Dento maxillo facial radiology最新文献

Objectives: This study aimed to evaluate the impact of 3D-printed mannequins on the training of predoctoral students.

Methods: Two 3D-printed training models were developed: a traditional model that simulates a sound adult patient and a customized model with pathological and physiological changes (impacted third molar and edentulous region). Students accomplished their pre-clinical training divided into a control group (CG, n = 23), which had access to the traditional model, and a test group (TG, n = 20), which had access to both models. Afterward, they performed a full mouth series on patients and filled out a perception questionnaire. Radiographs were evaluated for technical parameters. Descriptive statistics and the Mann-Whitney test were used to compare the groups.

Results: Students provided positive feedback regarding the use of 3D printing. The TG reported a more realistic training experience than the CG (P = .037). Both groups demonstrated good clinical performance (CG = 7.41; TG = 7.52), and no significant differences were observed between them.

Conclusions: 3D printing is an option for producing simulators for pre-clinical training in Oral Radiology, reducing student stress and increasing confidence during clinical care.

Objectives: This study aimed to compare the accuracy of cone-beam CT (CBCT) scanning and 3 different electronic apex locators (EALs) in the detection of simulated oblique root fractures (ORF) in different localizations.

Methods: The study utilised a total of 80 human maxillary incisors, which were categorised into two groups based on the location of the ORF (apical and middle third of the root) formed on the buccal side of the root surface. The measurement of the distance between the incisal edge and the intersection of the ORF with the root canal was conducted using a stereomicroscope. This measurement is referred to as the actual working length (AWL). Additionally, three EALs-Dentaport ZX, EndoRadar Pro, and Propex II-were utilised to determine the electronic working length (EWL). Furthermore, CBCT images were employed to assess the distance, known as the CBCT working length (CWL). The differences were determined by subtracting AWL from EWL and CWL.

Results: Based on the accuracy of the devices, there were no significant differences observed among Dentaport ZX, EndoRadar, Propex II, and CBCT measures in both the apical and middle third ORF groups, within the acceptable range of 0.5 and 1 mm.

Conclusions: The accuracy of Dentaport ZX, Propex II, and CBCT was higher in the middle third ORF group compared to the apical third ORF group, with a tolerance of 0.5 mm. However, there were no significant differences seen among the devices.

Objectives: In order to assist junior doctors in better diagnosing apical periodontitis (AP), an artificial intelligence AP grading system was developed based on deep learning (DL) and its reliability and accuracy were evaluated.

Methods: One hundred and twenty cone-beam computed tomography (CBCT) images were selected to construct a classification dataset with four categories, which were divided by CBCT periapical index (CBCTPAI), including normal periapical tissue, CBCTPAI 1-2, CBCTPAI 3-5, and young permanent teeth. Three classic algorithms (ResNet50/101/152) as well as one self-invented algorithm (PAINet) were compared with each other. PAINet were also compared with two recent Transformer-based models and three attention models. Their performance was evaluated by accuracy, precision, recall, balanced F score (F1-score), and the area under the macro-average receiver operating curve (AUC). Reliability was evaluated by Cohen's kappa to compare the consistency of model predicted labels with expert opinions.

Results: PAINet performed best among the four algorithms. The accuracy, precision, recall, F1-score, and AUC on the test set were 0.9333, 0.9415, 0.9333, 0.9336, and 0.9972, respectively. Cohen's kappa was 0.911, which represented almost perfect consistency.

Conclusions: PAINet can accurately distinguish between normal periapical tissues, CBCTPAI 1-2, CBCTPAI 3-5, and young permanent teeth. Its results were highly consistent with expert opinions. It can help junior doctors diagnose and score AP, reducing the burden. It can also be promoted in areas where experts are lacking to provide professional diagnostic opinions.

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.

Objectives: This study aimed to verify the accuracy of clinical protocols for the diagnosis of disc displacement (DD) compared with MRI, considering examiners' calibration.

Methods: PubMed, Cochrane (Central), Scopus, Web of Science, LILACS, Embase, Science Direct, Google Scholar, and DANS EASY Archive databases were searched. Two reviewers independently screened and selected the studies. A meta-analysis was conducted using the R Statistical software. Results are shown using sensitivity and specificity, and 95% confidence intervals.

Results: Of the 20 studies included in the systematic review, only three were classified as low risk of bias. Seventeen studies were included in the meta-analysis. Compared to MRI, clinical protocols showed overall sensitivity and specificity of 0.75 (0.63-0.83) and 0.73 (0.59-0.84) for DD diagnosis, respectively. For DD with reduction, sensitivity was 0.64 (0.48-0.77) and specificity was 0.72 (0.48-0.87). For DD without reduction, sensitivity was 0.58 (0.39-0.74) and specificity 0.93 (0.83-0.97). Only 8 studies reported examiner calibration when performing clinical and/or MRI evaluation; nevertheless, calibration showed a tendency to improve the diagnosis of DD.

Conclusion: The sensitivity and specificity of clinical protocols in the diagnosis of DD are slightly below the recommended values, as well as the studies lack calibration of clinical and MRI examiners. Examiner calibration seems to improve the diagnosis of DD.

Objectives: To determine the most distinctive quantitative radiomorphometric parameter(s) for the detection of MRONJ-affected bone changes in panoramic radiography (PR) and cone-beam CT (CBCT).

Methods: PR and sagittal CBCT slices of 24 MRONJ patients and 22 healthy controls were used for the measurements of mandibular cortical thickness (MCT), fractal dimension (FD), lacunarity, mean gray value (MGV), bone area fraction (BA/TA), trabecular thickness (Tb.Th), trabecular separation (Tb.Sp), trabecular number (Tb.N). MCT was measured in the mental foramen region. While FD and lacunarity were measured on mandibular trabecular and cortical regions-of-interest (ROIs), the remaining parameters were measured on trabecular ROIs. The independent samples t-test was used to compare the measurements between the MRONJ and control groups for both imaging modalities (P = .05).

Results: MCT was the only parameter that differentiated MRONJ-affected bone in both PR and CBCT (P < .05). None of the remaining parameters revealed any difference for MRONJ-affected bone in CBCT (P > .05). FD, lacunarity, MGV, BA/TA, and Tb.Sp could distinguish MRONJ-affected trabecular bone in PR (P < .05). The correspondent ROI for both imaging methods that was reliable for detecting MRONJ-affected bone was the trabecular bone distal to the mental foramen above the inferior alveolar canal (ROI-3).

Conclusions: MCT is a reliable parameter for the discrimination of MRONJ-affected bone in both PR and CBCT images. PR may be used to detect MRONJ-affected trabecular bone using FD, lacunarity, MGV, BA/TA, and Tb.Sp measurements as well.

Objectives: This study evaluated the performance of four large language model (LLM)-based chatbots by comparing their test results with those of dental students on an oral and maxillofacial radiology examination.

Methods: ChatGPT, ChatGPT Plus, Bard, and Bing Chat were tested on 52 questions from regular dental college examinations. These questions were categorized into three educational content areas: basic knowledge, imaging and equipment, and image interpretation. They were also classified as multiple-choice questions (MCQs) and short-answer questions (SAQs). The accuracy rates of the chatbots were compared with the performance of students, and further analysis was conducted based on the educational content and question type.

Results: The students' overall accuracy rate was 81.2%, while that of the chatbots varied: 50.0% for ChatGPT, 65.4% for ChatGPT Plus, 50.0% for Bard, and 63.5% for Bing Chat. ChatGPT Plus achieved a higher accuracy rate for basic knowledge than the students (93.8% vs. 78.7%). However, all chatbots performed poorly in image interpretation, with accuracy rates below 35.0%. All chatbots scored less than 60.0% on MCQs, but performed better on SAQs.

Conclusions: The performance of chatbots in oral and maxillofacial radiology was unsatisfactory. Further training using specific, relevant data derived solely from reliable sources is required. Additionally, the validity of these chatbots' responses must be meticulously verified.

Objectives: To elucidate the relationships between the maximum standardized uptake value (SUVmax) of alveolar bone and those of lymph nodes (LNs) around the neck on 18F-fluoro-2-deoxy-D-glucose (18F-FDG) positron emission tomography (PET).

Methods: The SUVmax values of alveolar bone and of level IA, level IB, and level IIA LNs of 174 patients, including those with and without active odontogenic inflammation, on PET/CT performed for a health check were retrospectively evaluated. The upper and lower jaws were divided into four blocks (right maxilla, left maxilla, right mandible, and left mandible). The SUVmax values of each block and of the LNs were calculated. The differences in the SUVmax of each LN level between patients with and without odontogenic inflammation, and the relationship between the SUVmax values of alveolar bone and of the LNs were analysed statistically.

Results: Significant differences in SUVmax values of bilateral level IB and IIA LNs were found between patients with and without odontogenic inflammation (Mann-Whitney U test: right level IB, P = .008; left level IB, P = .006; right level IIA, P < .001; left level IIA, P = .002), but not in bilateral level IA LNs (Mann-Whitney U test: right level IA, P = .432; left level IA, P = .549). The inflammatory site with the highest SUVmax in level IB LNs was the ipsilateral mandible (multivariate analysis: right, beta = 0.398, P < .001; left, beta = 0.472, P < .001), and the highest SUVmax in level IIA LNs was the ipsilateral maxilla (multivariate analysis: right, beta = 0.223, P = .002; left, beta = 0.391, P < .001).

Conclusions: The SUVmax values of level IB and IIA LNs were associated with a tendency towards a higher SUVmax value of alveolar bone on 18F-FDG-PET.

Objective: This study aims to develop a facial vascular enhancement imaging system and analyze vascular distribution in the facial region to assess its potential in preventing unintended intravascular injections during cosmetic facial filling procedures.

Methods: A facial vascular enhancement imaging system based on optical detection technology was designed, and volunteers were recruited. The system was utilized to detect and analyze vascular distribution in various anatomical regions of the faces. The vascular visualization-enhanced (VVE) images generated by the system were compared with visible light images to validate the vascular visualization capability of the system. Additionally, the reliability of vascular visualization was assessed by comparing the observed vascular patterns in the VVE images with those in near-infrared light images.

Results: Thirty volunteers were recruited. The VVE images produced by the system demonstrated a significant capacity to identify vascular morphology and yielded a higher vessel count compared to visible light images, particularly in the frontal, orbital, perioral, mental, temporal, cheek, and parotid masseter regions (P < .05). The temporal region exhibited the highest vascular density, followed by the cheek region and then the frontal region. Reliability analysis of vascular visualization enhancement indicated that the system's imaging of facial vasculature not only demonstrated reliability but also enhanced physicians' visual perception.

Conclusion: Blood vessel distribution varies across facial regions. The facial vascular enhancement imaging system facilitates real-time and clear visualization of facial vasculature, offering immediate visual feedback to surgeons. This innovation holds promise for enhancing the safety and effectiveness of facial filling procedures.

Objectives: To assess the performance of deep learning (DL) in the detection, classification, and segmentation of maxillary sinus diseases.

Methods: An electronic search was conducted by two reviewers on databases including PubMed, Scopus, Cochrane, and IEEE. All English papers published no later than February 7, 2024, were evaluated. Studies related to DL for diagnosing maxillary sinus diseases were also searched in journals manually.

Results: Fourteen of 1167 studies were eligible according to the inclusion criteria. All studies trained DL models based on radiographic images. Six studies applied to detection tasks, one focused on classification, two segmented lesions, and five studies made a combination of two types of DL models. The accuracy of the DL algorithms ranged from 75.7% to 99.7%, and the area under curves (AUC) varied between 0.7 and 0.997.

Conclusion: DL can accurately deal with the tasks of diagnosing maxillary sinus diseases. Students, residents, and dentists could be assisted by DL algorithms to diagnose and make rational decisions on implant treatment related to maxillary sinuses.