Dento maxillo facial radiology最新文献

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 in vitro study evaluated the diagnostic potential of short-wave infrared reflection (SWIRR) at 1050 and 1550 nm for proximal caries detection from the occlusal, buccal and lingual surfaces of posterior teeth under clinically relevant conditions. Bitewing radiography (BWR) was the alternative index test and micro-computed tomography (μCT) the reference standard.

Methods: 250 proximal surfaces of extracted human teeth were examined using SWIRR at 1050 and 1550 nm and BWR. SWIRR, BWR and μCT findings were evaluated twice by two trained examiners. SWIRR images were evaluated from occlusal and trilateral (occlusal, buccal and lingual combined) views. Sensitivity, specificity and AUC were calculated. Reliability assessment was performed using κ statistics.

Results: SWIRR (1050 nm) showed sensitivity of 0.44 for occlusal and 0.55 for trilateral assessment, paired with specificity of 0.96 and 0.90, whereas SWIRR (1550 nm) showed sensitivity of 0.73 and 0.85 paired with specificity of 0.76 and 0.59. Compared to occlusal view, trilateral SWIRR view revealed ≈10% higher sensitivity and lower specificity. BWR revealed lowest sensitivity (0.30) and highest specificity (0.99). Over-and underestimation of caries demonstrated opposite trends: from 1050-1550 nm, overestimation of trilateral SWIRR increased (0.08-0.29), while underestimation decreased (0.15-0.06).

Conclusion: Trilateral SWIRR has higher sensitivity and lower specificity for proximal caries, than occlusal SWIRR. 1050 nm are more suitable for trilateral SWIRR and 1550 nm for occlusal examinations. A combination of SWIRR at 1050 and 1550 nm may exhibit a balanced sensitivity and specificity for proximal caries.

Objectives: To identify if supplemental preoperative CBCT imaging could improve outcomes related to endodontic access cavity preparation, using 3D-printed maxillary first molars (M1Ms) in a rigorously simulated, controlled human analogue study.

Methods: 18 operators with three experience-levels took part in two simulated clinical sessions, one with and one without the availability of CBCT imaging, in a randomised order and with an intervening 8-week washout period. Operators attempted location of all four root canals in each of three custom-made M1Ms (two non-complex and one complex mesiobuccal canal anatomy). Primary outcome was tooth volume removed. Secondary outcomes were linear cavity dimensions, canals located, and procedural time. Operator confidence and 'helpfulness' of available imaging were recorded. Statistical analysis of data included: paired t-tests, Fishers Exact test, linear mixed effect modelling and Mann-Whitney U test, with an alpha level of .05 for all.

Results: When supplemental preoperative CBCT was available, there were significant reductions in volume of the access cavity and procedural times, with significantly increased mesiobuccal-2 (MB2) canal location, but only for teeth with non-complex anatomies and for more experienced operators. Linear mixed-effect modelling identified image type and operator experience as significant predictors of tooth volume removed and procedural time. There was significantly lower confidence in canal location and perceived 'helpfulness" (all experience groups) when conventional imaging only was used compared with when CBCT was available.

Conclusions: Supplemental preoperative CBCT had several beneficial impacts on access cavity preparation, although this only applied to teeth with non-complex anatomy and for more experienced operators.

Objectives: Lymph node metastasis (LNM) is a pivotal determinant that influences the treatment strategies and prognosis for oropharyngeal squamous cell carcinoma (OPSCC) patients. This study aims to establish and verify a deep learning (DL) radiomics model for the prediction of LNM in OPSCCs using contrast-enhanced computed tomography (CECT).

Methods: A retrospective analysis included 279 OPSCC patients from three institutions. CECT images were used for handcrafted (HCR) and DL feature extraction. Dimensionality reduction for HCR features used recursive feature elimination and least absolute shrinkage and selection operator algorithms, whereas DL feature dimensionality reduction used variance-threshold and recursive feature elimination algorithms. Radiomics signatures were constructed using support vector machine, decision tree, random forest, k-nearest neighbor, gaussian naive bayes classifiers and light gradient boosting machine. A combined model was then constructed using the screened DL, HCR, and clinical features. The area under the receiver operating characteristic curve (AUC) served to quantify the model's performance, and calibration curves were utilized to assess its calibration.

Results: The combined model exhibited robust performance, achieving AUC values of 0.909 (95% CI: 0.861-0.957) in the training cohort, 0.884 (95% CI: 0.800-0.968) in the internal validation cohort, and 0.865 (95% CI: 0.791-0.939) in the external validation cohort. It outperformed both the clinical model and best-performing radiomics model. Moreover, calibration was deemed satisfactory.

Conclusions: The combined model based on CECT demonstrates the potential to predict LNM in OPSCCs preoperatively, offering a valuable tool for more precise and tailored treatment strategies.

Advances in knowledge: This study presents a novel combined model integrating clinical factors with deep learning radiomics, significantly enhancing preoperative LNM prediction in OPSCC.

Objectives: To evaluate the antimicrobial efficacy of white vinegar, acetic acid and peracetic acid on photostimulable phosphor (PSP) plates disinfection, and to assess the disinfectant influence on the radiographic quality.

Methods: Eight PSP plates (Express system) were contaminated with Streptococcus mutans and Candida albicans. These plates were wiped with tissues without any substance, with white vinegar, acetic acid, and peracetic acid, followed by an agar imprint. Number of microbial colonies formed was recorded. Afterwards, the quality of radiographs was tested using the more efficient disinfectant. Before disinfection and after every five disinfections, two radiographs of an acrylic-block and two radiographs of an aluminum step-wedge were acquired for each plate. Density, noise, uniformity, and contrast were analyzed. Three oral radiologists evaluated the images for the presence of artifacts. One-way Analysis of Variance compared changes on gray values among the disinfections (α = 0.05). Intra- and inter-examiner agreement for the presence of artifacts was calculated by weighted Kappa.

Results: Peracetic acid was the only one that eliminated both microorganisms. Density and uniformity decreased after 100 disinfections, and contrast changed without a pattern in the course of disinfections (P ≤ 0.05). Small artifacts were observed after 30 disinfections. Intra- and inter-examiner agreements were almost perfect.

Conclusions: Disinfection with peracetic acid eliminated both microorganisms. However, it also affected density, uniformity and contrast of radiographs, and led to the formation of small artifacts.

Objectives: The purpose of this study was to generate radiographs including dentigerous cysts by applying the latest generative adversarial network (GAN; StyleGAN3) to panoramic radiography.

Methods: A total of 459 cystic lesions were selected, and 409 images were randomly assigned as training data and 50 images as test data. StyleGAN3 training was performed for 500 000 images. Fifty generated images were objectively evaluated by comparing them with 50 real images according to four metrics: Fréchet inception distance (FID), kernel inception distance (KID), precision and recall, and inception score (IS). A subjective evaluation of the generated images was performed by three specialists who compared them with the real images in a visual Turing test.

Results: The results of the metrics were as follows: FID, 199.28; KID, 0.14; precision, 0.0047; recall, 0.00; and IS, 2.48. The overall results of the visual Turing test were 82.3%. No significant difference was found in the human scoring of root resorption.

Conclusions: The images generated by StyleGAN3 were of such high quality that specialists could not distinguish them from the real images.

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.