Maxillofacial bone defects caused by congenital malformations, trauma, tumors, and inflammation can severely affect functions and aesthetics of maxillofacial region. Despite certain successful clinical applications of biomaterial scaffolds, ideal bone regeneration remains a challenge in maxillofacial region due to its irregular shape, complex structure, and unique biological functions. Scaffolds that address multiple needs of maxillofacial bone regeneration are under development to optimize bone regeneration capacity, costs, operational convenience. etc. In this review, we first highlight the special considerations of bone regeneration in maxillofacial region and provide an overview of the biomaterial scaffolds for maxillofacial bone regeneration under clinical examination and their efficacy, which provide basis and directions for future scaffold design. Latest advances of these scaffolds are then discussed, as well as future perspectives and challenges. Deepening our understanding of these scaffolds will help foster better innovations to improve the outcome of maxillofacial bone tissue engineering.

This study aimed to establish and validate machine learning models for prognosis prediction in endodontic microsurgery, avoiding treatment failure and supporting clinical decision-making. A total of 234 teeth from 178 patients were included in this study. We developed gradient boosting machine (GBM) and random forest (RF) models. For each model, 80% of the data were randomly selected for the training set and the remaining 20% were used as the test set. A stratified 5-fold cross-validation approach was used in model training and testing. Correlation analysis and importance ranking were conducted for feature selection. The predictive accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and the area under the curve (AUC) of receiver operating characteristic (ROC) curves were calculated to evaluate the predictive performance. There were eight important predictors, including tooth type, lesion size, type of bone defect, root filling density, root filling length, apical extension of post, age, and sex. For the GBM model, the predictive accuracy was 0.80, with a sensitivity of 0.92, specificity of 0.71, PPV of 0.71, NPV of 0.92, F1 of 0.80, and AUC of 0.88. For the RF model, the accuracy was 0.80, with a sensitivity of 0.85, specificity of 0.76, PPV of 0.73, NPV of 0.87, F1 of 0.79, and AUC of 0.83. The trained models were developed by eight common variables, showing the potential ability to predict the prognosis of endodontic microsurgery. The GBM model outperformed the RF model slightly on our dataset. Clinicians can use machine learning models for preoperative analysis in endodontic microsurgery. The models are expected to improve the efficiency of clinical decision-making and assist in clinician-patient communication.

The study aimed to develop and validate machine learning models for case difficulty prediction in endodontic microsurgery, assisting clinicians in preoperative analysis. The cone-beam computed tomographic images were collected from 261 patients with 341 teeth and used for radiographic examination and measurement. Through linear regression (LR), support vector regression (SVR), and extreme gradient boosting (XGBoost) algorithms, four models were established according to different loss functions, including the L1-loss LR model, L2-loss LR model, SVR model and XGBoost model. Five-fold cross-validation was applied in model training and validation. Explained variance score (EVS), coefficient of determination (R²), mean absolute error (MAE), mean squared error (MSE) and median absolute error (MedAE) were calculated to evaluate the prediction performance. The MAE, MSE and MedAE values ​​of the XGBoost model were the lowest, which were 0.1010, 0.0391 and 0.0235, respectively. The EVS and R² values ​​of the XGBoost model were the highest, which were 0.7885 and 0.7967, respectively. The factors used to predict the case difficulty in endodontic microsurgery were ordered according to their relative importance, including lesion size, the distance between apex and adjacent important anatomical structures, root filling density, root apex diameter, root resorption, tooth type, tooth length, root filling length, root canal curvature and the number of root canals. The XGBoost model outperformed the LR and SVR models on all evaluation metrics, which can assist clinicians in preoperative analysis. The relative feature importance provides a reference to develop the scoring system for case difficulty assessment in endodontic microsurgery. Preoperative case assessment is a crucial step to identify potential risks and make referral decisions. Machine learning models for case difficulty prediction in endodontic microsurgery can assist clinicians in preoperative analysis efficiently and accurately.

Oral squamous cell carcinoma is one of the most malignant tumors with high mortality rate worldwide. Biomarker discovery is critical for early diagnosis and precision treatment of this disease. MicroRNAs are small noncoding RNA molecules which often regulate essential biological processes and are good candidates for biomarkers. By integrative analysis of both the cancer-associated gene expression data and microRNA-mRNA network, miR-148b-3p, miR-629-3p, miR-27a-3p, and miR-142-3p were screened as novel diagnostic biomarkers for oral squamous cell carcinoma based on their unique regulatory abilities in the network structure of the conditional microRNA-mRNA network and their important functions. These findings were confirmed by literature verification and functional enrichment analysis. Future experimental validation is expected for the further investigation of their molecular mechanisms.

The use of computer-aided rapid prototyping (CARP) models was considered to reduce surgical trauma and improve outcomes when autotransplantation of teeth (ATT) became a viable alternative for dental rehabilitation. However, ATT is considered technique-sensitive due to its series of complicated surgical procedures and unfavorable outcomes in complex cases. This study reported a novel autotransplantation technique of a 28-year-old patient with an unrestorable lower first molar (#36) with double roots. Regardless of a large shape deviation, a lower third molar (#38) with a completely single root formation was used as the donor tooth. ATT was performed with a combined use of virtual simulation, CARP model-based rehearsed surgery, and tooth replica-guided surgery. A 3D virtual model of the donor and recipient site was generated from cone-beam computed tomographic (CBCT) radiographs prior to surgery for direct virtual superimposition simulation and CARP model fabrication. The virtual simulation indicated that it was necessary to retain cervical alveolar bone during the surgical socket preparation, and an intensive surgical rehearsal was performed on the CARP models. The donor tooth replica was used during the procedure to guide precise socket preparation and avoid periodontal ligament injury. Without an additional fitting trial and extra-alveolar storage, the donor tooth settled naturally into the recipient socket within 30 s. The transplanted tooth showed excellent stability and received routine root canal treatment three weeks post-surgery, and the one-year follow-up examination verified the PDL healing outcome and normal functioning. Patient was satisfied with the transplanted tooth. This cutting-edge technology combines virtual simulation, digital surgery planning, and guided surgery implementation to ensure predictable and minimally invasive therapy in complex cases.

[This corrects the article DOI: 10.1155/2017/9803018.].