Search

Aim: To evaluate the effects of the combined use of segmentation or detection models on the deep learning (DL) classification performance for cyst‐like lesions of the jaws on panoramic radiographs. Methods: The panoramic radiographs of 536 patients with cyst‐like lesions of the jaws and 130 patients without cyst‐like lesions were used in this study. The radiographs were arbitrarily assigned to training, validation, and test datasets. The following three DL systems were created: System 1 directly classified cyst‐like lesions of the jaws on panoramic radiographs using a VGG‐16 convolution neural network (CNN), System 2 combined two CNNs to perform a preceding segmentation (U‐Net) and then the classification (VGG‐16), and System 3 combined two CNNs to perform a preceding detection (YOLO) and then the classification (VGG‐16). The classification performance of three systems was evaluated and compared with that of oral and maxillofacial radiologists. Results: The classification performance of System 2 was higher than the other DL systems, demonstrating the efficacy of the combined use of DL segmentation and classification models. System 3 followed it. The radiologists showed similar accuracy with System 2 and higher performance than Systems 1 and 3. The three DL systems and the radiologists all showed higher performance for dentigerous and radicular cysts than for ameloblastoma and odontogenic keratocysts, because of bias in the number of cases between categories even if data were collected at two institutions. Conclusions: The performance of DL classification of cyst‐like lesions of the jaws was improved by the addition of a DL segmentation technique. [ABSTRACT FROM AUTHOR]

Aims: Various factors, including depth of invasion (DOI) and hemodynamics have been linked with the prediction of late cervical lymph nodes metastasis in patients with early tongue cancers. The objective of this study was to examine the deep learning performance of the intraoral Doppler ultrasound images for predicting the late cervical metastasis, by comparing DOI. Methods: Thirty‐three patients with early squamous cell tongue carcinomas were divided into two groups: 12 with late cervical metastasis, and 21 without metastasis. Intraoral Doppler ultrasound images of all subjects were cropped to 400 × 400 pixel squares, and 80% were used for a training dataset, and 20% were used for a testing dataset. The training dataset was imported into the DIGITS deep learning training system, the learning process for 300 epochs was performed using AlexNet neural network, and the resultant learning model was created. The testing dataset was applied to the model to evaluate the performance for distinguishing between the two groups. Results: Use of intraoral Doppler ultrasound images for predicting the late cervical metastasis achieved deep learning performances of 0.883 for the area under the ROC curve (AUC), 85.9% for accuracy, and 84.0% for sensitivity. On the other hand, the corresponding performances of DOI were 0.873, 84.8%, and 75.0%, using a DOI threshold of 5.6 mm. Conclusion: Our findings suggested that the performance of a deep learning system using intraoral Doppler ultrasound images of early tongue cancers to predict late cervical metastasis was sufficiently high, suggesting possible applications in imaging diagnosis support. [ABSTRACT FROM AUTHOR]

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. 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). 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. Deep learning could reliably detect the maxillary sinuses and identify maxillary sinusitis and cysts of the maxillary sinus regions. 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%. [ABSTRACT FROM AUTHOR]

Objectives: The purpose of this study was to generate radiographs including dentigerous cysts by applying the latest generative adversarial network (GAN; StyleGAN3) to panoramic radiography., Methods: A total of 459 cystic lesions were selected, and 409 images were randomly assigned as training data and 50 images as test data. StyleGAN3 training was performed for 500 000 images. Fifty generated images were objectively evaluated by comparing them with 50 real images according to four metrics: Fréchet inception distance (FID), kernel inception distance (KID), precision and recall, and inception score (IS). A subjective evaluation of the generated images was performed by three specialists who compared them with the real images in a visual Turing test., Results: The results of the metrics were as follows: FID, 199.28; KID, 0.14; precision, 0.0047; recall, 0.00; and IS, 2.48. The overall results of the visual Turing test were 82.3%. No significant difference was found in the human scoring of root resorption., Conclusions: The images generated by StyleGAN3 were of such high quality that specialists could not distinguish them from the real images., (© The Author(s) 2024. Published by Oxford University Press on behalf of the British Institute of Radiology and the International Association of Dentomaxillofacial Radiology. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Objectives: This study aimed to clarify the performance of magnetic resonance imaging (MRI)-based deep learning classification models in diagnosing temporomandibular joint osteoarthritis (TMJ-OA) and to compare the developed diagnostic assistance with human observers., Methods: The subjects were 118 patients who underwent MRI for examination of TMJ disorders. One hundred condyles with TMJ-OA and 100 condyles without TMJ-OA were enrolled. Deep learning was performed with four networks (ResNet18, EfficientNet b4, Inception v3, and GoogLeNet) using five-fold cross validation. Receiver operating characteristics (ROC) curves were drawn for each model and diagnostic metrics were determined. The performances of the four network models were compared using Kruskal-Wallis tests and post-hoc Scheffe tests, and ROCs between the best model and human were compared using chi-square tests, with p < 0.05 considered significant., Results: ResNet18 had areas under the curves (AUCs) of 0.91-0.93 and accuracy of 0.85-0.88, which were the highest among the four networks. There were significant differences in AUC and accuracy between ResNet and GoogLeNet (p = 0.0264 and p = 0.0418, respectively). The kappa values of the models were large, 0.95 for ResNet and 0.93 for EfficientNet. The experts achieved similar AUC and accuracy values ​​to the ResNet metrics, 0.94 and 0.85, and 0.84 and 0.84, respectively, but with a lower kappa of 0.67. Those of the dental residents showed lower values. There were significant differences in AUCs between ResNet and residents (p < 0.0001) and between experts and residents (p < 0.0001)., Conclusions: Using a deep learning model, high performance was confirmed for MRI diagnosis of TMJ-OA., (© The Author(s) 2024. Published by Oxford University Press on behalf of the British Institute of Radiology and the International Association of Dentomaxillofacial Radiology. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

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., Competing Interests: Conflicts of Interest: None, (Copyright © 2024 by Korean Academy of Oral and Maxillofacial Radiology.)

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.

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%.

Objectives: It is unclear whether computer-aided detection (CAD) systems for panoramic radiography can help inexperienced dentists to diagnose maxillary sinusitis. The aim of this study was to clarify whether a CAD system for panoramic radiography can contribute to improved diagnostic performance for maxillary sinusitis by inexperienced dentists., Methods: The panoramic radiographs of 49 patients with maxillary sinusitis and 49 patients with healthy sinuses were evaluated in this study. The diagnostic performance of the CAD system was determined. 12 inexperienced dentists and 4 expert oral and maxillofacial radiologists observed the total of 98 panoramic radiographs and judged the presence or absence of maxillary sinusitis, under conditions with and without the support of the CAD system. The receiver operating characteristic curves of the two groups were compared., Results: The CAD system provided sensitivity of 77.6%, specificity of 69.4% and accuracy of 73.5%. The diagnostic performance of the inexperienced dentists increased with the support of the CAD system. When the inexperienced dentists diagnosed maxillary sinusitis with CAD support, the area under the curve (AUC) was significantly higher than that without CAD support. When the focus was only on panoramic radiographs in which CAD support led to a correct diagnosis, the AUC of the inexperienced dentists increased to an equivalent level to that of the experienced radiologists., Conclusions: The CAD system supported the inexperienced dentists in diagnosing maxillary sinusitis on the panoramic radiographs. If the accuracy of the CAD system can be increased, the benefits of CAD support will be further enhanced.

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.