Search

Objectives: The objective of our study was to develop and validate a deep learning approach based on convolutional neural networks (CNNs) for automatic detection of the mandibular third molar (M3) and the mandibular canal (MC) and evaluation of the relationship between them on CBCT., Materials and Methods: A dataset of 254 CBCT scans with annotations by radiologists was used for the training, the validation, and the test. The proposed approach consisted of two modules: (1) detection and pixel-wise segmentation of M3 and MC based on U-Nets; (2) M3-MC relation classification based on ResNet-34. The performances were evaluated with the test set. The classification performance of our approach was compared with two residents in oral and maxillofacial radiology., Results: For segmentation performance, the M3 had a mean Dice similarity coefficient (mDSC) of 0.9730 and a mean intersection over union (mIoU) of 0.9606; the MC had a mDSC of 0.9248 and a mIoU of 0.9003. The classification models achieved a mean sensitivity of 90.2%, a mean specificity of 95.0%, and a mean accuracy of 93.3%, which was on par with the residents., Conclusions: Our approach based on CNNs demonstrated an encouraging performance for the automatic detection and evaluation of the M3 and MC on CBCT. Clinical relevance An automated approach based on CNNs for detection and evaluation of M3 and MC on CBCT has been established, which can be utilized to improve diagnostic efficiency and facilitate the precision diagnosis and treatment of M3., (© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Objective: We performed a systematic review to investigate the appearance of imaging signs on magnetic resonance imaging (MRI), cone-beam computed tomography (CBCT), and conventional computed tomography (CT) scans of the temporomandibular joints (TMJs) of patients with juvenile idiopathic arthritis (JIA)., Materials and Methods: We performed electronic searches of the PubMed, Embase, Web of Science, Scopus, Lilacs, and the Cochrane Library databases to identify studies investigating JIA and its related imaging findings. Inclusion criteria were as follows: original article studies based on humans and systematic reviews, studies enrolling patients under 18 years of age with a diagnostic of JIA, the use of International League of Associations for Rheumatology (ILAR) criteria and one type of medical imaging (MRI, CBCT, or CT), and papers published in the English language., Results: A total of six studies met the inclusion criteria, four involving MRI and two involving CBCT. Additionally, all six studies analyzed the imaging findings of pathological TMJ affected by JIA. The results showed that synovial membrane enhancement, condylar erosions, and condylar flattening were the most prevalent imaging findings in JIA., Conclusion: MRI examinations are more specific for detecting anomalies in the TMJ than CBCT and CT. Additionally, these results must be correlated with clinical signs to verify the correct diagnosis., Clinical Relevance: This study identified the most prevalent imaging signs of JIA to provide an early and correct diagnosis of the disease., (© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Objectives: The aim of this study is to verify whether the diagnostic accuracy of cone beam computed tomography (CBCT) is superior to panoramic radiography (PR) in predicting inferior alveolar nerve (IAN) exposure during the lower third molar extraction., Materials and Methods: Eight electronic databases were searched up to September 2020. Studies that evaluated the accuracy (sensitivity, specificity, positive-predictive value, and negative predictive value) of both imaging methods were included. The gold standard was the visualization of the IAN exposure during the extraction of lower third molars. The gray literature was also used to include any other paper that might meet the eligibility criteria. The meta-analysis was performed with OpenMeta-Analyst and ReviewManager v.5.3 software. The methodology of the studies was evaluated using QUADAS-2., Results: Among the search, three studies met all the eligibility criteria and were included in the qualitative and quantitative synthesis. The meta-analysis was conducted with all included studies. Accuracy values for CBCT were 95.1% for sensitivity (p=0.666) and 64.4% for specificity (p<0.001). For PR sensitivity and specificity, we observed 73.9% (p=0.101) and 24.8% (p<0.001), respectively., Conclusions: Both exams were reliable for detecting positive cases of exposure of the IAN. However, CBCT had a better performance compared to PT in predicting IAN exposure during surgery., Clinical Relevance: To better understand the CBCT accuracy in predicting the IAN exposure during surgery, since this event can increase the likelihood of IAN injury and, consequently, cause neurosensory disturbances., (© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)