Automatic deep learning detection of overhanging restorations in bitewing radiographs.

OBJECTIVES: This study aimed to assess the effectiveness of deep convolutional neural network (CNN) algorithms for the detecting and segmentation of overhanging dental restorations in bitewing radiographs. METHODS: A total of 1160 anonymized bitewing radiographs were used to progress the artificial intelligence (AI) system for the detection and segmentation of overhanging restorations. The data were then divided into three groups: 80% for training (930 images, 2399 labels), 10% for validation (115 images, 273 labels), and 10% for testing (115 images, 306 labels). A CNN model known as You Only Look Once (YOLOv5) was trained to detect overhanging restorations in bitewing radiographs. After utilizing the remaining 115 radiographs to evaluate the efficacy of the proposed CNN model, the accuracy, sensitivity, precision, F1 score, and area under the receiver operating characteristic curve (AUC) were computed. RESULTS: The model demonstrated a precision of 90.9%, a sensitivity of 85.3%, and an F1 score of 88.0%. Furthermore, the model achieved an AUC of 0.859 on the receiver operating characteristic (ROC) curve. The mean average precision (mAP) at an intersection over a union (IoU) threshold of 0.5 was notably high at 0.87. CONCLUSIONS: The findings suggest that deep CNN algorithms are highly effective in the detection and diagnosis of overhanging dental restorations in bitewing radiographs. The high levels of precision, sensitivity, and F1 score, along with the significant AUC and mAP values, underscore the potential of these advanced deep learning techniques in revolutionizing dental diagnostic procedures.

The Detection of Pulp Stones with Automatic Deep Learning in Panoramic Radiographies: An AI Pilot Study.

This study aims to evaluate the effectiveness of employing a deep learning approach for the automated detection of pulp stones in panoramic imaging. A comprehensive dataset comprising 2409 panoramic radiography images (7564 labels) underwent labeling using the CranioCatch labeling program, developed in Eskisehir, Turkey. The dataset was stratified into three distinct subsets: training (n = 1929, 80% of the total), validation (n = 240, 10% of the total), and test (n = 240, 10% of the total) sets. To optimize the visual clarity of labeled regions, a 3 × 3 clash operation was applied to the images. The YOLOv5 architecture was employed for artificial intelligence modeling, yielding F1, sensitivity, and precision metrics of 0.7892, 0.8026, and 0.7762, respectively, during the evaluation of the test dataset. Among deep learning-based artificial intelligence algorithms applied to panoramic radiographs, the use of numerical identification for the detection of pulp stones has achieved remarkable success. It is expected that the success rates of training models will increase by using datasets consisting of a larger number of images. The use of artificial intelligence-supported clinical decision support system software has the potential to increase the efficiency and effectiveness of dentists.

Tooth numbering and classification on bitewing radiographs: an artificial intelligence pilot study.

OBJECTIVE: The aim of this study is to assess the efficacy of employing a deep learning methodology for the automated identification and enumeration of permanent teeth in bitewing radiographs. The experimental procedures and techniques employed in this study are described in the following section. STUDY DESIGN: A total of 1248 bitewing radiography images were annotated using the CranioCatch labeling program, developed in Eskisehir, Turkey. The dataset has been partitioned into 3 subsets: training (n = 1000, 80% of the total), validation (n = 124, 10% of the total), and test (n = 124, 10% of the total) sets. The images were subjected to a 3 × 3 clash operation in order to enhance the clarity of the labeled regions. RESULTS: The F1, sensitivity and precision results of the artificial intelligence model obtained using the Yolov5 architecture in the test dataset were found to be 0.9913, 0.9954, and 0.9873, respectively. CONCLUSION: The utilization of numerical identification for teeth within deep learning-based artificial intelligence algorithms applied to bitewing radiographs has demonstrated notable efficacy. The utilization of clinical decision support system software, which is augmented by artificial intelligence, has the potential to enhance the efficiency and effectiveness of dental practitioners.

3D evaluation of the maxillary sinus volumes in patients with bilateral cleft lip and palate.

One of the most common congenital anomalies of the head and neck region is a cleft lip and palate. This retrospective case-control research aimed to compare the maxillary sinus volumes in individuals with bilateral cleft lip and palate (BCLP) to a non-cleft control group. The study comprised 72 participants, including 36 patients with BCLP and 36 gender and age-matched control subjects. All topographies were obtained utilizing Cone Beam Computed Tomography (CBCT) for diagnostic purposes, and 3D Dolphin software was utilized for sinus segmentation. Volumetric measurements were taken in cubic millimeters. No significant differences were found between the sex and age distributions of both groups. Additionally, there was no statistically significant difference observed between the BCLP group and the control group on the right and left sides (p > 0.05). However, the mean maxillary sinus volumes of BCLP patients (8014.26 ± 2841.03 mm3) were significantly lower than those of the healthy control group (11,085.21 ± 3146.12 mm3) (p < 0.05). The findings of this study suggest that clinicians should be aware of the lower maxillary sinus volumes in BCLP patients when planning surgical interventions. The utilization of CBCT and sinus segmentation allowed for precise measurement of maxillary sinus volumes, contributing to the existing literature on anatomical variations in BCLP patients.

Evaluation of Bone Thickness and Density Values in Resistance Regions in Rapid Maxillary Expansion Using Computed Tomography.

OBJECTIVES: This study used computed tomography (CT) to compare the bone thickness and density values around the zygomaticomaxillary, zygomaticotemporal, and pterygomaxillary sutures that are resistant to rapid maxillary expansion (RME) treatment according to age, sex, and cervical vertebrae maturation (CVM) stage. METHODS: The study included 200 paranasal sinus records obtained for medical diagnosis and examination in a radiology clinic. The records provided data on 110 males and 90 females aged between 4 and 28 years. Bone thickness and density values around the zygomaticomaxillary, zygomaticotemporal, and pterygomaxillary sutures were measured using CT imaging. The correlations of bone thickness and density values with the variables of age, sex, and CVM stage were evaluated. RESULTS: No statistically significant difference was revealed between the bone thickness values around the zygomaticomaxillary and zygomaticotemporal sutures and age, sex, CVM stage, and the right and left regions of the same individual ( P >0.05). A strong correlation was identified between Hounsfield units (Hu) values on bone density in all 3 regions and age and sex ( P <0.001). No correlation was found between the CVM stage and density values around the zygomaticomaxillary, zygomaticotemporal, and pterygomaxillary sutures ( P >0.05). CONCLUSIONS: The Hu values of the records from females were higher than those of males in all age groups. It was observed that with increasing age, bone density values increased in all 3 regions, and thus circummaxillary region's Hu value increased.