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. 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. 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. 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.
Manufacturing three-dimensional (3D) objects with polymers/bioceramic composite materials has been investigated in recent years. In this study, we manufactured and evaluated solvent-free polycaprolactone (PCL) and beta-tricalcium phosphate (β-TCP) composite fiber as a scaffold material for 3D printing. To investigate the optimal ratio of feedstock material for 3D printing, the physical and biological characteristics of four different ratios of β-TCP compounds mixed with PCL were investigated. PCL/β-TCP ratios of 0 wt.%, 10 wt.%, 20 wt.%, and 30 wt.% were fabricated, with PCL melted at 65 °C and blended with β-TCP with no solvent added during the fabrication process. Electron microscopy revealed an even distribution of β-TCP in the PCL fibers, while Fourier transform infrared spectroscopy demonstrated that the biomaterial compounds remained intact after the heating and manufacturing process. In addition, adding 20% β-TCP into the PCL/β-TCP mixture significantly increased hardness and Young’s Modulus by 10% and 26.5%, respectively, suggesting that PCL-20 has better resistance to deformation under load. Cell viability, alkaline phosphatase (ALPase) activity, osteogenic gene expression, and mineralization were also observed to increase according to the amount of β-TCP added. Cell viability and ALPase activity were 20% higher with PCL-30, while upregulation for osteoblast-related gene expression was better with PCL-20. In conclusion, PCL-20 and PCL-30 fibers fabricated without solvent exhibited excellent mechanical properties, high biocompatibility, and high osteogenic ability, making them promising materials for 3D printing customized bone scaffolds promptly, sustainably, and cost-effectively.
Background: In mixed dentition analysis, estimation of the mesiodistal width of unerupted permanent canines and premolars is essential for successful diagnosis and treatment planning. The present study aimed to develop a simple linear equation to predict permanent tooth sizes from mixed dentition analysis for Taiwanese people. Methods: The sample comprised 200 dental casts, derived from Taiwanese patients (100 males and 100 females; age, 12–35 years). Mesial distal tooth widths were measured in dental casts with a digital caliper. A student’s t-test was conducted to detect tooth size correlations with gender-specific differences, as well as intra-arch counterparts. Standard linear regression was conducted to develop a simple equation representing predictions of canine-premolar relationships. Results: All teeth were not significantly different between the left and right sides, regardless of gender and upper or lower arches. In terms of types of teeth, males had larger tooth dimensions in both arches than females. New regression equations for estimating the dimensions of the unerupted canines and premolars in the Taiwanese population were developed. Conclusions: Using a sample of Taiwanese people, new models derived for females and males separately were developed, which should provide highly accurate predictions for unerupted canines and premolars in the Taiwanese population.
Background: Tricalcium phosphate (TCP, Molecular formula: Ca3(PO4)2) is a hydrophilic bone graft biomaterial extensively used for guided bone regeneration (GBR). However, few studies have investigated 3D-printed polylactic acid (PLA) combined with the osteo-inductive molecule fibronectin (FN) for enhanced osteoblast performance in vitro, and specialized bone defect treatments. Aim: This study evaluated PLA properties and efficacy following glow discharge plasma (GDP) treatment and FN sputtering for fused deposition modeling (FDM) 3D printed PLA alloplastic bone grafts. Methods: 3D trabecular bone scaffolds (8 × 1 mm) were printed by the 3D printer (XYZ printing, Inc. 3D printer da Vinci Jr. 1.0 3-in-1). After printing PLA scaffolds, additional groups for FN grafting were continually prepared with GDP treatment. Material characterization and biocompatibility evaluations were investigated at 1, 3 and 5 days. Results: SEM images showed the human bone mimicking patterns, and EDS illustrated the increased C and O after fibronectin grafting, XPS and FTIR results together confirmed the presence of FN within PLA material. Degradation increased after 150 days due to FN presence. 3D immunofluorescence at 24 h demonstrated better cell spreading, and MTT assay results showed the highest proliferation with PLA and FN (p < 0.001). Cells cultured on the materials exhibited similar alkaline phosphatase (ALP) production. Relative quantitative polymerase chain reaction (qPCR) at 1 and 5 days revealed a mixed osteoblast gene expression pattern. Conclusion: In vitro observations over a period of five days, it was clear that PLA/FN 3D-printed alloplastic bone graft was more favorable for osteogenesis than PLA alone, thereby demonstrating great potential for applications in customized bone regeneration.