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.

In this study, three PCL-based polyurethane acrylates were synthesized and further formulated into twelve resins for digital light processing (DLP) 3D printing. Three PCL diols with different molecular weights were synthesized via ring-opening reaction of ε-caprolactone on diethylene glycol, with the catalyst stannous octoate. Isophorone diisocyanate (IPDI) was reacted with 2-hydroxyethyl acrylate (2-HEA) and the PCL diols form PCL-based polyurethane acrylates. Twelve resins composed of different percentages of PCL-based polyurethane acrylates, poly (ethylene glycol) diacrylate (PEGDA), propylene glycol (PPG) and photo-initiator were further printed from a DLP 3D printer. The viscosities of twelve resins decreased by 10 times and became printable after adding 30% of PEGDA. The degree of conversion for the twelve resins can reach more than 80% after the post-curing process. By changing the amount of PEGDA and PPG, the mechanical properties of the twelve resins could be adjusted. PUA530-PEG-PPG (70:30:0), PUA800-PEG-PPG (70:30:0), and PUA1000-PEG-PPG (70:30:0) were successfully printed into customized tissue scaffolds. Twelve PCL-based polyurethane photo-curable resins with tunable mechanical properties, cytotoxicity, and degradability were successfully prepared. With the DLP 3D printing technique, a complex structure could be achieved. These resins have great potential for customized tissue engineering and other biomedical application.

The aim of this research is to synthesize polycaprolactone-based polyurethanes (PCL-based PUs) that can be further used for the fabrication of guided bone regeneration (GBR) membranes with higher tensile strength and elongation at break than collagen and PTFE membranes. The PCL-based PUs were prepared by the polymerization of polycaprolactone (PCL) diol with 1,6-hexamethylene diisocyanate (HDI) at different ratios using either polyethylene glycol (PEG) or ethylenediamine (EDA) as chain extenders. The chemical, mechanical, and thermal properties of the synthesized polymers were determined using NMR, FTIR, GPC, DSC, and tensile tester. The PCL and polyurethanes were fabricated as nanofiber membranes by electrospinning, and their mechanical properties and SEM morphology were also investigated. In vitro tests, including WST-1 assay, SEM of cells, and phalloidin cytoskeleton staining, were also performed. It was shown that electrospun membranes made of PCL and PCL-HDI-PEG (2 : 3 : 1) possessed tensile strength of 19.84 MPa and 11.72 MPa and elongation at break of 627% and 362%, respectively. These numbers are equivalent or higher than most of the commercially available collagen and PTFE membrane. As a result, these membranes may have potential for future GBR applications.

Gelatin methacryloyl (GelMA) hydrogel is a photopolymerizable biomaterial widely used for three-dimensional (3D) cell culture due to its high biocompatibility. However, the drawback of GelMA hydrogel is its poor mechanical properties, which may compromise the feasibility of biofabrication techniques. In this study, a cell-laden GelMA composite hydrogel with a combination incorporating silanized hydroxyapatite (Si-HAp) and a simple and harmless visible light crosslinking system for this hydrogel were developed. The incorporation of Si-HAp into the GelMA hydrogel enhanced the mechanical properties of the composite hydrogel. Moreover, the composite hydrogel exhibited low cytotoxicity and promoted the osteogenic gene expression of embedded MG63 cells and Human bone marrow mesenchymal stem cells (hBMSCs). We also established a maskless lithographic method to fabricate a defined 3D structure under visible light by using a digital light processing projector, and the incorporation of Si-HAp increased the resolution of photolithographic hydrogels. The GelMA-Si-HAp composite hydrogel system can serve as an effective biomaterial in bone regeneration.