Patients with odontogenic cysts and tumors may have to undergo serious surgery unless the lesion is properly detected at the early stage. The purpose of this study is to evaluate the diagnostic performance of the real-time object detecting deep convolutional neural network You Only Look Once (YOLO) v2—a deep learning algorithm that can both detect and classify an object at the same time—on panoramic radiographs. In this study, 1602 lesions on panoramic radiographs taken from 2010 to 2019 at Yonsei University Dental Hospital were selected as a database. Images were classified and labeled into four categories: dentigerous cysts, odontogenic keratocyst, ameloblastoma, and no lesion. Comparative analysis among three groups (YOLO, oral and maxillofacial surgeons, and general practitioners) was done in terms of precision, recall, accuracy, and F1 score. While YOLO ranked highest among the three groups (precision = 0.707, recall = 0.680), the performance differences between the machine and clinicians were statistically insignificant. The results of this study indicate the usefulness of auto-detecting convolutional networks in certain pathology detection and thus morbidity prevention in the field of oral and maxillofacial surgery.

Studies on allogeneic demineralized dentin matrix (Allo-DDM) implantation in the 1960s and 1970s provided the most reliable preclinical evidence of bone formation and antigenicity in an extraosseous site. Recently, applications of Allo-DDM at skeletal sites were studied, and have provided reliable evidence of bone-forming capacity and negligible antigenicity. However, the osteoinductivity and antigenicity properties of Allo-DDM in extraskeletal sites have not yet been investigated due to the lack of follow-up studies after the initial research. The clinical applications of autogenous DDM (Auto-DDM) have been standardized in some countries. Long-term clinical studies have reported the development of several shapes of Auto-DDM, such as powders, blocks, moldable forms, and composites, with recombinant human bone morphogenetic protein-2. For the development of Allo-DDM as a reliable bone graft substitute next to Auto-DDM, we reviewed preclinical studies on the bone induction capacity of allogeneic dentin at extraskeletal as well as skeletal sites. Electronic databases were screened for this review in January 2020 and searched from 1960 to 2019. This review aims to provide a foundation on the preclinical studies of Allo-DDM, which could enable future researches on its osteogenic capability and antigenicity. In conclusion, Allo-DDM showed great potential for osteoinductivity in extraskeletal sites with low antigenicity, which neither adversely affected osteogenic capability nor provoked immunologic reactions. However, the risk of viral disease transmission should be researched before the clinical application of Allo-DDM.

This study aimed to propose a fully automatic posteroanterior (PA) cephalometric landmark identification model using deep learning algorithms and compare its accuracy and reliability with those of expert human examiners. In total, 1032 PA cephalometric images were used for model training and validation. Two human expert examiners independently and manually identified 19 landmarks on 82 test set images. Similarly, the constructed artificial intelligence (AI) algorithm automatically identified the landmarks on the images. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the performance of the model. The performance of the model was comparable with that of the examiners. The MRE of the model was 1.87 ± 1.53 mm, and the SDR was 34.7%, 67.5%, and 91.5% within error ranges of < 1.0, < 2.0, and < 4.0 mm, respectively. The sphenoid points and mastoid processes had the lowest MRE and highest SDR in auto-identification; the condyle points had the highest MRE and lowest SDR. Comparable with human examiners, the fully automatic PA cephalometric landmark identification model showed promising accuracy and reliability and can help clinicians perform cephalometric analysis more efficiently while saving time and effort. Future advancements in AI could further improve the model accuracy and efficiency.