This study aimed to assess the reliability of AI-based Diagnocat system that assists the healthcare processes in the diagnosis of caries on intraoral radiographs. The proximal surfaces of the 323 selected teeth on the intraoral radiographs were evaluated by two independent observers using the AI-based Diagnocat system. The presence or absence of carious lesions was recorded during Phase 1. After 4 months, the AI-aided human observers evaluated the same radiographs (Phase 2), and the advanced convolutional neural network (CNN) reassessed the radiographic data (Phase 3). Subsequently, data reflecting human disagreements were excluded (Phase 4). For each phase, the Cohen and Fleiss kappa values, as well as the sensitivity, specificity, positive and negative predictive values, and diagnostic accuracy ​​of Diagnocat, were calculated. During the four phases, the range of Cohen kappa values between the human observers and Diagnocat were κ=0.66-1, κ=0.58-0.7, and κ=0.49-0.7. The Fleiss kappa values were κ=0.57-0.8. The sensitivity, specificity and diagnostic accuracy values ranged between 0.51-0.76, 0.88-0.97 and 0.76-0.86, respectively. The Diagnocat CNN supports the evaluation of intraoral radiographs for caries diagnosis, as determined by consensus between human and AI system observers. Our study may aid in the understanding of deep learning-based systems developed for dental imaging modalities for dentists and contribute to expanding the body of results in the field of AI-supported dental radiology, as concluded by other scientific publications.

Background/Objectives: Our study aimed to determine the accuracy of the artificial intelligence-based Diagnocat system (DC) in detecting periapical lesions (PL) on panoramic radiographs (PRs). Methods: 616 teeth were selected from 357 panoramic radiographs, including 308 teeth with clearly visible periapical radiolucency and 308 without any periapical lesion. Three groups were generated: teeth with radiographic signs of caries (Group 1), teeth with coronal restoration (Group 2), and teeth with root canal filling (Group 3). The PRs were uploaded to the Diagnocat system for evaluation. The performance of the convolutional neural network in detecting PLs was assessed by its sensitivity, specificity, and positive and negative predictive values, as well as the diagnostic accuracy value. We investigated the possible effect of the palatoglossal air space (PGAS) on the evaluation of the AI tool. Results: DC identified periapical lesions in 240 (77.9%) cases out of the 308 teeth with PL and detected no PL in 68 (22.1%) teeth with PL. The AI-based system detected no PL in any of the groups without PL. The overall sensitivity, specificity, and diagnostic accuracy of DC were 0.78, 1.00, and 0.89, respectively. Considering these parameters for each group, Group 2 showed the highest values at 0.84, 1.00, and 0.95, respectively. Fisher’s Exact test showed that PGAS does not significantly affect (p = 1) the detection of PL in the upper teeth. The AI-based system showed lower probability values for detecting PL in the case of central incisors, wisdom teeth, and canines. The sensitivity and diagnostic accuracy of DC for detecting PL on canines showed lower values at 0.27 and 0.64, respectively. Conclusions: The CNN-based Diagnocat system can support the diagnosis of PL on PRs and serves as a decision-support tool during radiographic assessments.

The purpose of our study was to compare micromorphometric data obtained by cone-beam computed-tomography (CBCT) and microcomputed-tomography (micro-CT) of the augmented sinus and to evaluate the long-term stability of the bone gain achieved using BoneAlbumin. Sinus lifts, and after 6-months, healing bone-biopsy and implant placement were carried out. Specimens were analyzed by micro-CT. A total of 16 samples were collected from nine patients (mean age 54.7 ± 6.5 years). Pre-, postoperative, and 3-year control CBCT-data were registered to determine from where the biopsy samples were harvested. Micromorphometric variables were calculated from the micro-CT- and CBCT-data, and their correlation was determined by Spearman’s test. The volume of augmented bone was calculated at the time of implant placement and after 3 years. A positive correlation was found between bone-volume fraction, trabecular-separation, open-, and total-porosity, while a negative correlation was found between trabecular-thickness obtained from CBCT- and micro-CT-data (p < 0.05). Mean volumetric reduction of 39.28% (11.88–60.02%) was observed. Correlation of CBCT- and micro-CT-data suggested that micromorphometric analysis of CBCT reconstructions of the augmented sinuses provided reliable information on the microarchitecture of augmented bone. CBCT as a modality might be adequate in the analysis of bone quality in the augmented sinus. At the 3-year, control sinus grafts showed volumetric stability.

Introduction: The aim of this study was to compare the paranasal sinus volumes obtained by manual and semiautomatic imaging software programs using both CT and CBCT imaging. Methods: 121 computed tomography (CT) and 119 cone beam computed tomography (CBCT) examinations were selected from the databases of the authors’ institutes. The Digital Imaging and Communications in Medicine (DICOM) images were imported into 3-dimensonal imaging software, in which hand mode and semiautomatic tracing methods were used to measure the volumes of both maxillary sinuses and the sphenoid sinus. The determined volumetric means were compared to previously published averages. Results: Isometric CBCT-based volume determination results were closer to the real volume conditions, whereas the non-isometric CT-based volume measurements defined coherently lower volumes. By comparing the 2 volume measurement modes, the values gained from hand mode were closer to the literature data. Furthermore, CBCT-based image measurement results corresponded to the known averages. Conclusions: Our results suggest that CBCT images provide reliable volumetric information that can be depended on for artificial organ construction, and which may aid the guidance of the operator prior to or during the intervention.

Objectives: This study aimed to create a three-dimensional histological reconstruction through the AI-assisted classification of tissues and the alignment of serial sections. The secondary aim was to evaluate if the novel technique for histological reconstruction accurately replicated the trabecular microarchitecture of bone. This was performed by conducting micromorphometric measurements on the reconstruction and comparing the results obtained with those of microCT reconstructions. Methods: A bone biopsy sample was harvested upon re-entry following sinus floor augmentation. Following microCT scanning and histological processing, a modified version of the U-Net architecture was trained to categorize tissues on the sections. Detector-free local feature matching with transformers was used to create the histological reconstruction. The micromorphometric parameters were calculated using Bruker’s CTAn software (version 1.18.8.0, Bruker, Kontich, Belgium) for both histological and microCT datasets. Results: Correlation coefficients calculated between the micromorphometric parameters measured on the microCT and histological reconstruction suggest a strong linear relationship between the two with p-values of 0.777, 0.717, 0.705, 0.666, and 0.687 for BV/TV, BS/TV, Tb.Pf Tb.Th, and Tb.Sp, respectively. Bland–Altman and mountain plots suggest good agreement between BV/TV measurements on the two reconstruction methods. Conclusions: This novel method for three-dimensional histological reconstruction provides researchers with a tool that enables the assessment of accurate trabecular microarchitecture and histological information simultaneously.

Objective We aimed to find morphological properties of the hyoid bone, which are predominant among the patients diagnosed with obstructive sleep apnea (OSA), and compare them with healthy individuals. Methods A total of 67 cone-beam computed tomography (CBCT) image sequences of patients (44 males, 23 females) diagnosed with OSA and a total of 70 multislice computed tomography (MSCT) data of non-OSA patients (45 males, 25 females) were selected in this study. DICOM images were imported into InVivo 5.1.2 (Anatomage, San Jose, CA, USA) software. The position of the hyoid bone relative to the C3 and C4 cervical vertebrae, as well as its morphological type (B, V, U, H, D, HK-type) and its total volume were determined. Results The volumetric values of the hyoid bone of OSA patients (2384.49±682.073 mm³) were significantly (p<0.001) lower compared to the values derived from non-OSA patients (2952.96± 932.5 mm³). The difference was independent of gender, and volumetric values showed a strong significant (p<0.01) difference between male OSA and non-OSA (2709.18±608.05 mm³. 3157.87±926.5 mm³) and female OSA and non-OSA patients (1763±242.51 2584 mm³. 2584.12±840.21 mm³), as well. In the case of B and V-types, the volumetric values showed significant differences (p <0.05), when the OSA (2300,77±622 mm³; 2166±312 mm³) and non-OSA patients were compared (2823,48±780 mm³; 3216±463 mm³). Conclusion Our results suggest, that the volume of the hyoid bone might be a potential biological marker for OSA, especially in the case of B and V hyoid bone types.