Oral RadiologyPub Date : 2023-10-01Epub Date: 2023-03-09DOI: 10.1007/s11282-023-00678-7
Gülsün Akay, M Ali Akcayol, Kevser Özdem, Kahraman Güngör
{"title":"Deep convolutional neural network-the evaluation of cervical vertebrae maturation.","authors":"Gülsün Akay, M Ali Akcayol, Kevser Özdem, Kahraman Güngör","doi":"10.1007/s11282-023-00678-7","DOIUrl":"10.1007/s11282-023-00678-7","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to automatically determine the cervical vertebral maturation (CVM) processes on lateral cephalometric radiograph images using a proposed deep learning-based convolutional neural network (CNN) model and to test the success rate of this CNN model in detecting CVM stages using precision, recall, and F1-score.</p><p><strong>Methods: </strong>A total of 588 digital lateral cephalometric radiographs of patients with a chronological age between 8 and 22 years were included in this study. CVM evaluation was carried out by two dentomaxillofacial radiologists. CVM stages in the images were divided into 6 subgroups according to the growth process. A convolutional neural network (CNN) model was developed in this study. Experimental studies for the developed model were carried out in the Jupyter Notebook environment using the Python programming language, the Keras, and TensorFlow libraries.</p><p><strong>Results: </strong>As a result of the training that lasted 40 epochs, 58% training and 57% test accuracy were obtained. The model obtained results that were very close to the training on the test data. On the other hand, it was determined that the model showed the highest success in terms of precision and F1-score in the CVM Stage 1 and the highest success in the recall value in the CVM Stage 2.</p><p><strong>Conclusion: </strong>The experimental results have shown that the developed model achieved moderate success and it reached a classification accuracy of 58.66% in CVM stage classification.</p>","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"629-638"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10626374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluation of the influence of hyoid bone position, volume, and types on pharyngeal airway volume and cephalometric measurements.","authors":"Aida Kurbanova, Seçil Aksoy, Meltem Nalça Andrieu, Ulaş Öz, Kaan Orhan","doi":"10.1007/s11282-023-00691-w","DOIUrl":"10.1007/s11282-023-00691-w","url":null,"abstract":"<p><strong>Objectives: </strong>We aimed to explore the position, morphological, and morphometric properties of the hyoid bone (HB) and to investigate the effect of HB on the pharyngeal airway (PA) volume and cephalometric measurements.</p><p><strong>Methods: </strong>A total of 305 patients with CT images were included in the study. DICOM images were transferred to the InVivoDental three-dimensional imaging software. The position of the HB was determined based on the cervical vertebra level and in volume render tab, the bone was classified into six types after all structures around the HB were removed. Also, final bone volume was recorded. In the same tab, the pharyngeal airway volume was divided and measured in three groups (nasopharynx-oropharynx-hypopharynx). The linear and angular measurements were performed on the 3D cephalometric analysis tab.</p><p><strong>Results: </strong>HB was most commonly located in C3 vertebra level (80.3%). While B-type was found to be the most frequent (34%), V-type was the least frequent (8%). The volume of the HB was found to be significantly higher in male (3205 mm<sup>3</sup>) than female (2606 mm<sup>3</sup>) patients. Also, it was significantly higher in the C4 vertebra group. The vertical height of the face was positively correlated with the HB volume, C4 level position, and increased oro-nasopharyngeal airway volume.</p><p><strong>Conclusion: </strong>The volume of the HB is found to differ significantly between genders and can potentially serve as a valuable diagnostic tool for understanding respiratory disorders. Its morphometric features are associated with increased face height and airway volume; however, are not related with the skeletal malocclusion classes.</p>","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"731-742"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10283034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Effect of data size on tooth numbering performance via artificial intelligence using panoramic radiographs.","authors":"Semih Gülüm, Seçilay Kutal, Kader Cesur Aydin, Gazi Akgün, Aleyna Akdağ","doi":"10.1007/s11282-023-00689-4","DOIUrl":"10.1007/s11282-023-00689-4","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to investigate the effect of number of data on model performance, for the detection of tooth numbering problem on dental panoramic radiographs, with the help of image processing and deep learning algorithms.</p><p><strong>Study design: </strong>The data set consists of 3000 anonymous dental panoramic X-rays of adult individuals. Panoramic X-rays were labeled on the basis of 32 classes in line with the FDI tooth numbering system. In order to examine the relationship between the number of data used in image processing algorithms and model performance, four different datasets which include 1000, 1500, 2000 and 2500 panoramic X-rays, were used. The training of the models was carried out with the YOLOv4 algorithm and trained models were tested on a fixed test dataset with 500 data and compared based on F1 score, mAP, sensitivity, precision and recall metrics.</p><p><strong>Results: </strong>The performance of the model increased as the number of data used during the training of the model increased. Therefore, the last model trained with 2500 data showed the highest success among all the trained models.</p><p><strong>Conclusion: </strong>Dataset size is important for dental enumeration, and large samples should be considered as more reliable.</p>","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"715-721"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10283535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Assessment of palatal mucosal thickness and location of the greater palatine foramen using cone-beam computed tomography: a retrospective study.","authors":"Bahar Füsun Oduncuoğlu, Hazal Karslioğlu, Ipek Naz Karasu, Mediha Nur Nisanci Yilmaz, Elif Inonu","doi":"10.1007/s11282-023-00699-2","DOIUrl":"10.1007/s11282-023-00699-2","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to measure the palatal mucosal thickness and examine the location of the greater palatine foramen using cone-beam computerized tomography (CBCT).</p><p><strong>Methods: </strong>In this study, cone-beam computed tomography (CBCT) images of the maxillary posterior region of 120 subjects were evaluated. The palatal mucosal thickness (PMT), palatal width and depth, and location of the greater palatine foramen (GPF) were determined on CBCT. The differences in the palatal mucosal thickness according to gender and palatal width/palatal depth were analyzed. The location of the GPF related to the maxillary molars was noted.</p><p><strong>Results: </strong>The mean palatal mucosal thicknesses from the canine to the second molar teeth were 3.66, 3.90, 4.06, 3.76, and 3.92 mm, respectively. The mean PMT at the second premolar was statistically thicker than at other regions (p < 0,001). There was no relationship between PMT and gender. However, the palatal depth and width of the males were greater than females. (p = 0.004 and p = 0.014, respectively) PMT in the low palatal vault group had statistically higher compared to the high palatal vault group. (p = 0.023) Greater palatine foramen was mostly observed between second and third molar teeth. (48%).</p><p><strong>Conclusions: </strong>According to our results, first and second premolar regions can be preferable in soft tissue grafting procedures for safe and successful treatment outcomes. The measurement of the thickness of the palatal mucosa and the evaluation of the greater palatine foramen location before the surgical procedures are essential steps to harvest from the ideal donor site and to achieve optimal surgical outcomes.</p>","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"784-791"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10284587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oral RadiologyPub Date : 2023-10-01DOI: 10.1007/s11282-023-00684-9
Salih Eren Meral, Seyhan Karaaslan, Hakan Hıfzı Tüz, Serdar Uysal
{"title":"Correction: Evaluation of the temporomandibular joint morphology and condylar position with cone-beam computerized tomography in patients with internal derangement.","authors":"Salih Eren Meral, Seyhan Karaaslan, Hakan Hıfzı Tüz, Serdar Uysal","doi":"10.1007/s11282-023-00684-9","DOIUrl":"10.1007/s11282-023-00684-9","url":null,"abstract":"","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"822"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10259703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oral RadiologyPub Date : 2023-10-01Epub Date: 2023-07-10DOI: 10.1007/s11282-023-00698-3
Abbas Shokri, Azita Ehsani, Arman Yousefi
{"title":"Prevalence of bifid variations of the mandibular canal in an Iranian population using cone-beam computed tomography.","authors":"Abbas Shokri, Azita Ehsani, Arman Yousefi","doi":"10.1007/s11282-023-00698-3","DOIUrl":"10.1007/s11282-023-00698-3","url":null,"abstract":"<p><strong>Objectives: </strong>Bifid mandibular canal (MC) is an anatomical variation of the MC. This study aimed to assess the prevalence and shape of bifid MC in an Iranian population.</p><p><strong>Materials and methods: </strong>A total of 681 patients who had undergone cone-beam computed tomography (CBCT) for different purposes between 2018 and 2020 were evaluated. After detection, bifid MCs were classified into four types forward, buccolingual, dental, and retromolar. CBCT images were assessed by two oral and maxillofacial radiologists. Data were analyzed by SPSS using an independent t-test and Chi-square test.</p><p><strong>Results: </strong>Bifid MC was found in 23 (3.4%) out of 681 patients, with a mean age of 32.21 years. Ten patients (1.5%) had a bifid MC on the right side, 6 (0.9%) on the left side, and 7 (1%) bilaterally. However, no significant correlation was found between laterality and the prevalence of bifid MC (P > 0.05). Bifid MC was found in 8 males (34.8%) and 15 females (65.2%). Gender had no significant correlation with the prevalence of bifid MC (P > 0.05). Forward type was the most common (n = 8, 1.2%) followed by buccolingual (n = 5, 0.73%), dental (n = 2, 0.3%), and retromolar (n = 1, 0.14%) types.</p><p><strong>Conclusion: </strong>According to the present results, bifid MC was not uncommon in the Iranian population of the present study, and forward type was the most common, followed by buccal and then dental bifid MCs. There was no significant correlation between sex and age with bifid MC but bifid MC was detected more frequently in females than males, and it was seen unilaterally in a higher percentage of the cases.</p>","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"779-783"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10279572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Accuracy of non-contact semiconductor X-ray analyzer for quality assurance in intraoral radiography: a comparison with ionization chamber dosimeter.","authors":"Shun Nouchi, Hidenori Yoshida, Yusaku Miki, Yasuhito Tezuka, Ruri Ogawa, Ichiro Ogura","doi":"10.1007/s11282-023-00692-9","DOIUrl":"10.1007/s11282-023-00692-9","url":null,"abstract":"<p><strong>Objectives: </strong>The aim of the present study was to evaluate the accuracy of a non-contact semiconductor X-ray analyzer for quality assurance in intraoral radiography, especially a comparison with an ionization chamber dosimeter.</p><p><strong>Methods: </strong>Intraoral radiography was performed with intraoral X-ray unit using the dental protocol at our hospital: tube voltage, 70 kV; tube current, 7 mA. Accuracy of dose and half-value layer (HVL) measurements was analyzed with a non-contact semiconductor X-ray analyzer and an ionization chamber dosimeter. Stability of the semiconductor sensor, effect of scattered radiation, and comparison of measured HVL between the ionization chamber and the semiconductor sensor were analyzed in this study.</p><p><strong>Results: </strong>The values with the semiconductor sensor were tube voltage: 70.3 ± 0.2 kVp (degree of variability: 0.28%), dose: 454.1 ± 12.3 μGy (degree of variability: 2.7%), and HVL: 1.91 ± 0.02 mmAl (degree of variability: 1.0%). With collimator, the dose with the semiconductor sensor and the ionization chamber decreased by 2.3 μ Gy and 5.2 μ Gy, respectively. The measured HVL of the semiconductor dosimeter was more than that of ionization chamber, and the semiconductor dosimeter was less than ionization chamber in variation of between without and with collimator.</p><p><strong>Conclusion: </strong>This study indicated the accuracy of a non-contact semiconductor X-ray analyzer for quality assurance in intraoral radiography, especially a comparison with an ionization chamber dosimeter. The semiconductor sensor can be useful for quality assurance in intraoral radiography.</p>","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"766-770"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10282123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oral RadiologyPub Date : 2023-10-01Epub Date: 2023-04-25DOI: 10.1007/s11282-023-00685-8
Habib Al Hasan, Farhan Hasin Saad, Saif Ahmed, Nabeel Mohammed, Taseef Hasan Farook, James Dudley
{"title":"Experimental validation of computer-vision methods for the successful detection of endodontic treatment obturation and progression from noisy radiographs.","authors":"Habib Al Hasan, Farhan Hasin Saad, Saif Ahmed, Nabeel Mohammed, Taseef Hasan Farook, James Dudley","doi":"10.1007/s11282-023-00685-8","DOIUrl":"10.1007/s11282-023-00685-8","url":null,"abstract":"<p><strong>Purpose: </strong>(1) To evaluate the effects of denoising and data balancing on deep learning to detect endodontic treatment outcomes from radiographs. (2) To develop and train a deep-learning model and classifier to predict obturation quality from radiomics.</p><p><strong>Methods: </strong>The study conformed to the STARD 2015 and MI-CLAIMS 2021 guidelines. 250 deidentified dental radiographs were collected and augmented to produce 2226 images. The dataset was classified according to endodontic treatment outcomes following a set of customized criteria. The dataset was denoised and balanced, and processed with YOLOv5s, YOLOv5x, and YOLOv7 models of real-time deep-learning computer vision. Diagnostic test parameters such as sensitivity (Sn), specificity (Sp), accuracy (Ac), precision, recall, mean average precision (mAP), and confidence were evaluated.</p><p><strong>Results: </strong>Overall accuracy for all the deep-learning models was above 85%. Imbalanced datasets with noise removal led to YOLOv5x's prediction accuracy to drop to 72%, while balancing and noise removal led to all three models performing at over 95% accuracy. mAP saw an improvement from 52 to 92% following balancing and denoising.</p><p><strong>Conclusion: </strong>The current study of computer vision applied to radiomic datasets successfully classified endodontic treatment obturation and mishaps according to a custom progressive classification system and serves as a foundation to larger research on the subject matter.</p>","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"683-698"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10504118/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10289139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oral RadiologyPub Date : 2023-10-01DOI: 10.1007/s11282-023-00708-4
Kyriaki Seremidi, Anastasia Mitsea, William Papaioannou, Konstantina Petroleka, Sotiria Gizani
{"title":"Correction: Assessing quality and quantity of cortical bone in childhood cancer survivors using anthropometric indices.","authors":"Kyriaki Seremidi, Anastasia Mitsea, William Papaioannou, Konstantina Petroleka, Sotiria Gizani","doi":"10.1007/s11282-023-00708-4","DOIUrl":"10.1007/s11282-023-00708-4","url":null,"abstract":"","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"821"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10262462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oral RadiologyPub Date : 2023-10-01Epub Date: 2023-03-15DOI: 10.1007/s11282-023-00677-8
Andaç Imak, Adalet Çelebi, Onur Polat, Muammer Türkoğlu, Abdulkadir Şengür
{"title":"ResMIBCU-Net: an encoder-decoder network with residual blocks, modified inverted residual block, and bi-directional ConvLSTM for impacted tooth segmentation in panoramic X-ray images.","authors":"Andaç Imak, Adalet Çelebi, Onur Polat, Muammer Türkoğlu, Abdulkadir Şengür","doi":"10.1007/s11282-023-00677-8","DOIUrl":"10.1007/s11282-023-00677-8","url":null,"abstract":"<p><strong>Objective: </strong>Impacted tooth is a common problem that can occur at any age, causing tooth decay, root resorption, and pain in the later stages. In recent years, major advances have been made in medical imaging segmentation using deep convolutional neural network-based networks. In this study, we report on the development of an artificial intelligence system for the automatic identification of impacted tooth from panoramic dental X-ray images.</p><p><strong>Methods: </strong>Among existing networks, in medical imaging segmentation, U-Net architectures are widely implemented. In this article, for dental X-ray image segmentation, blocks and convolutional block structures using inverted residual blocks are upgraded by taking advantage of U-Net's network capacity-intensive connections. At the same time, we propose a method for jumping connections in which bi-directional convolution long short-term memory is used instead of a simple connection. Assessment of the proposed artificial intelligence model performance was evaluated with accuracy, F1-score, intersection over union, and recall.</p><p><strong>Results: </strong>In the proposed method, experimental results are obtained with 99.82% accuracy, 91.59% F1-score, 84.48% intersection over union, and 90.71% recall.</p><p><strong>Conclusion: </strong>Our findings show that our artificial intelligence system could help with future diagnostic support in clinical practice.</p>","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":"39 4","pages":"614-628"},"PeriodicalIF":2.2,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10281127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}