Artificial intelligence in the diagnosis of dental diseases on panoramic radiographs: a preliminary study.

BACKGROUND: Artificial intelligence (AI) has been introduced to interpret the panoramic radiographs (PRs). The aim of this study was to develop an AI framework to diagnose multiple dental diseases on PRs, and to initially evaluate its performance. METHODS: The AI framework was developed based on 2 deep convolutional neural networks (CNNs), BDU-Net and nnU-Net. 1996 PRs were used for training. Diagnostic evaluation was performed on a separate evaluation dataset including 282 PRs. Sensitivity, specificity, Youden's index, the area under the curve (AUC), and diagnostic time were calculated. Dentists with 3 different levels of seniority (H: high, M: medium, L: low) diagnosed the same evaluation dataset independently. Mann-Whitney U test and Delong test were conducted for statistical analysis (ɑ=0.05). RESULTS: Sensitivity, specificity, and Youden's index of the framework for diagnosing 5 diseases were 0.964, 0.996, 0.960 (impacted teeth), 0.953, 0.998, 0.951 (full crowns), 0.871, 0.999, 0.870 (residual roots), 0.885, 0.994, 0.879 (missing teeth), and 0.554, 0.990, 0.544 (caries), respectively. AUC of the framework for the diseases were 0.980 (95%CI: 0.976-0.983, impacted teeth), 0.975 (95%CI: 0.972-0.978, full crowns), and 0.935 (95%CI: 0.929-0.940, residual roots), 0.939 (95%CI: 0.934-0.944, missing teeth), and 0.772 (95%CI: 0.764-0.781, caries), respectively. AUC of the AI framework was comparable to that of all dentists in diagnosing residual roots (p > 0.05), and its AUC values were similar to (p > 0.05) or better than (p < 0.05) that of M-level dentists for diagnosing 5 diseases. But AUC of the framework was statistically lower than some of H-level dentists for diagnosing impacted teeth, missing teeth, and caries (p < 0.05). The mean diagnostic time of the framework was significantly shorter than that of all dentists (p < 0.001). CONCLUSIONS: The AI framework based on BDU-Net and nnU-Net demonstrated high specificity on diagnosing impacted teeth, full crowns, missing teeth, residual roots, and caries with high efficiency. The clinical feasibility of AI framework was preliminary verified since its performance was similar to or even better than the dentists with 3-10 years of experience. However, the AI framework for caries diagnosis should be improved.

Computer-designed surgical templates improve the extraction of impacted supernumerary teeth in the hard palate.

OBJECTIVES: The surgical procedure of bony impacted supernumerary teeth (SNT) in hard palate is commonly done with poor visualization and uncomfortable posture. This study aims to introduce our primary practice of presurgical evaluation and guiding exodontia of bony impacted supernumerary teeth (SNT) in the hard palate to reduce surgical trauma, duration and uncertainty. STUDY DESIGN: Twelve patients with impacted supernumerary teeth in hard palate were included. Intraoral scan and the three-dimensional (3D) reconstruction of the cone beam computed tomography (CBCT) file was superimposed, and virtual simulation of flap elevation and osteotomy was conducted on the rebuilt 3D model. A couple of surgical templates were designed with surgical planning software Mimics, fabricated by a 3D printer and were used to guide the extraction of the impacted SNT. RESULTS: The surgical templates fitted well to the teeth and operation site. All the impacted SNTs were accurately located and extracted without damaging the adjacent vital anatomical structures. All patients had an uneventful postoperative recovery without infection or sensory disturbance. CONCLUSIONS: The application of 3D printed surgical templates reduced trauma and increased the accuracy and predictability of surgical extraction of bony impacted SNT in hard palate. The results of this study increased the accuracy and predictability of surgical extraction of bony impacted SNT in hard palate, and reduced the surgeon's embarrassment and surgical trauma because of location difficulty.

Low-Grade Myofibroblastic Sarcoma in the Mandibular Canal: A Case Report.

Low-grade myofibroblastic sarcoma (LGMS) represents an atypical myofibroblastic tumor characterized by a diffusely infiltrating pattern of spindle-shaped tumor cells. It was classified as a distinct soft tissue tumor by the World Health Organization in 2002. LGMS occurs mostly in adult patients and has a predilection for the head and neck region. So far, only a few cases of LGMS located in the mandible have been reported. Aggressive surgical resection with clear margins is the primary treatment for LGMS. Because of its rarity, reports of radiation therapy are limited, and the therapeutic effect is still controversial. We present the case of an 8-year-old girl with LGMS of the mandibular canal to highlight the clinical features and rarity and to improve the understanding of the therapeutic effect of radiotherapy on LGMS.

[A study of repairing mandibular defect using tissue engineering bone with bone marrow stem cells cell sheets in dog].

OBJECTIVE: To reconstruct mandibular defect using tissue engineering bone with bone marrow stem cells (BMSCs) cell sheets and investigate the effect of cell sheets on osteogenesis. METHODS: BMSCs were isolated with the method of density gradient centrifugation from canine and cultured. BMSCs were induced to differentiate to osteoblasts. BMSCs induced were fabricated to BMSCs cell sheets. The poly (lactic-co-glycolic acid) (PLGA) wrapped with cell sheets were implanted into the mandibular defect in the left side (experimental side). PLGA wrapped without cell sheets were implanted into the right side (control side) of mandibles. 16 dogs were evenly divided into 4 groups, and one group of them was executed in 4, 8, 12, 16 weeks for gross investigation and histological observation. RESULTS: The osteogenesis of experimental side was better than that of control side. 16 weeks after implantation, most areas of the mandibular defect were replaced by fresh bone tissue. Compact bone similar to normal bone tissue formed in the lingual defect of mandible and had bony union with the bone stump. The optical density of the fresh bone in the experimental side was higher than that of the control side, there was a significant difference between the two methods (P<0.05). Plenty of lamellar bones formed in experimental side and Haversian system, as well as red marrow, were observed. CONCLUSION: Tissue engineering bone with the structure of lamellar bones can be formed by the technology of BMSCs cell sheets.