Deep learning for preliminary profiling of panoramic images.

OBJECTIVE: This study explored the feasibility of using deep learning for profiling of panoramic radiographs. STUDY DESIGN: Panoramic radiographs of 1000 patients were used. Patients were categorized using seven dental or physical characteristics: age, gender, mixed or permanent dentition, number of presenting teeth, impacted wisdom tooth status, implant status, and prosthetic treatment status. A Neural Network Console (Sony Network Communications Inc., Tokyo, Japan) deep learning system and the VGG-Net deep convolutional neural network were used for classification. RESULTS: Dentition and prosthetic treatment status exhibited classification accuracies of 93.5% and 90.5%, respectively. Tooth number and implant status both exhibited 89.5% classification accuracy; impacted wisdom tooth status exhibited 69.0% classification accuracy. Age and gender exhibited classification accuracies of 56.0% and 75.5%, respectively. CONCLUSION: Our proposed preliminary profiling method may be useful for preliminary interpretation of panoramic images and preprocessing before the application of additional artificial intelligence techniques.

Variance of radiographical alveolar bone mineral density by the anatomical morphology of mandibular bone.

Purpose: Evaluating the bone mineral density (BMD) of alveolar bone is useful for dental treatments. The DentalSCOPE is an image analysis system developed to evaluate the BMD of alveolar bone. The aim of this study was to evaluate the relationship between cross-sectional anatomical size and BMD value. Materials and methods: Thirty-four subjects (adult dental patients and volunteers) participated in this study. Intraoral radiographs of the mandibular molar region were acquired. Using DentalSCOPE software, three to four line-shaped regions of interest (ROIs) were obtained in the alveolar septum region. Cross-sectional CT images of mandible at the same position to above mentioned line-shaped ROI was reconstructed from subject's dental CBCT images. The measurements were performed using cross-sectional CT images and compared with BMD value. Results and discussion: For stepwise multiple linear regression analysis, the buccal-lingual width of the mandibular body (mandible width) and the CT value of the cancellous bone were adopted as explanatory variables that affected the BMD of the mandible. The BMD value increased by 20 mg/mm2 when the mandible width increased by 1 mm, and the BMD value increased by 5 mg/mm2 when the CT value of the cancellous bone increased by 1%. Conclusion: In the clinical application of alveolar bone BMD, the effect of the anatomical morphology of alveolar bone should be taken into consideration.

Performance of deep learning technology for evaluation of positioning quality in periapical radiography of the maxillary canine.

OBJECTIVES: The aim of the present study was to create and test an automatic system for assessing the technical quality of positioning in periapical radiography of the maxillary canines using deep learning classification and segmentation techniques. METHODS: We created and tested two deep learning systems using 500 periapical radiographs (250 each of good- and bad-quality images). We assigned 350, 70, and 80 images as the training, validation, and test datasets, respectively. The learning model of system 1 was created with only the classification process, whereas system 2 consisted of both the segmentation and classification models. In each model, 500 epochs of training were performed using AlexNet and U-net for classification and segmentation, respectively. The segmentation results were evaluated by the intersection over union method, with values of 0.6 or more considered as success. The classification results were compared between the two systems. RESULTS: The segmentation performance of system 2 was recall, precision, and F measure of 0.937, 0.961, and 0.949, respectively. System 2 showed better classification performance values than those obtained by system 1. The area under the receiver operating characteristic curve values differed significantly between system 1 (0.649) and system 2 (0.927). CONCLUSIONS: The deep learning systems we created appeared to have potential benefits in evaluation of the technical positioning quality of periapical radiographs through the use of segmentation and classification functions.

Retrospective magnetic resonance imaging study of risk factors associated with sideways disk displacement of the temporomandibular joint.

As part of our ongoing investigation of risk and predictive factors associated with temporomandibular disorders, we used magnetic resonance imaging (MRI) to identify risk factors for sideways disk displacement of the temporomandibular joint in 26 patients with MRI-confirmed unilateral pure sideways disk displacement (medial or lateral disk displacement) and normal positioning of the contralateral temporomandibular joint. Coronal morphologic harmonization between the condyle and fossa, angle between the axis of the ramus and condyle, and angle between the lateral pterygoid muscle (LPM) and condyle were evaluated. Only angle of the LPM related to the condyle was significantly correlated with mediolateral disk position; the angles of joints with medial, normal, and lateral disk positions were 70.2°, 66.7°, and 60.1°, respectively. These results suggest that a greater angle of the inferior head of the LPM to the axis of the condyle on axial MRI images may cause medial disk displacement, while a smaller angle may result in lateral disk displacement. (J Oral Sci 58, 29-34, 2016).

Comparative analysis of the gonial angle on lateral cephalometric radiographs and panoramic radiographs.

We measured the gonial angle (GA) on panoramic radiography (PR) and analyzed the correlation between the GA on PR and lateral cephalometric radiography (LCR). In total, 49 PR films and LCR films from dentate young adults were evaluated. Orthodontists plotted four points (articulare, menton, posterior gonion, and lower gonion) on the PR and carefully traced them. Using a protractor, two radiologists measured the GA on LCR images. A simultaneous experimental study of two dry skulls was performed to compare the GA on LCR and PR. The GA was slightly smaller on the PR of the dry mandible than on the LCR and tended to decrease continuously with magnitude toward the Frankfort horizontal plane. The mean GA was 115.1 ± 5.2° on PR and 122.2 ± 6.4° on the LCR. The values were highly correlated (Pearson product-moment correlation coefficient, 0.801). The GA on PR was nonsignificantly smaller than that measured on LCR. The difference may be due to head position, the inclination angle of the mandibular body, and/or the direction of the incident X-ray beam.

Assessment of quality and interpretation of panoramic radiographs obtained in the Lao People's Democratic Republic as part of a teleradiology collaboration with Japan.

As part of quality assessment of a teleradiology program we evaluated the validity of patient information received, the quality of panoramic radiography imaging in Laos, and the ability of a Laotian radiologist to detect temporomandibular joint abnormalities. The amount of patient information gathered from 2,021 scans of panoramic radiographs was evaluated by triage before image diagnosis. Among the radiographs from 2,021 patients, primary triage indicated that there was insufficient information for 794 (39.3%) patients. Secondary triage to assess imaging failure included 1,227 radiographs, four of which were excluded from imaging diagnosis because of unacceptable image flaws. In total, 2,446 joints from 1,223 radiographs were evaluated for temporomandibular joint abnormalities in order to compare the image interpretation abilities of Laotian and Japanese radiologists. The kappa coefficient was 0.836 (P < 0.01) for the agreement between the two observers in detecting temporomandibular joint abnormalities on radiographs. We conclude that additional efforts are needed in order to overcome the challenges of maintaining quality in imaging techniques and diagnoses in Laos.