability of implants when combined with the new artificial intelligence classification method of jaw density. Materials and Methods: 49 patients who received dental implant treatment in the Affiliated Hospital of Stomatological of Fujian Medical University were included. The torque value and implant stability quotient (ISQ) value of the implants after implantation were recorded. Artificial intelligence image segmentation software was used to obtain the distribution of jaw density in implant areas, and the neck, the middle, the bottom and the total bone mineral density (BMD) coefficients of the 1mm region around the implant were calculated by model overlap and image overlap techniques. Then, the correlation betwen ISQ and BMD evaluated by a new jaw density artificial intelligence classification method were investigated. Results: There was a significant positive correlation between the BMD coefficient of the total, the neck and the middle region around implants and the ISQ value (P < 0.05), but there was no significant correlation between the BMD coefficient of the bottom around implants and the ISQ value (P > 0.05). BMD was significantly higher at the implant site with larger implant torque (P < 0.05). Conclusions:The results of this study suggest that there is a positive correlation between BMD coefficient and the ISQ. BMD of both the neck and the middle of the implant have a significant positive correlation with the ISQ, while BMD of the bottom of the implant has no significant correlation with ISQ.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.