Five-year change of panoramic radiomorphometric indices and fractal dimension values in type 2 diabetes patients.

OBJECTIVES: Diabetes mellitus is a chronic disease characterized by dysregulation of glucose metabolism, with characteristic long-term complications accompanied by changes in bone quality. The purpose of this study is to compare the results with a control group by performing radiomorphometric analyses on panoramic radiographs obtained 5 years apart to examine changes in the mandibular bone cortex and microstructures of type 2 diabetes mellitus (T2DM) patients. METHODS: Two panoramic radiographs that were taken 5 years (mean 5.26 ± 0.134) apart from 52 patients with T2DM (n:26) and a control group (n:26) were used. A total of 104 images were evaluated. Analyses were done from the condyle (FD1), angulus (FD2), distal second premolar apex (FD3), and anterior to the mental foramen (FD4) for fractal dimension (FD) in the mandible. Symphysis index (SI), anterior index (AI), molar index (MI), posterior index (PI), and panoramic mandibular index (PMI) measurements were taken for cortical analysis. Three-way ANOVA, three-way robust ANOVA, two-way ANOVA, and two-way robust ANOVA tests were used for statistical analysis (p < 0.05). RESULTS: After a 5-year period, there was a significant decrease in all FD measures of the mandible in both T2DM and control groups (p < 0.05). This resulted in a statistical difference in the main effect of time. After a 5-year period, no significant difference in mandibular cortical measures was identified between the T2DM and control groups (p > 0.05). CONCLUSION: According to panoramic radiography, the mandibular trabecular structure deteriorated after 5 years, whereas cortical values remained the same. It concluded that T2DM had no effect on these results.

Second mesiobuccal canal segmentation with YOLOv5 architecture using cone beam computed tomography images.

The objective of this study is to use a deep-learning model based on CNN architecture to detect the second mesiobuccal (MB2) canals, which are seen as a variation in maxillary molars root canals. In the current study, 922 axial sections from 153 patients' cone beam computed tomography (CBCT) images were used. The segmentation method was employed to identify the MB2 canals in maxillary molars that had not previously had endodontic treatment. Labeled images were divided into training (80%), validation (10%) and testing (10%) groups. The artificial intelligence (AI) model was trained using the You Only Look Once v5 (YOLOv5x) architecture with 500 epochs and a learning rate of 0.01. Confusion matrix and receiver-operating characteristic (ROC) analysis were used in the statistical evaluation of the results. The sensitivity of the MB2 canal segmentation model was 0.92, the precision was 0.83, and the F1 score value was 0.87. The area under the curve (AUC) in the ROC graph of the model was 0.84. The mAP value at 0.5 inter-over union (IoU) was found as 0.88. The deep-learning algorithm used showed a high success in the detection of the MB2 canal. The success of the endodontic treatment can be increased and clinicians' time can be preserved using the newly created artificial intelligence-based models to identify variations in root canal anatomy before the treatment.

Nasopharynx evaluation in children of unilateral cleft palate patients and normal with cone beam computed tomography.

OBJECTIVE: This study aimed to examine the morphological characteristics of the nasopharynx in unilateral Cleft lip/palate (CL/P) children and non-cleft children using cone beam computed tomography (CBCT). METHODS: A retrospective study consisted of 54 patients, of which 27 patients were unilateral CL/P, remaining 27 patients have no CL/P. Eustachian tubes orifice (ET), Rosenmuller fossa (RF) depth, presence of pharyngeal bursa (PB), the distance of posterior nasal spine (PNS)-pharynx posterior wall were quantitatively evaluated. RESULTS: The main effect of the CL/P groups was found to be effective on RF depth-right (p < 0.001) and RF depth-left (p < 0.001). The interaction effect of gender and CL/P groups was not influential on measurements. The cleft-side main effect was found to be effective on RF depth-left (p < 0.001) and RF depth-right (p = 0002). There was no statistically significant relationship between CL/P groups and the presence of bursa pharyngea. CONCLUSIONS: Because it is the most common site of nasopharyngeal carcinoma (NPC), the anatomy of the nasopharynx should be well known in the early diagnosis of NPC.

Convolutional Neural Network Performance for Sella Turcica Segmentation and Classification Using CBCT Images.

The present study aims to validate the diagnostic performance and evaluate the reliability of an artificial intelligence system based on the convolutional neural network method for the morphological classification of sella turcica in CBCT (cone-beam computed tomography) images. In this retrospective study, sella segmentation and classification models (CranioCatch, Eskisehir, Türkiye) were applied to sagittal slices of CBCT images, using PyTorch supported by U-Net and TensorFlow 1, and we implemented the GoogleNet Inception V3 algorithm. The AI models achieved successful results for sella turcica segmentation of CBCT images based on the deep learning models. The sensitivity, precision, and F-measure values were 1.0, 1.0, and 1.0, respectively, for segmentation of sella turcica in sagittal slices of CBCT images. The sensitivity, precision, accuracy, and F1-score were 1.0, 0.95, 0.98, and 0.84, respectively, for sella-turcica-flattened classification; 0.95, 0.83, 0.92, and 0.88, respectively, for sella-turcica-oval classification; 0.75, 0.94, 0.90, and 0.83, respectively, for sella-turcica-round classification. It is predicted that detecting anatomical landmarks with orthodontic importance, such as the sella point, with artificial intelligence algorithms will save time for orthodontists and facilitate diagnosis.