ABSTRACT
OBJECTIVES: Like other bones, the mandible and cervical vertebrae are affected by several systemic diseases. The aim of this study is to evaluate the effects of osteoporosis (OP), diabetes mellitus (DM), and dialysis-indicated advanced chronic kidney disease (CKD), which are the most effective systemic diseases on the bone metabolism, on the trabecular microstructure of the mandible and cervical vertebrae using cone beam computed tomography (CBCT). METHODS: 81 patients who signed our informed consent form are involved in the study. 18 of them were diagnosed with osteoporosis, 18 of them with diabetes mellitus, 18 of the patients had dialysis-indicated CKD, and 27 of them were in the control group without any systemic diseases. Nine patients in the control group, patients with CKD and patients with DM were men, and nine were women. All patients with osteoporosis and 18 of the patients in the control group were women. Using CBCT images, microstructural parameters of trabecular thickness (Tb.Th), trabecular spacing (Tb.Sp) and volume fraction (bone volume/total volume, BV/TV) were measured. RESULTS: Tb.Th and BV/TV values were higher in the control group, while Tb.Sp was higher in the osteoporosis group. The difference in BV/TV parameters was statistically significant (p = 0.02). In the DM group, Tb.Th and BV/TV values were lower and Tb.Sp values were significantly higher than in the control group (p = 0.001). In patients with advanced CKD, Tb.Th and BV/TV values were lower, while Tb.Sp values were higher than in the control group. Differences in Tb.Sp parameters were statistically significant (0.004). CONCLUSION: Systemic diseases affect bone tissue at different levels, and to evaluate these effects, cortical and trabecular bone parts must be investigated separately, and findings must be combined with patients' clinical symptoms. CBCT is suitable for microstructural evaluation of trabecular bone and the mandible carries valuable data for this purpose.
Subject(s)
Diabetes Mellitus , Osteoporosis , Male , Humans , Female , Cone-Beam Computed Tomography/methods , Osteoporosis/diagnostic imaging , Mandible/diagnostic imaging , Diabetes Mellitus/diagnostic imagingABSTRACT
Purpose: This study developed a convolutional neural network (CNN) model to diagnose maxillary sinusitis on panoramic radiographs (PRs) and cone-beam computed tomographic (CBCT) images and evaluated its performance. Materials and Methods: A CNN model, which is an artificial intelligence method, was utilized. The model was trained and tested by applying 5-fold cross-validation to a dataset of 148 healthy and 148 inflamed sinus images. The CNN model was implemented using the PyTorch library of the Python programming language. A receiver operating characteristic curve was plotted, and the area under the curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive values for both imaging techniques were calculated to evaluate the model. Results: The average accuracy, sensitivity, and specificity of the model in diagnosing sinusitis from PRs were 75.7%, 75.7%, and 75.7%, respectively. The accuracy, sensitivity, and specificity of the deep-learning system in diagnosing sinusitis from CBCT images were 99.7%, 100%, and 99.3%, respectively. Conclusion: The diagnostic performance of the CNN for maxillary sinusitis from PRs was moderately high, whereas it was clearly higher with CBCT images. Three-dimensional images are accepted as the "gold standard" for diagnosis; therefore, this was not an unexpected result. Based on these results, deep-learning systems could be used as an effective guide in assisting with diagnoses, especially for less experienced practitioners.
ABSTRACT
OBJECTIVES: Our study aimed to determine the prevalence and volumetric estimates of Stafne bone cavities (SBC) on cone beam computed tomography (CBCT) images. METHODS: This retrospective study, which involved the CBCT images of 1141 men and 1260 women with an age range of 10-90 years, aimed to determine the prevalence of SBCs and to calculate their volumes using the semi-automatic segmentation method. RESULTS: A total of 15 SBCs were diagnosed in 14 patients. Among the detected SBCs, 7.14% were found in a female patient and 92.86% were found in 13 male patients. Of the total number of SBCs, 6.67% were anteriorly located and 93.33% were posteriorly located. Bilateral SBCs had a prevalence of 0.04%; unilateral posterior SBCs 0.54% and anterior SBCs 0.04%. The mean SBC volume was calculated as 338.05 mm3. CONCLUSIONS: The results of our study showed that SBC is a rare anomaly. In contrast to two-dimensional imaging techniques, CBCT allows a precise determination of SBCs' pattern of impact on adjacent bony structures, relationship with the mandibular canal and dimensions.
