Yuan M, Gao AT, Wang TM, Liang JH, Aihemati GB, Cao Y, Xie X, Miao LY, Lin ZT. Using Meglumine Diatrizoate to improve the accuracy of diagnosis of cracked teeth on Cone-beam CT images. International Endodontic Journal, 53, 709-714, 2020. Aim To explore in a laboratory setting the feasibility of using Meglumine Diatrizoate (MD) to improve the accuracy of diagnosis of cracked teeth on cone-beam CT (CBCT) images. Methodology Twenty-four teeth were cracked artificially by soaking them cyclically in liquid nitrogen and hot water. The number and position of crack lines were evaluated with a dental operating microscope and used as the gold standard. The artificially cracked teeth were then examined using routine scanning (RS) and enhanced scanning (ES) modes, respectively. For the ES mode, MD was painted on the surface of the crack lines, and then, CBCT scanning with the same parameters was performed after 10 min. A radiological graduate student and an experienced radiologist evaluated the presence or absence of crack lines, respectively. The differences between the RS and ES modes were determined and assessed using McNemar's test. Inter-examiner agreement and intra-examiner agreement were assessed using kappa analysis. Results Fifty-seven crack lines were found in the 24 cracked teeth. In the RS mode, the accuracy of detection of crack lines was 23% (radiological graduate student) and 32% (experienced radiologist), whereas in the ES mode, the accuracy was 61% (radiological graduate student) and 65% (experienced radiologist). The inter-examiner agreement was 0.693 in RS mode and 0.849 in ES mode. The intra-examiner agreement was 0.872 and 0.949 for the radiological graduate student in RS and ES mode respectively; and one for the experienced radiologist both in RS and ES mode. Conclusions Compared with routine scanning mode, more crack lines could be detected in enhanced scanning mode using Meglumine Diatrizoate as a contrast medium. MD could be a potential contrast medium to improve the accuracy of detection of crack lines on CBCT images.

Cone-beam computed tomography (CBCT) has been widely used in diagnosis of vertical root fractures (VRFs) in recent years. According to the American Association of Endodontists (AAE) classification, there are five types of cracked teeth and VRF is one of them. Due to the variability and overlapping of the cracks and fractures, some narrow fractures on the roots of VRFs could not be detected by CBCT, and some wide cracks on the crown of cracked teeth could be detected by CBCT. In this review, we firstly discussed the value of CBCT in the diagnosis of the AAE five types of cracked teeth and presented CBCT manifestations of some typical cases. Secondly, we summarized the factors influencing the diagnosis of cracks/fractures using CBCT, namely, CBCT device-related factors, patient-related factors, and evaluator-related factors. The possible strategies to improve the diagnostic accuracy in the clinic practice are also discussed in this part. Finally, we compared the differences of root fractures with lateral canals and external root resorption on CBCT images.

No abstract

Objectives Evaluating the diagnostic efficiency of deep learning models to diagnose vertical root fracture in vivo on cone-beam CT (CBCT) images. Materials and methods The CBCT images of 276 teeth (138 VRF teeth and 138 non-VRF teeth) were enrolled and analyzed retrospectively. The diagnostic results of these teeth were confirmed by two chief radiologists. There were two experimental groups: auto-selection group and manual selection group. A total of 552 regions of interest of teeth were cropped in manual selection group and 1118 regions of interest of teeth were cropped in auto-selection group. Three deep learning networks (ResNet50, VGG19 and DenseNet169) were used for diagnosis (3:1 for training and testing). The diagnostic efficiencies (accuracy, sensitivity, specificity, and area under the curve (AUC)) of three networks were calculated in two experiment groups. Meanwhile, 552 teeth images in manual selection group were diagnosed by a radiologist. The diagnostic efficiencies of the three deep learning network models in two experiment groups and the radiologist were calculated. Results In manual selection group, ResNet50 presented highest accuracy and sensitivity for diagnosing VRF teeth. The accuracy, sensitivity, specificity and AUC was 97.8%, 97.0%, 98.5%, and 0.99, the radiologist presented accuracy, sensitivity, and specificity as 95.3%, 96.4 and 94.2%. In auto-selection group, ResNet50 presented highest accuracy and sensitivity for diagnosing VRF teeth, the accuracy, sensitivity, specificity and AUC was 91.4%, 92.1%, 90.7% and 0.96. Conclusion In manual selection group, ResNet50 presented higher diagnostic efficiency in diagnosis of in vivo VRF teeth than VGG19, DensenNet169 and radiologist with 2 years of experience. In auto-selection group, Resnet50 also presented higher diagnostic efficiency in diagnosis of in vivo VRF teeth than VGG19 and DensenNet169. This makes it a promising auxiliary diagnostic technique to screen for VRF teeth.

Sclerosing odontogenic carcinoma (SOC) is a primary intraosseous carcinoma of the jaw that was listed as a separate entity for the first time in the latest version of the World Health Organization classification of Head and Neck Tumors (2017). In this report, we present a case of SOC involving a circuitous diagnostic process because of the inadequately detailed biopsy findings and inherent impression based on the imaging manifestations. Through an extensive literature review, the histopathological and immunohistochemical features of the disease were briefly summarized. Radiological findings of SOC have been characterized in detail, and an imaging classification scheme has been proposed to further discuss the diversity of radiographic features. Due to the rarity of the disease, a comprehensive understanding of SOC is needed, and close collaboration between clinicians, radiologists, and pathologists is crucial to avoid misdiagnosis.