It is necessary to accurately identify dental implant brands and the stage of treatment to ensure efficient care. Thus, the purpose of this study was to use multi-task deep learning to investigate a classifier that categorizes implant brands and treatment stages from dental panoramic radiographic images. For objective labeling, 9767 dental implant images of 12 implant brands and treatment stages were obtained from the digital panoramic radiographs of patients who underwent procedures at Kagawa Prefectural Central Hospital, Japan, between 2005 and 2020. Five deep convolutional neural network (CNN) models (ResNet18, 34, 50, 101 and 152) were evaluated. The accuracy, precision, recall, specificity, F1 score, and area under the curve score were calculated for each CNN. We also compared the multi-task and single-task accuracies of brand classification and implant treatment stage classification. Our analysis revealed that the larger the number of parameters and the deeper the network, the better the performance for both classifications. Multi-tasking significantly improved brand classification on all performance indicators, except recall, and significantly improved all metrics in treatment phase classification. Using CNNs conferred high validity in the classification of dental implant brands and treatment stages. Furthermore, multi-task learning facilitated analysis accuracy.

Pell and Gregory, and Winter’s classifications are frequently implemented to classify the mandibular third molars and are crucial for safe tooth extraction. This study aimed to evaluate the classification accuracy of convolutional neural network (CNN) deep learning models using cropped panoramic radiographs based on these classifications. We compared the diagnostic accuracy of single-task and multi-task learning after labeling 1330 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014–2021). The mandibular third molar classifications were analyzed using a VGG 16 model of a CNN. We statistically evaluated performance metrics [accuracy, precision, recall, F1 score, and area under the curve (AUC)] for each prediction. We found that single-task learning was superior to multi-task learning (all p < 0.05) for all metrics, with large effect sizes and low p-values. Recall and F1 scores for position classification showed medium effect sizes in single and multi-task learning. To our knowledge, this is the first deep learning study to examine single-task and multi-task learning for the classification of mandibular third molars. Our results demonstrated the efficacy of implementing Pell and Gregory, and Winter’s classifications for specific respective tasks.

For osteochondral allograft transplantation to be successful, chondrocytes must survive preservation and retain their capacity to produce normal matrix components: proteoglycans and Type II collagen. Clinical success with osteochondral allograft transplantation has created an increased demand for supplies of suitable cartilage-bearing grafts. This demand has stimulated attempts to find successful methods for low temperature storage of cartilage for "banking" and heightened interest in cartilage cryobiology. In order to achieve the maximum viability of cryopreserved articular cartilage, previous comprehensive studies have focused on rates and temperatures of freezing, cryoprotective agents, and methods and influences of thawing. This study presents evidence that cryopreserved articular chondrocytes maintain their ability to grow in tissue culture following thawing and to produce normal matrix components. Chondrocytes isolated from Japanese white rabbits were divided into groups of fresh controls and experimental cryopreserved cells. Cells were incubated in dimethylsulfoxide, frozen at a rate of -1 degrees C/min, stored at -79 degrees C, rapidly thawed, and plated for culture. Growth rates were comparable in all groups. In all groups, typical chondroid characteristics were maintained throughout 14 days of culture. Typical cartilage phenotypic characteristics included maintenance of polygonal and rhomboidal cells, cell aggregation, proteoglycan production, and Type II collagen synthesis. This investigation strongly indicates that articular chondrocyte cryopreservation yields viable, functional cells and although these results cannot be directly extrapolated to intact adult articular cartilage, they do give further support for low temperature banking of cartilage-bearing allografts for transplantation.

This study aimed to investigate the success factors of the bone lid surgery technique in the maxillofacial region. A retrospective cohort study was performed on 30 maxillofacial patients who underwent bone lid surgery between January 2014 and December 2019 at our hospital. The predictor variables consisted of clinical factors that were classified as attribute (age and sex), health status (smoking and alcohol intake), anatomical (maxillary/mandibular site, left/right side, and cortical bone thickness), lesion (lesion size, location, and pathological diagnosis), and treatment variables (differences in absorbable osteosynthesis materials). The outcome variable was the incidence of bone lid necrosis after surgery. Various risk factors for postoperative bone lid necrosis were investigated statistically. A value <0.05 was considered statistically significant. Postoperative bone lid necrosis was observed in three patients (10.0%). No significant differences in the attribute, anatomical, and treatment status variables were noted. Significant differences were observed between smoking (p=0.005) and alcohol intake (p=0.003) in the health status variables. There was a significant difference in the distance of the lesion from the alveolar bone crest in the lesion variables (p=0.037). Smoking and alcohol consumption were the health status variables found to be risk factors for bone lid necrosis. In addition, proximity to the alveolar crest was also a risk factor for lesion development.

No abstract