Purpose: The present study aimed to develop 2 deep learning (DL) systems incorporating detection functions for the diagnosis of carotid artery calcifications (CACs) on panoramic radiographs and to compare their diagnostic performances using CAC-based, side-based, and patient-based evaluations. Materials and Methods: Panoramic radiographs from 290 patients with CACs and 290 control patients without CACs were used to develop 2 detection models: one designed to detect individual CACs across the entire radiograph (System 1) and another designed to detect CACs within the limited bilateral cervical areas (System 2). CAC-based performance was evaluated using recall, precision, and F1-score. Side-based and patient-based performances were assessed usingsensitivity, specificity, positive predictive value, negative predictive value, accuracy, and the area under the receiveroperating characteristic curve (AUC). Results: For System 1, CAC-based recall, precision, and F1-score were 0.81, 0.68, and 0.74, respectively. For System 2,the corresponding values were 0.90, 0.67, and 0.77. Side-based sensitivity, specificity, and AUC were 0.87, 0.80, and 0.83 for System 1, and 0.93, 0.84, and 0.89 for System 2. Patient-based sensitivity, specificity, and AUC were 0.93, 0.73,and 0.83 for System 1, and 0.95, 0.70, and 0.83 for System 2. Although a relatively large number of false positives were observed in CAC-based assessments, side-based and patient-based performances showed improvement. Conclusion Side-based and patient-based performances were sufficient when calculated on the basis of CAC-basedevaluations for diagnosing CACs on panoramic radiographs. When conducting studies of this type, performance assessments should include side-based and patient-based evaluations in addition to CAC-based analyses.

Purpose: The purpose of this study was to clarify the panoramic image differences of cleft alveolus patients with or without a cleft palate, with emphases on the visibility of the line formed by the junction between the nasal septum and nasal floor (the upper line) and the appearances of the maxillary lateral incisor. Materials and Methods: Panoramic radiographs of 238 patients with cleft alveolus were analyzed for the visibility of the upper line, including clear, obscure or invisible, and the appearances of the maxillary lateral incisor, regarding congenital absence, incomplete growth, delayed eruption and medial inclination. Differences in the distribution ratio of these visibility and appearances were verified between the patients with and without a cleft palate using the chi-square test. Results: There was a significant difference in the visibility distribution of the upper line between the patients with and without a cleft palate (p<0.05). In most of the patients with a cleft palate, the upper line was not observed. In the unilateral cleft alveolus patients, the medial inclination of the maxillary lateral incisor was more frequently observed in patients with a cleft palate than in patients without a cleft palate. Conclusion Two differences were identified in panoramic appearances. The first was the disappearance (invisible appearance) of the upper line in patients with a cleft palate, and the second was a change in the medial inclination on the affected side maxillary lateral incisor in unilateral cleft alveolus patients with a cleft palate.

Purpose: The aims of this study were to create a deep learning model to distinguish between nasopalatine duct cysts (NDCs), radicular cysts, and no-lesions (normal) in the midline region of the anterior maxilla on panoramic radiographs and to compare its performance with that of dental residents. Materials and Methods: One hundred patients with a confirmed diagnosis of NDC (53 men, 47 women; average age, 44.6±16.5 years), 100 with radicular cysts (49 men, 51 women; average age, 47.5±16.4 years), and 100 with normal groups (56 men, 44 women; average age, 34.4±14.6 years) were enrolled in this study. Cases were randomly assigned to the training datasets (80%) and the test dataset (20%). Then, 20% of the training data were randomly assigned as validation data. A learning model was created using a customized DetectNet built in Digits version 5.0 (NVIDIA, Santa Clara, USA). The performance of the deep learning system was assessed and compared with that of two dental residents. Results: The performance of the deep learning system was superior to that of the dental residents except for the recall of radicular cysts. The areas under the curve (AUCs) for NDCs and radicular cysts in the deep learning system were significantly higher than those of the dental residents. The results for the dental residents revealed a significant difference in AUC between NDCs and normal groups. Conclusion This study showed superior performance in detecting NDCs and radicular cysts and in distinguishing between these lesions and normal groups.