Search

Objective This study aimed to compare the performance of 3 deep learning models, including a model constructed with the transfer learning method, in detecting submandibular gland sialoliths on panoramic radiographs. Study Design We used data from 2 institutions (A and B) to create the models for use in institution B. In total, 224 panoramic radiographs with sialoliths were used. Model 1 was created using data from institution A only, model 2 was created using combined data from institutions A and B, and model 3 was created using the transfer learning method by having model 1 transferred and trained in various learning epochs using data from institution B. These models were tested and compared in their detection performance using testing data sets from institution B. Results Model 2 and model 3 with 300 epochs performed equally well and yielded the highest detection rates (recall: sensitivity of 85%, precision: positive predictive value of 100%, and F measure of 91.9%) for sialoliths on panoramic radiographs. Conclusion The results of this study suggest that use of the transfer learning method with an appropriate number of epochs may be an alternative to sharing patient personal data among institutions.

Summary Objectives Orthodontic tooth movement (OTM) increases sympathetic and sensory neurological markers in periodontal tissue. However, the relationship between the sympathetic and sensory nervous systems during OTM remains unclear. Therefore, the present study investigated the relationship between the sympathetic and sensory nervous systems activated by OTM using pharmacological methods. Materials and Methods We compared the effects of sympathectomy and sensory nerve injury during OTM in C57BL6/J mice. Capsaicin (CAP) was used to induce sensory nerve injury. Sympathectomy was performed using 6-hydroxydopamine. To investigate the effects of a β-agonist on sensory nerve injury, isoproterenol (ISO) was administered to CAP-treated mice. Furthermore, to examine the role of the central nervous system in OTM, the ventromedial hypothalamic nucleus (VMH) was ablated using gold thioglucose. Results Sensory nerve injury and sympathectomy both suppressed OTM and decreased the percent of the alveolar socket covered with osteoclasts (Oc.S/AS) in periodontal tissue. Sensory nerve injury inhibited increases in OTM-induced calcitonin gene-related peptide (CGRP) immunoreactivity (IR), a marker of sensory neurons, and tyrosine hydroxylase (TH) IR, a marker of sympathetic neurons, in periodontal tissue. Although sympathectomy did not decrease the number of CGRP-IR neurons in periodontal tissue, OTM-induced increases in the number of TH-IR neurons were suppressed. The ISO treatment restored sensory nerve injury-inhibited tooth movement and Oc.S/AS. Furthermore, the ablation of VMH, the centre of the sympathetic nervous system, suppressed OTM-induced increases in tooth movement and Oc.S/AS. Conclusions The present results suggest that OTM-activated sensory neurons contribute to enhancements in osteoclast activity and tooth movement through sympathetic nervous signalling.

To clarify the performance of transfer learning with a small number of Waters' images at institution B in diagnosing maxillary sinusitis, based on a source model trained with a large number of panoramic radiographs at institution A.The source model was created by a 200-epoch training process with 800 training and 60 validation datasets of panoramic radiographs at institution A using VGG-16. One hundred and eighty Waters' and 180 panoramic image patches with or without maxillary sinusitis at institution B were enrolled in this study, and were arbitrarily assigned to 120 training, 20 validation, and 40 test datasets, respectively. Transfer learning of 200 epochs was performed using the training and validation datasets of Waters' images based on the source model, and the target model was obtained. The test Waters' images were applied to the source and target models, and the performance of each model was evaluated. Transfer learning with panoramic radiographs and evaluation by two radiologists were undertaken and compared. The evaluation was based on the area of receiver-operating characteristic curves (AUC).When using Waters' images as the test dataset, the AUCs of the source model, target model, and radiologists were 0.780, 0.830, and 0.806, respectively. There were no significant differences between these models and the radiologists, whereas the target model performed better than the source model. For panoramic radiographs, AUCs were 0.863, 0.863, and 0.808, respectively, with no significant differences.This study performed transfer learning using a small number of Waters' images, based on a source model created solely from panoramic radiographs, resulting in a performance improvement to 0.830 in diagnosing maxillary sinusitis, which was equivalent to that of radiologists. Transfer learning is considered a useful method to improve diagnostic performance.

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.

Objectives The aim of the present study was to create effective deep learning-based models for diagnosing the presence or absence of cleft palate (CP) in patients with unilateral or bilateral cleft alveolus (CA) on panoramic radiographs. Methods The panoramic images of 491 patients who had unilateral or bilateral cleft alveolus were used to create two models. Model A, which detects the upper incisor area on panoramic radiographs and classifies the areas into the presence or absence of CP, was created using both object detection and classification functions of DetectNet. Using the same data for developing Model A, Model B, which directly classifies the presence or absence of CP on panoramic radiographs, was created using classification function of VGG-16. The performances of both models were evaluated with the same test data and compared with those of two radiologists. Results The recall, precision, and F-measure were all 1.00 in Model A. The area under the receiver operating characteristic curve (AUC) values were 0.95, 0.93, 0.70, and 0.63 for Model A, Model B, and the radiologists, respectively. The AUCs of the models were significantly higher than those of the radiologists. Conclusions The deep learning-based models developed in the present study have potential for use in supporting observer interpretations of the presence of cleft palate on panoramic radiographs.

Objective This investigation aimed to verify and compare the performance of 3 deep learning systems for classifying maxillary impacted supernumerary teeth (ISTs) in patients with fully erupted incisors. Study Design In total, the study included 550 panoramic radiographs obtained from 275 patients with at least 1 IST and 275 patients without ISTs in the maxillary incisor region. Three learning models were created by using AlexNet, VGG-16, and DetectNet. Four hundred images were randomly selected as training data, and 100 images were assigned as validating and testing data. The remaining 50 images were used as new testing data. The sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve were calculated. Detection performance was evaluated by using recall, precision, and F-measure. Results DetectNet generally produced the highest values of diagnostic efficacy. VGG-16 yielded significantly lower values compared with DetectNet and AlexNet. Assessment of the detection performance of DetectNet showed that recall, precision, and F-measure for detection in the incisor region were all 1.0, indicating perfect detection. Conclusions DetectNet and AlexNet appear to have potential use in classifying the presence of ISTs in the maxillary incisor region on panoramic radiographs. Additionally, DetectNet would be suitable for automatic detection of this abnormality.

[Purpose] The efficacy of exercise therapy in temporomandibular disorders has been recognized. Here, we present our experience with exercise therapy. [Participant and Methods] A 25-year-old female with a sudden onset of mouth opening limitation in October 2018 was admitted to our hospital in November 2018. Based on our initial findings, the patient was diagnosed with left disc derangement of the temporomandibular joint without reduction. A definitive diagnosis was established following magnetic resonance imaging in December 2018. Subsequently, range-of-motion exercises for the temporomandibular joint as passive movements and self-traction therapy as active movements were conducted. Magnetic resonance imaging was repeated 4 months after the first treatment. [Results] The temporomandibular joint disc remained in anterior dislocation during mouth opening and closing. The mouth opening joint motion was significantly improved compared to the pre-therapy range. The pain-related visual analog scale score also significantly improved. [Conclusion] The range of motion of the temporomandibular joint was improved by range-of-motion exercises for the temporomandibular joint, and was maintained and managed using self-traction therapy. Improvement of the range of motion was confirmed by magnetic resonance imaging.

Objective Both clinical and X-ray findings have been used for postoperative assessment of the donor site following secondary alveolar bone grafting in our department. However, this approach requires that patients be exposed to X-ray irradiation several times at the donor site and the cleft site. Furthermore, the findings do not depict bone healing status in detail and thus offer little information to help in deciding the required duration of postoperative movement restriction. Therefore, we sought to determine the utility of ultrasound in addition to X-ray for evaluating bone surface healing at the donor site. Methods Subjects were 17 patients (9 boys and 8 girls; median weight of harvested bone, 7.5 g) who underwent alveolar bone grafting using tibial grafts. All cases were evaluated on X-ray and ultrasound images. Results Agreement between the X-ray and ultrasound assessments was 88.2 % (15/17) at postoperative month 3 and 70.6 % (12/17) at postoperative month 6. No significant differences were observed, but the time required for healing tended to be longer when the weight of harvested bone was larger. Conclusions Ultrasound was a useful modality in postoperative assessment, and the combined use of ultrasound and X-ray examination was found to enable reduced exposure to X-ray irradiation and close observation of the bone surface. Also, movement restriction of ≥1 month appeared necessary, and the time to healing was longer for a larger weight of harvested bone.

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. 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. 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. The proposed method can be useful in automatic filing of dental charts for forensic identification and preprocessing of dental disease prescreening purposes.

Objective: This study aimed to create a deep learning model for automated bolus segmentation on videofluorography (VFG) images of patients with healthy swallowing and dysphagia using the artificial intelligence deep learning segmentation method, and to assess the performance of the method.Study Design: VFG images of 72 swallowing of 12 patients were continuously converted into 15 static images per second. In total, 3910 images were arbitrarily assigned to the training, validation, test 1, and test 2 datasets. In the training and validation datasets, images of colored bolus areas were prepared, along with original images. Using a U-Net neural network, a trained model was created after 500 epochs of training. The test datasets were applied to the trained model, and the performances of automatic segmentation (Jaccard index, Sørensen–Dice coefficient, and sensitivity) were calculated.Results: All performance values for the segmentation of the test 1 and 2 datasets were high, exceeding 0.9.Conclusion: Using an artificial intelligence deep learning segmentation method, we automatically segmented the bolus areas on VFG images; our method exhibited high performance. This model also allowed assessment of aspiration and laryngeal invasion.

Objectives: The purpose of this study was to evaluate the difference in performance of deep-learning (DL) models with respect to the image classes and amount of training data to create an effective DL model for detecting both unilateral cleft alveoli (UCAs) and bilateral cleft alveoli (BCAs) on panoramic radiographs. Methods: Model U was created using UCA and normal images, and Model B was created using BCA and normal images. Models C1 and C2 were created using the combined data of UCA, BCA, and normal images. The same number of CAs was used for training Models U, B, and C1, whereas Model C2 was created with a larger amount of data. The performance of all four models was evaluated with the same test data and compared with those of two human observers. Results: The recall values were 0.60, 0.73, 0.80, and 0.88 for Models A, B, C1, and C2, respectively. The results of Model C2 were highest in precision and F-measure (0.98 and 0.92) and almost the same as those of human observers. Significant differences were found in the ratios of detected to undetected CAs of Models U and C1 (p = 0.01), Models U and C2 (p < 0.001), and Models B and C2 (p = 0.036). Conclusions: The DL models trained using both UCA and BCA data (Models C1 and C2) achieved high detection performance. Moreover, the performance of a DL model may depend on the amount of training data.

Objectives: The aims of the present study were to construct a deep learning model for automatic segmentation of the temporomandibular joint (TMJ) disc on magnetic resonance (MR) images, and to evaluate the performances using the internal and external test data. Methods: In total, 1200 MR images of closed and open mouth positions in patients with temporomandibular disorder (TMD) were collected from two hospitals (Hospitals A and B). The training and validation data comprised 1000 images from Hospital A, which were used to create a segmentation model. The performance was evaluated using 200 images from Hospital A (internal validity test) and 200 images from Hospital B (external validity test). Results: Although the analysis of performance determined with data from Hospital B showed low recall (sensitivity), compared with the performance determined with data from Hospital A, both performances were above 80%. Precision (positive predictive value) was lower when test data from Hospital A were used for the position of anterior disc displacement. According to the intra-articular TMD classification, the proportions of accurately assigned TMJs were higher when using images from Hospital A than when using images from Hospital B. Conclusion: The segmentation deep learning model created in this study may be useful for identifying disc positions on MR images.

The aim of this study was to create and assess a deep learning model using segmentation and transfer learning methods to visualize the proximity of the mandibular canal to an impacted third molar on panoramic radiographs.The panoramic radiographs containing the mandibular canal and impacted third molar were collected from 2 hospitals (Hospitals A and B). A total of 3200 areas were used for creating and evaluating learning models. A source model was created using the data from Hospital A, simulatively transferred to Hospital B, and trained using various amounts of data from Hospital B to create target models. The same data were then applied to the target models to calculate the Dice coefficient, Jaccard index, and sensitivity.The performance of target models trained using 200 or more data sets was equivalent to that of the source model tested using data obtained from the same hospital (Hospital A).Sufficiently qualified models could delineate the mandibular canal in relation to an impacted third molar on panoramic radiographs using a segmentation technique. Transfer learning appears to be an effective method for creating such models using a relatively small number of data sets.

The purpose of this study was to create an effective deep learning (DL) model for detecting cleft alveolus (CA), including bilateral CA (BCA), on panoramic radiographs by comparing the detection performance of a DL model based on unilateral CA (UCA) and normal data with a model developed by combining UCA, BCA and normal data. We created two models using DetectNet. Model A was created using only UCA and normal images, and Model B was created using UCA, BCA and normal images. The performance of Models A and B was evaluated with the same testing data, and compared with two human observers. The total detection sensitivities were 0.55, 0.85, and 0.86 for Model A, Model B, and human observers, respectively. The ratios of detected and undetected CAs were significantly different among these three evaluators (p < 0.001). Regarding the UCA group, no significant differences were found in the ratio of those between Models A and B (p = 0.248). However, in the BCA group, the ratios were significantly different between the models (p < 0.001). The DL model created with the data including the BCA (Model B) achieved high detection performance for the testing data of both the UCA and BCA.

Although panoramic radiography has a role in the examination of patients with cleft alveolus (CA), its appearances is sometimes difficult to interpret. The aims of this study were to develop a computer-aided diagnosis system for diagnosing the CA status on panoramic radiographs using a deep learning object detection technique with and without normal data in the learning process, to verify its performance in comparison to human observers, and to clarify some characteristic appearances probably related to the performance. The panoramic radiographs of 383 CA patients with cleft palate (CA with CP) or without cleft palate (CA only) and 210 patients without CA (normal) were used to create two models on the DetectNet. The models 1 and 2 were developed based on the data without and with normal subjects, respectively, to detect the CAs and classify them into with or without CP. The model 2 reduced the false positive rate (1/30) compared to the model 1 (12/30). The overall accuracy of Model 2 was higher than Model 1 and human observers. The model created in this study appeared to have the potential to detect and classify CAs on panoramic radiographs, and might be useful to assist the human observers.

Objective The aim of this study was to investigate whether a deep learning object detection technique can automatically detect and classify radiolucent lesions in the mandible on panoramic radiographs. Study Design Panoramic radiographs of patients with mandibular radiolucent lesions of 10 mm or greater, including ameloblastomas, odontogenic keratocysts, dentigerous cysts, radicular cysts, and simple bone cysts, were included. Lesion labels, including region of interest coordinates, were created in text format. In total, 210 training images and labels were imported into the deep learning GPU training system (DIGITS). A learning model was created using the deep neural network DetectNet. Two testing data sets (testing 1 and 2) were applied to the learning model. Similarities and differences between the prediction and ground-truth images were evaluated using Intersection over Union (IoU). Sensitivity and false-positive rate per image were calculated using an IoU threshold of 0.6. The detection performance for each disease was assessed using multiclass learning. Results Sensitivity was 0.88 for both testing 1 and 2. The false-positive rate per image was 0.00 for testing 1 and 0.04 for testing 2. The best combination of detection and classification sensitivity occurred with dentigerous cysts. Conclusions Radiolucent lesions of the mandible can be detected with high sensitivity using deep learning.

The aim of this study was to evaluate the use of a convolutional neural network (CNN) system for detecting vertical root fracture (VRF) on panoramic radiography. Three hundred panoramic images containing a total of 330 VRF teeth with clearly visible fracture lines were selected from our hospital imaging database. Confirmation of VRF lines was performed by two radiologists and one endodontist. Eighty percent (240 images) of the 300 images were assigned to a training set and 20% (60 images) to a test set. A CNN-based deep learning model for the detection of VRFs was built using DetectNet with DIGITS version 5.0. To defend test data selection bias and increase reliability, fivefold cross-validation was performed. Diagnostic performance was evaluated using recall, precision, and F measure. Of the 330 VRFs, 267 were detected. Twenty teeth without fractures were falsely detected. Recall was 0.75, precision 0.93, and F measure 0.83. The CNN learning model has shown promise as a tool to detect VRFs on panoramic images and to function as a CAD tool.

The present study aimed to clarify the reliabilities of four characteristic appearances, subchondral cyst, erosion, generalized sclerosis, and osteophyte, for evaluation of degenerative diseases with osseous changes in the temporomandibular joint (TMJ) using panoramic TMJ projection imaging and computed tomography (CT), and to investigate the imaging features of these modalities for subchondral cyst with reference to its magnetic resonance imaging (MRI) features. The reliabilities (κ values) of panoramic TMJ projection and CT images were determined by three radiologists for each characteristic appearance of TMJ osseous changes in 146 condyles. The features of cyst-like areas on CT images with agreement among the three radiologists were investigated for size, location, and continuity with the joint space together with MRI signal intensity and surrounding edema-like lesions. Panoramic TMJ projection images showed moderate and substantial agreements for erosion and osteophyte evaluations, respectively; while CT images showed substantial agreements for subchondral cyst, erosion, and osteophyte evaluations. Cyst-like areas on CT images were predominantly located in the central parts and 69 of 86 (80.2%) areas showed no communication with the joint space. Cyst-like areas with diameters exceeding 2 mm showed high or moderate MRI signal intensities. Edema-like lesions were observed in 10 of 28 (29.4%) condyles. The reliabilities of panoramic TMJ projection and CT images were clarified for each characteristic appearance. The results support the bone contusion theory for the formation of subchondral cysts in the TMJ. A possible improvement in reliability is suggested relative to MRI findings.

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.

Objectives To assess the feasibility of using a super-resolution convolutional neural network to improve the quality of cone-beam computed tomography (CBCT) images for visualizing soft-tissue structures. Methods Multidetector computed tomography (CT) images of 200 subjects who were assessed for the status of an impacted third molar were collected as training datasets. CBCT images of 10 subjects who were also examined with CT were collected as testing datasets. The training process used a modified U-Net and bone and soft-tissue window CT images. After creating a model to convert bone images to soft-tissue images, CBCT images were provided as input and the model outputted estimated CBCT images. These estimated CBCT images were then compared with soft-tissue window CBCT and CT images, using slices through approximately the same anatomical regions. Image evaluation was performed with subjective observations and histogram descriptions. Results The visibility of soft-tissue structures was improved by the technique, with high visibility being attained in the submandibular region, although visibility remained a little obscured in the maxillary region. Conclusions The feasibility of a deep learning-based super resolution technique to improve the visibility of soft-tissue structures on estimated CBCT images was verified.

To investigate the use of transfer learning when applying a deep learning source model from one institution (institution A) to another institution (institution B) for creating effective models (target models) for the detection of maxillary sinuses and diagnosis of maxillary sinusitis on panoramic radiographs. In addition, to determine appropriate numbers of training data for the transfer learning. Source model was created using 350 panoramic radiographs from institution A as training data. Transfer learning was performed by adding 25, 50, 100, 150, or 225 panoramic radiographs as training data from institution B to the source model; this yielded the target models T25, T50, T100, T150 and T225. Each model was then evaluated using test data that comprised 40 images from institution A, 30 images from institution B. The performance indices (recall, precision and F1 score) for detecting the maxillary sinuses by the source model exceeded 0.98 when using test data A from institution A, but they deteriorated when using test data B from institution B. In the evaluation of target models using test data B, model T25 showed improved detection performance (recall of 0.967). The diagnostic performance of model T50 for maxillary sinusitis exceeded 0.9 in sensitivity. Transfer learning, which involves applying a small amount of data to the source model, yielded high performances in detecting the maxillary sinuses and diagnosing the maxillary sinusitis on panoramic radiographs. This study serves as a reference when adapting source models to other institutions.

The purpose of this study is to analyze dental panoramic radiographs for completing dental files to contribute to the diagnosis by dentists. As the initial stage, we detected each tooth and classified its tooth type. Since the final goal of this study includes multiple tasks, such as determination of dental conditions and recognition of lesions, we proposed a multitask training based on a Single Shot Multibox Detector (SSD) with a branch to predict the presence or absence of a tooth. The results showed that the proposed model improved the detection rate by 1.0%, the number of false positives per image by 0.03, and the detection rate by tooth type (total number of successfully detected and classified teeth/total number of teeth) by 1.6% compared with the original SSD, suggesting the effectiveness of the multi-task learning in dental panoramic radiographs. In addition, we integrated results of single-class detection without distinguishing the tooth type and 16-class (central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, third molar, distinguished by upper and lower jaws) detection for improving the detection rate and included post-processing for classification of teeth into 32 types and correction of tooth numbering. As a result, the detection rate of 98.8%, 0.33 false positives per image, and classification rate of 92.4% for 32 tooth types were archived.

Purpose This study investigated the effects of 1 year of training on imaging diagnosis, using static ultrasonography (US) salivary gland images of Sjogren syndrome patients. Materials and methods This study involved 3 inexperienced radiologists with different levels of experience, who received training 1 or 2 days a week under the supervision of experienced radiologists. The training program included collecting patient histories and performing physical and imaging examinations for various maxillofacial diseases. The 3 radiologists (observers A, B, and C) evaluated 400 static US images of salivary glands twice at a 1-year interval. To compare their performance, 2 experienced radiologists evaluated the same images. Diagnostic performance was compared between the 2 evaluations using the area under the receiver operating characteristic curve (AUC). Results Observer A, who was participating in the training program for the second year, exhibited no significant difference in AUC between the first and second evaluations, with results consistently comparable to those of experienced radiologists. After 1 year of training, observer B showed significantly higher AUCs than before training. The diagnostic performance of observer B reached the level of experienced radiologists for parotid gland assessment, but differed for submandibular gland assessment. For observer C, who did not complete the training, there was no significant difference in the AUC between the first and second evaluations, both of which showed significant differences from those of the experienced radiologists. Conclusion These preliminary results suggest that the training program effectively helped inexperienced radiologists reach the level of experienced radiologists for US examinations.

In fields using functional near-infrared spectroscopy (fNIRS), there is a need for an easy-to-understand method that allows visual presentation and rapid analysis of data and test results. This preliminary study examined whether deep learning (DL) could be applied to the analysis of fNIRS-derived brain activity data. To create a visual presentation of the data, an imaging program was developed for the analysis of hemoglobin (Hb) data from the prefrontal cortex in healthy volunteers, obtained by fNIRS before and after tooth clenching. Three types of imaging data were prepared: oxygenated hemoglobin (oxy-Hb) data, deoxygenated hemoglobin (deoxy-Hb) data, and mixed data (using both oxy-Hb and deoxy-Hb data). To differentiate between rest and tooth clenching, a cross-validation test using the image data for DL and a convolutional neural network was performed. The network identification rate using Hb imaging data was relatively high (80‒90%). These results demonstrated that a method using DL for the assessment of fNIRS imaging data may provide a useful analysis system.

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 2 data sets. A learning process of 1000 epochs with the training images and labels was performed using DetectNet, and a learning model was created. The testing 1 and testing 2 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 2 data sets, 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%.

This study aimed to examine the performance of deep learning object detection technology for detecting and identifying maxillary cyst-like lesions on panoramic radiography. Altogether, 412 patients with maxillary cyst-like lesions (including several benign tumors) were enrolled. All panoramic radiographs were arbitrarily assigned to the training, testing 1, and testing 2 datasets of the study. The deep learning process of the training images and labels was performed for 1000 epochs using the DetectNet neural network. The testing 1 and testing 2 images were applied to the created learning model, and the detection performance was evaluated. For lesions that could be detected, the classification performance (sensitivity) for identifying radicular cysts or other lesions were examined. The recall, precision, and F-1 score for detecting maxillary cysts were 74.6%/77.1%, 89.8%/90.0%, and 81.5%/83.1% for the testing 1/testing 2 datasets, respectively. The recall was higher in the anterior regions and for radicular cysts. The sensitivity was higher for identifying radicular cysts than for other lesions. Using deep learning object detection technology, maxillary cyst-like lesions could be detected in approximately 75–77%.

To apply a deep learning object detection technique to CT images for detecting cervical lymph nodes metastasis in patients with oral cancers, and to clarify the detection performance. One hundred and fifty-nine metastatic and 517 non-metastatic lymph nodes on 365 CT images in 56 patients with oral squamous cell carcinoma were examined. The images were arbitrarily assigned to training, validation, and testing datasets. Using the neural network, ‘DetectNet’ for object detection, the training procedure was conducted for 1000 epochs. Testing image datasets were applied to the learning model, and the detection performance was calculated. The learning curve indicated that the recall (sensitivity) for detecting metastatic and non-metastatic lymph nodes reached 90% and 80%, respectively, while the model performance recall by applying the test dataset was 73.0% and 52.5%, respectively. The recall for detecting level IB and Level II metastatic lymph nodes was relatively high. A system that has the potential to automatically detect cervical lymph nodes was constructed.

Dental record plays an important role in dental diagnosis and personal identification. Automatic image preinterpretation can help reducing dentists’ workload and improving diagnostic efficiency. Systematic dental record filing enables effective utilization of accumulated records at dental clinics for forensic identification. We have been investigating a tooth labeling method on dental cone-beam CT images for the purpose of automatic filing of dental charts. In our previous method, two separate networks were employed for detection and classification of teeth. Although detection accuracy was promising, classification performance had a room of improvement. The purpose of this study was to investigate the use of the relation network to utilize information of positional relationship between teeth for the detection and classification. Using the proposed method, both detection and classification performance improved. Especially, the tooth type classification accuracy improved. The proposed method can be useful in automatic filing of the dental chart.

The present study aimed to clarify the characteristic computed tomography (CT) features that indicate synovial chondromatosis (SC) with a few small calcified bodies or without calcification on panoramic images, and to discuss their differences from the features of temporomandibular disorder (TMD). Panoramic and CT images from 11 patients with histologically verified SC of the temporomandibular joint were investigated. Based on the panoramic images, the patients were classified into a distinct group (5 patients) with typical features of calcified loose bodies and an indistinct group (6 patients) without such bodies. On the CT images, findings for high-density structures suggesting calcified loose bodies, joint space widening, and bony changes in the articular eminence and glenoid fossa (eminence/fossa) and condyle were analyzed. All 5 distinct group patients showed high-density structures on CT images, while 2 of 6 indistinct group patients showed no high-density structures even on soft-tissue window CT images. A significant difference was found for the joint space distance between the affected and unaffected sides. A low-density area relative to the surrounding muscles, suggesting joint space widening, was observed on the affected side in 2 indistinct group patients. All 11 patients regardless of distinct or indistinct classification showed bony changes in the eminence/fossa with predominant findings of extended sclerosis and erosion. Eminence/fossa osseous changes including extended sclerosis and erosion may be effective CT features for differentiating SC from TMD even when calcified loose bodies cannot be identified.

Objective The aim of this study was to compare time and storage space requirements, diagnostic performance, and consistency among 3 image recognition convolutional neural networks (CNNs) in the evaluation of the relationships between the mandibular third molar and the mandibular canal on panoramic radiographs. Study Design Of 600 panoramic radiographs, 300 each were assigned to noncontact and contact groups based on the relationship between the mandibular third molar and the mandibular canal. The CNNs were trained twice by using cropped image patches with sizes of 70 × 70 pixels and 140 × 140 pixels. Time and storage space were measured for each system. Accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC) were determined. Intra-CNN and inter-CNN consistency values were calculated. Results Time and storage space requirements depended on the depth of CNN layers and number of learned parameters, respectively. The highest AUC values ranged from 0.88 to 0.93 in the CNNs created by 70 × 70 pixel patches, but there were no significant differences in diagnostic performance among any of the models with smaller patches. Intra-CNN and inter-CNN consistency values were good or very good for all CNNs. Conclusions The size of the image patches should be carefully determined to ensure acquisition of high diagnostic performance and consistency.

This study was performed to evaluate the diagnostic performance of deep learning systems using ultrasonography (USG) images of the submandibular glands (SMGs) in three different conditions: obstructive sialoadenitis, Sjögren’s syndrome (SjS), and normal glands. Fifty USG images with a confirmed diagnosis of obstructive sialoadenitis, 50 USG images with a confirmed diagnosis of SjS, and 50 USG images with no SMG abnormalities were included in the study. The training group comprised 40 obstructive sialoadenitis images, 40 SjS images, and 40 control images, and the test group comprised 10 obstructive sialoadenitis images, 10 SjS images, and 10 control images for deep learning analysis. The performance of the deep learning system was calculated and compared between two experienced radiologists. The sensitivity of the deep learning system in the obstructive sialoadenitis group, SjS group, and control group was 55.0%, 83.0%, and 73.0%, respectively, and the total accuracy was 70.3%. The sensitivity of the two radiologists was 64.0%, 72.0%, and 86.0%, respectively, and the total accuracy was 74.0%. This study revealed that the deep learning system was more sensitive than experienced radiologists in diagnosing SjS in USG images of two case groups and a group of healthy subjects in inflammation of SMGs.

The purpose of this study was to clarify which panoramic radiographic features can predict the development of bisphosphonate-related osteonecrosis of the jaw (BRONJ). Participants included 24 patients treated with bisphosphonates (BP) for osteoporosis who developed osteonecrosis of the jaw (ONJ+ group). Controls included 179 patients treated with BP who did not have osteonecrosis (ONJ− group) and 200 patients with no history of BP administration (unmedicated group). The mandibular cortical width, mandibular cortical index (MCI), sclerosis of trabecular bone, and thickening of the lamina dura were evaluated on panoramic radiographs. The mandibular cortical width was significantly smaller in the ONJ– group than in the other groups. Class II MCI (semilunar defects of endosteal margin) was frequently noted on the affected and contralateral sides in the ONJ+ group but not in the ONJ− or unmedicated groups. Sclerosis of the trabecular bone was significantly more frequently observed on the affected side in the ONJ+ group than in the other groups. Thickening of the lamina dura was observed significantly more frequently in the BP-treated groups than in the unmedicated group. Class II MCI may be an indicator to predict the development of BRONJ. Sclerosis of trabecular bone was a characteristic imaging feature of BRONJ. Thickening of the lamina dura may be an imaging feature caused by BP administration.

To clarify CT diagnostic performance in extranodal extension of cervical lymph node metastases using deep learning classification. Seven-hundred and three CT images (178 with and 525 without extranodal extension) in 51 patients with cervical lymph node metastases from oral squamous cell carcinoma were enrolled in this study. CT images were cropped to an arbitrary size to include lymph nodes and surrounding tissues. All images were automatically divided into two datasets, assigning 80% as the training dataset and 20% as the testing dataset. The automated selection was repeated five times. Each training dataset was imported to a deep learning training system “DIGITS”. Five learning models were created after 300 epochs of the learning process using a neural network “AlexNet”. Each testing dataset was applied to each created learning model and resulting five performances were averaged as estimated diagnostic performances. A radiologist measured the minor axis and three radiologists evaluated central necrosis and irregular borders of each lymph node, and the diagnostic performances were obtained. The deep learning accuracy of extranodal extension was 84.0%. The radiologists’ accuracies based on minor axis ≥ 11 mm, central necrosis, and irregular borders were 55.7%, 51.1% and 62.6%, respectively. The deep learning diagnostic performance in extranodal extension was significantly higher than that of radiologists. This method is expected to improve diagnostic accuracy by further study with increasing the number of patients.