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.

Tooth recognition of 32 tooth types by branched single shot multibox detector and integration processing in panoramic radiographs.

Purpose: The purpose of our study was to analyze dental panoramic radiographs and contribute to dentists' diagnosis by automatically extracting the information necessary for reading them. As the initial step, we detected teeth and classified their tooth types in this study. Approach: We propose single-shot multibox detector (SSD) networks with a side branch for 1-class detection without distinguishing the tooth type and for 16-class detection (i.e., the central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, and third molar, distinguished by the upper and lower jaws). In addition, post-processing was conducted to integrate the results of the two networks and categorize them into 32 classes, differentiating between the left and right teeth. The proposed method was applied to 950 dental panoramic radiographs obtained at multiple facilities, including a university hospital and dental clinics. Results: The recognition performance of the SSD with a side branch was better than that of the original SSD. In addition, the detection rate was improved by the integration process. As a result, the detection rate was 99.03%, the number of false detections was 0.29 per image, and the classification rate was 96.79% for 32 tooth types. Conclusions: We propose a method for tooth recognition using object detection and post-processing. The results show the effectiveness of network branching on the recognition performance and the usefulness of post-processing for neural network output.

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.

Performance of deep learning models constructed using panoramic radiographs from two hospitals to diagnose fractures of the mandibular condyle.

OBJECTIVE: The present study aimed to verify the classification performance of deep learning (DL) models for diagnosing fractures of the mandibular condyle on panoramic radiographs using data sets from two hospitals and to compare their internal and external validities. METHODS: Panoramic radiographs of 100 condyles with and without fractures were collected from two hospitals and a fivefold cross-validation method was employed to construct and evaluate the DL models. The internal and external validities of classification performance were evaluated as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS: For internal validity, high classification performance was obtained, with AUC values of >0.85. Conversely, external validity for the data sets from the two hospitals exhibited low performance. Using combined data sets from both hospitals, the DL model exhibited high performance, which was slightly superior or equal to that of the internal validity but without a statistically significant difference. CONCLUSION: The constructed DL model can be clinically employed for diagnosing fractures of the mandibular condyle using panoramic radiographs. However, the domain shift phenomenon should be considered when generalizing DL systems.

Tooth detection and classification on panoramic radiographs for automatic dental chart filing: improved classification by multi-sized input data.

OBJECTIVES: Dental state plays an important role in forensic radiology in case of large scale disasters. However, dental information stored in dental clinics are not standardized or electronically filed in general. The purpose of this study is to develop a computerized system to detect and classify teeth in dental panoramic radiographs for automatic structured filing of the dental charts. It can also be used as a preprocessing step for computerized image analysis of dental diseases. METHODS: One hundred dental panoramic radiographs were employed for training and testing an object detection network using fourfold cross-validation method. The detected bounding boxes were then classified into four tooth types, including incisors, canines, premolars, and molars, and three tooth conditions, including nonmetal restored, partially restored, and completely restored, using classification network. Based on the visualization result, multisized image data were used for the double input layers of a convolutional neural network. The result was evaluated by the detection sensitivity, the number of false-positive detection, and classification accuracies. RESULTS: The tooth detection sensitivity was 96.4% with 0.5 false positives per case. The classification accuracies for tooth types and tooth conditions were 93.2% and 98.0%. Using the double input layer network, 6 point increase in classification accuracy was achieved for the tooth types. CONCLUSIONS: The proposed method can be useful in automatic filing of dental charts for forensic identification and preprocessing of dental disease prescreening purposes.

Isothermal Growth and Stacking Evolution in Highly Uniform Bernal-Stacked Bilayer Graphene.

Controlling the stacking order in bilayer graphene (BLG) allows realizing interesting physical properties. In particular, the possibility of tuning the band gap in Bernal-stacked (AB) BLG (AB-BLG) has a great technological importance for electronic and optoelectronic applications. Most of the current methods to produce AB-BLG suffer from inhomogeneous layer thickness and/or coexistence with twisted BLG. Here, we demonstrate a method to synthesize highly pure large-area AB-BLG by chemical vapor deposition using Cu-Ni films. Increasing the reaction time resulted in a gradual increase of the AB stacking, with the BLG eventually free from twist regions for the longer growth times (99.4% of BLG has AB stacking), due to catalyst-assisted continuous BLG reconstruction driven by carbon dissolution-segregation processes. The band gap opening was confirmed by the electrical measurements on field-effect transistors using two different device configurations. The concept of the continuous reconstruction to achieve highly pure AB-BLG offers a way to control the stacking order of catalytically grown two-dimensional materials.

Shear-wave sonoelastography for assessing masseter muscle hardness in comparison with strain sonoelastography: study with phantoms and healthy volunteers.

UNLABELLED: Objectives Shear-wave sonoelastography is expected to facilitate low operator dependency, high reproducibility and quantitative evaluation, whereas there are few reports on available normative values of in vivo tissue in head and neck fields. The purpose of this study was to examine the reliabilities on measuring hardness using shear-wave sonoelastography and to clarify normal values of masseter muscle hardness in healthy volunteers. Methods Phantoms with known hardness ranging from 20 to 140 kPa were scanned with shear-wave sonoelastography, and inter- and intraoperator reliabilities were examined compared with strain sonoelastography. The relationships between the actual and measured hardness were analyzed. The masseter muscle hardness in 30 healthy volunteers was measured using shear-wave sonoelastography. RESULTS: The inter- and intraoperator intraclass correlation coefficients were almost perfect. Strong correlations were seen between the actual and measured hardness. The mean hardness of the masseter muscles in healthy volunteers was 42.82 ± 5.56 kPa at rest and 53.36 ± 8.46 kPa during jaw clenching. CONCLUSIONS: The hardness measured with shear-wave sonoelastography showed high-level reliability. Shear-wave sonoelastography may be suitable for evaluation of the masseter muscles.

Can sonographic features be efficacy predictors of robotic massage treatment for masseter and temporal muscle in patients with temporomandibular disorder with myofascial pain?

OBJECTIVE: The aim of this study was to detect sonographic predictors for the efficacy of massage treatment of masseter and temporal muscle in temporomandibular disorders (TMDs) patients with myofascial pain. METHODS: Thirty-seven TMD patients with myofascial pain (6 men and 31 women, a median age of 45 years) were enrolled. An oral rehabilitation robot massaged the patient's masseter and temporal muscles with a standard massage pressure of 10 N for 16 min. The standard treatment protocol was set five sessions every 2 weeks. The median total duration of treatment was 9.5 weeks. Efficacy of treatment was evaluated based on maximum mouth opening and visual analog scale scores of muscle pain and daily life impediments. The intramuscular echogenic bands and elasticity index ratios of the masseter muscles were evaluated on sonographic or sonoelastographic images obtained before treatment and after the third and last treatment sessions. RESULTS: The sonographic features detected different changes after the third treatment session between the therapy-effective and therapy-ineffective groups: in the therapy-effective group, the frequency of visibility of the distinct echogenic bands increased, and the elasticity index ratio decreased. CONCLUSION: Sonographic features after the third treatment session may be useful as predictors of therapeutic efficacy.

Potential clinical application of masseter and temporal muscle massage treatment using an oral rehabilitation robot in temporomandibular disorder patients with myofascial pain.

OBJECTIVES: To investigate the safety, suitable treatment regimen, and efficacy of masseter and temporal muscle massage treatment using an oral rehabilitation robot. METHODS: Forty-one temporomandibular disorder (TMD) patients with myofascial pain (8 men, 33 women, median age: 46 years) were enrolled. The safety, suitable massage regimen, and efficacy of this treatment were investigated. Changes in masseter muscle thickness were evaluated on sonograms. RESULTS: No adverse events occurred with any of the treatment sessions. Suitable massage was at pressure of 10 N for 16 minutes. Five sessions were performed every 2 weeks. Total duration of treatment was 9·5 weeks in median. Massage treatment was effective in 70·3% of patients. Masseter muscle thickness decreased with treatment in the therapy-effective group. CONCLUSION: This study confirmed the safety of massage treatment, and established a suitable regimen. Massage was effective in 70·3% of patients and appeared to have a potential as one of the effective treatments for myofascial pain.

Observation of maxillary incisive canal using dry skulls between Hellman's dental age IA and IIIC.

The maxillary incisive canals were observed in childhood from infancy to school-aged children to clarify their development. Cone-beam computed tomography was performed to investigate 44 dry child skulls. Two-dimensional images of various planes in the maxillary incisive canal were reconstructed on a computer using 3-dimensional visualization and measurement software. Then, antero-posterior angulation, and antero-posterior and lateral axes of the maxillary incisive canal were measured at the inferior and middle levels. The mean difference of angulation between the inferior and middle levels was 2.3 degrees in IIC, and 11.1 degrees in IIIC. The mean ratio of the lateral axis to antero-posterior axis at the middle level was 2.54 in IIC, and 1.93 in IIIC. In conclusion, it was antero-posteriorly straight from IA to IIC, and, after IIIA, it curved at the middle level. The cross-sectional shape in IIC was depressed with a larger lateral axis.