Objective: The first aim of this study was to determine the performance of a deep learning object detection technique in the detection of maxillary sinuses on panoramic radiographs. The second aim was to clarify the performance in the classification of maxillary sinus lesions compared with healthy maxillary sinuses. Methods: The imaging data for healthy maxillary sinuses (587 sinuses, Class 0), inflamed maxillary sinuses (416 sinuses, Class 1), cysts of maxillary sinus regions (171 sinuses, Class 2) were assigned to training, testing 1, and testing two datasets.Alearning process of 1000 epochs with the training images and labelswas performed using DetectNet, and a learning model was created. The testing 1 and testing two images were applied to the model, and the detection sensitivities and the false-positive rates per image were calculated. The accuracies, sensitivities and specificities were determined for distinguishing the inflammation group (Class 1) and cyst group (Class 2) with respect to the healthy group (Class 0). Results: Detection sensitivities of healthy (Class 0) and inflamed (Class 1) maxillary sinuses were 100% for both testing 1 and testing two datasets, whereas they were 98 and 89% for cysts of the maxillary sinus regions (Class 2). False-positive rates per image were nearly 0.00. Accuracies, sensitivities and specificities for diagnosis maxillary sinusitis were 90–91%, 88–85%, and 91–96%, respectively; for cysts of the maxillary sinus regions, these values were 97–100%, 80–100%, and 100–100%, respectively. Conclusion: Deep learning could reliably detect the maxillary sinuses and identify maxillary sinusitis and cysts of the maxillary sinus regions. Advances in knowledge: This study using a deep leaning object detection technique indicated that the detection sensitivities of maxillary sinuses were high and the performance of maxillary sinus lesion identification was ≧80%.In particular, performance of sinusitis identification was ≧90%.

Microfocus X-ray computed tomography (micro-CT) has been applied as a method for the nondestructive and detailed assessment of trabecular bone patterns and tooth structure. Voxel values obtained from micro-CT are not absolute values. Therefore, voxel values were assessed using hydroxyapatite (HA) blocks with a different vesicle rate to quantify voxel values of micro-CT images in the present investigation.HA blocks with 4 levels of porosity and a block with a soft tissue-equivalent density were used, and the voxel values of each block were measured. Correlations between voxel values of micro-CT and HA densities were analyzed. Also, black and white binary images were produced, and the ratios of white pixels to pixels in regions of interest (ROIs) were calculated. The relationship between voxel values of micro-CT and HA densities could be regressed using a linear equation, and the correlation coefficient was high. Also, there were no significant differences in the regression equations between the first and second times. Voxel values of micro-CT might be convertible to HA densities using a regression equation.

No abstract