Arteriovenous malformations (AVMs) are rare congenital anomalies characterized by direct communication between arteries and veins that bypass the capillary bed. AVMs may not manifest clinically until late infancy or childhood. In particular, facial AVMs can cause urgent life-threatening dental events. A 5-year-old girl without a medical history visited the hospital because of spontaneous gingival bleeding around the posterior gingival area of the lower left 2nd primary molar.
Angiography through the femoral approach under general anesthesia was performed for differential diagnosis and therapeutic option. The blood flow was effectively reduced after arterial embolization alone, and there was no evidence of recurrence at the 5-month follow-up.
The present study reports that embolization of the affected vessels can be a more effective and safe method than surgical resection for the treatment of AVM during the growth period.

Adenoid cystic carcinoma is a relatively rare tumor that usually arises in the parotid and submandibular salivary glands. The initial management is surgical, and this is often combined with post-operative radiotherapy, but local relapse is common and distant metastasis is not infrequent. We experienced the case of a 59 years old male who had been previously operated on for a primary submandibular salivary cyst, and he then had a distant pulmonary metastasis 9 years later. We operated on him with performing a wedge resection on the left lower lobe for the metastatic lesion, and he hasn't had any evidence of tumor recurrence for 84 months after the second operation.
Adenoids ; Carcinoma, Adenoid Cystic ; Humans ; Male ; Neoplasm Metastasis ; Recurrence ; Salivary Glands

Objective: The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals. Methods: Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradientweighted class activation mapping (Grad-CAM). Results: In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis. Conclusions Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.