In the last few years, artificial intelligence (AI) research has been rapidly developing and emerging in the field of dental and maxillofacial radiology. Dental radiography, which is commonly used in daily practices, provides an incredibly rich resource for AI development and attracted many researchers to develop its application for various purposes. This study reviewed the applicability of AI for dental radiography from the current studies. Online searches on PubMed and IEEE Xplore databases, up to December 2020, and subsequent manual searches were performed. Then, we categorized the application of AI according to similarity of the following purposes: diagnosis of dental caries, periapical pathologies, and periodontal bone loss; cyst and tumor classification; cephalometric analysis; screening of osteoporosis; tooth recognition and forensic odontology; dental implant system recognition; and image quality enhancement. Current development of AI methodology in each aforementioned application were subsequently discussed. Although most of the reviewed studies demonstrated a great potential of AI application for dental radiography, further development is still needed before implementation in clinical routine due to several challenges and limitations, such as lack of datasets size justification and unstandardized reporting format. Considering the current limitations and challenges, future AI research in dental radiography should follow standardized reporting formats in order to align the research designs and enhance the impact of AI development globally.

Background: The impact of the jaw bone condition, such as bone quantity and quality in the implant placement site, affecting the accuracy of implant placement with computer-guided surgery (CGS) remains unclear. Therefore, this study aimed to evaluate the influence of bone condition, i.e., bone density, bone width, and cortical bone thickness at the crestal bone on the accuracy of implant placement with CGS.Methods: A total of 47 tissue-level implants from 25 patients placed in the posterior mandibular area were studied. Implant placement position was planned on the simulation software, Simplant® Pro 16, by superimposing preoperative computed tomography images with stereolithography data of diagnostic wax-up on the dental cast. Implant placement surgery was performed using the surgical guide plate to reflect the planned implant position. The post-surgical dental cast was scanned to determine the position of the placed implant. Linear and vertical deviations between planned and placed implants were calculated. Deviations at both platform and apical of the implant were measured in the bucco-lingual and mesio-distal directions. Intra- and inter-observer variabilities were calculated to ensure measurement reliability. Multiple linear regression analysis was employed to investigate the effect of the bone condition, such as density, width, and cortical bone thickness at the implant site area, on the accuracy of implant placement (α= 0.05).Result: Intra- and inter-observer variabilities of these measurements showed excellent agreement (intra class correlation coefficient ± 0.90). Bone condition significantly influenced the accuracy of implant placement using CGS (p < 0.05). Both bone density and width were found to be significant predictors.Conclusions: Low bone density and/or narrow bucco-lingual width near the alveolar bone crest in the implant placement site might be a risk factor influencing the accuracy of implant placement with CGS.

Whilst the newly established biomechanical conditions following mandibular reconstruction using fibula free flap can be a critical determinant for achieving favorable bone union, little has been known about their association in a time-dependent fashion. This study evaluated the bone healing/remodeling activity in reconstructed mandible and its influence on jaw biomechanics using CT data, and further quantified their correlation with mechanobiological responses through an in-silico approach. A 66-year-old male patient received mandibular reconstruction was studied. Post-operative CT scans were taken at 0, 4, 16 and 28 months. Longitudinal change of bone morphologies and mineral densities were measured at three bone union interfaces (two between the fibula and mandibular bones and one between the osteotomized fibulas) to investigate bone healing/remodeling events. Three-dimensional finite element models were created to quantify mechanobiological responses in the bone at these different time points. Bone mineral density increased rapidly along the bone interfaces over the first four months. Cortical bridging formed at the osteotomized interface earlier than the other two interfaces with larger shape discrepancy between fibula and mandibular bones. Bone morphology significantly affected mechanobiological responses in the osteotomized region (R² > 0.77). The anatomic position and shape discrepancy at bone union affected the bone healing/remodeling process.

The aim of this study was to evaluate the effect of implant location on load distribution in the abutment tooth, implant and residual ridge with a distal-extension implant-supported removable partial denture (ISRPD). A mandibular unilateral distal-extension edentulous simulation model was used. Implants were inserted at the second premolar (mesial implant) and second molar (distal implant) positions in the edentulous area. An experimental ISRPD was fabricated of acrylic resin with a cobalt-chromium alloy framework. Loads on the implants and abutment tooth were measured with piezoelectric force transducers. The load on the residual ridge was measured with pressure-sensitive film. A vertical load of 100N was applied at the first molar region. Measurements were made under the following three conditions: with conventional removable partial denture (CRPD), with mesial-implant-supported removable partial denture (MISRPD), and with distal-implant-supported removable partial denture (DISRPD). In each condition, the unused implants were made inactive by eliminating contact with the inner surface of the denture. The load on the abutment tooth was greatest with DISRPD, followed by CRPD and MISRPD (P<0.01). The load on the implant was greater with DISRPD than with MISRPD (P<0.01). The load on the residual ridge was lowest with DISRPD, followed by MISRPD and CRPD (P<0.01). This experimental study provided quantitative data regarding the effect of implant location on load distribution with ISRPDs. Further investigation regarding the effect of denture design on the load distribution is needed for determining the proper implant location of ISRPD.

This study combines clinical investigation with finite element (FE) analysis to explore the effects of buccal bone thickness (BBT) on the morphological changes of buccal bone induced by the loaded implant. One specific patient who had undergone an implant treatment in the anterior maxilla and experienced the buccal bone resorption on the implant was studied. Morphological changes of the bone were measured through a series of cone-beam computed tomography (CT) scans. A three-dimensional heterogeneous nonlinear FE model was constructed based on the CT images of this patient, and the in-vivo BBT changes are correlated to the FE in-silico mechanobiological stimuli; namely, von Mises equivalent stress, equivalent strain, and strain energy density. The anterior incisory bone region of this model was then varied systematically to simulate five different BBTs (0.5, 1.0, 1.5, 2.0, and 2.5mm), and the optimal BBT was inversely determined to minimize the risk of resorption. Significant changes in BBTs were observed clinically after 6 month loading on the implant. The pattern of bone resorption fell into a strong correlation with the distribution of mechanobiological stimuli onsite. The initial BBT appeared to play a critical role in distributing mechanobiological stimuli, thereby determining subsequent variation in BBT. A minimum initial thickness of 1.5mm might be suggested to reduce bone resorption. This study revealed that the initial BBT can significantly affect mechanobiological responses, which consequentially determines the bone remodeling process. A sufficient initial BBT is considered essential to assure a long-term stability of implant treatment.