Dento maxillo facial radiology最新文献

{"title":"Patient experience and movement frequency in young children during simulated ddMRI examinations.","authors":"A B Jensen, L H Matzen, J Christensen","doi":"10.1093/dmfr/twag049","DOIUrl":"https://doi.org/10.1093/dmfr/twag049","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the feasibility of dental-dedicated MRI (ddMRI), a non-ionizing imaging modality, for scanning children and to explore associations between age, sex, perceived experience, and movement during scanning.</p><p><strong>Methods: </strong>Thirty-seven children age 8-14 underwent a mock ddMRI examination simulating the scan of an impacted canine (5 pulse sequences, total scan time 12'27 min) using a 0.55 T scanner and a dedicated dental radiofrequency surface coil. Perceived patient experience was recorded using a 5-point visual analogue scale (VAS) before and after the examination. Movements of the head and body were quantified and characterized from video recordings of the scan. Multiple linear regression analyses were applied to evaluate associations between log-transformed movement and age, sex, and VAS scores. Separate regression models were applied for pre- and post-scan VAS. Significance level was set at 0.05.</p><p><strong>Results: </strong>Number of movements during scan time was registered for the head separately (mean/median 6.3/0, range 0-82) and for the body in total (62/34, 0-430). Increased head movement was significantly associated with younger age (34%/year, p = 0.010). Overall movement was significantly associated with sex (M > F, 24.8% more movement, p = 0.010). Pre-scan VAS (mean/median 1,73/2, range 1-3) decreased significantly with increasing age (0.21 points/year, p = 0.035). Post-scan VAS (1.95/2, 1-3) was significantly higher in girls than in boys (0.6 points/year, p = 0.031).</p><p><strong>Conclusion: </strong>Age and sex influence the child's experience and the number of movements during the mock scan. ddMRI may prove to be a feasible method for scanning children in a dental setting, offering a comfortable experience without ionizing radiation.</p><p><strong>Advances in knowledge: </strong>This paper is the first to demonstrate the applicability of ddMRI in a paediatric population, thereby laying the groundwork for future research into its use in diagnosis and treatment planning for children and adolescents.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148430116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical Contribution of CBCT to Pre-Intubation Nasal Passage Assessment in Pediatric Patients: A Retrospective Study.","authors":"Bilgun Çetin, Funda Arun","doi":"10.1093/dmfr/twag048","DOIUrl":"https://doi.org/10.1093/dmfr/twag048","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to investigate the relationship between nasal anatomical features identified on preoperative cone-beam computed tomography (CBCT) and nostril selection for nasotracheal intubation in pediatric patients undergoing general anesthesia.</p><p><strong>Materials and methods: </strong>CBCT scans of 40 patients aged 8-16 years were evaluated by an oral and maxillofacial radiologist, who measured the shortest bony distance at the inferior meatus, documented septal deviation, inferior turbinate hypertrophy, and dental pathologies, and recommended the nostril deemed most suitable for intubation. Anesthesiologists, blinded to imaging data, performed nasotracheal intubation based solely on clinical assessment. Agreement between radiologist and anesthesiologist choices was analyzed, and logistic regression and ROC analyses were performed to assess the predictive value of nasal diameter differences.</p><p><strong>Results: </strong>Moderate agreement was observed between the nostril recommended by the radiologist and the nostril selected by the anesthesiologist (Cohen's kappa = 0.497, p = 0.002). Nasal diameter differences significantly predicted radiologist nostril selection (OR = 9.433, 95% CI: 2.388-37.264, p = 0.001). ROC analysis demonstrated moderate discriminative ability (AUC = 0.750, p = 0.017). Anatomical variations, such as septal deviation and inferior turbinate hypertrophy, were common but did not significantly influence anesthesiologists' nostril selection.</p><p><strong>Conclusion: </strong>Preoperative CBCT scans, even when obtained for dental or surgical purposes, can provide valuable anatomical information to guide nostril selection in pediatric nasotracheal intubation. Evaluation of nasal diameter differences may improve preoperative planning, optimize nostril selection, and potentially reduce intubation-related complications.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148419578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-Based Detection of Proximal Caries Across Radiographic Modalities: A Systematic Review and Meta-Analysis.","authors":"Yiyang Wang, Di Fu, Ge Zhou, Ling Zou","doi":"10.1093/dmfr/twag046","DOIUrl":"https://doi.org/10.1093/dmfr/twag046","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate diagnostic performance of artificial intelligence (AI) models in detecting proximal caries across different radiographic modalities.</p><p><strong>Methods: </strong>We systematically searched in five electronic databases: Web of Science, PubMed, IEEE Xplore, ScienceDirect and CNKI. Essential study characteristics, AI models and their accuracy metrics for proximal caries detection were extracted. Methodological quality of eligible studies was assessed with QUADAS-2. Studies judged to be of adequate quality were retained for meta-analysis.</p><p><strong>Results: </strong>Twenty studies were included: fifteen employed bitewing radiographs, three utilized panoramic radiographs, and two adopted periapical radiographs. AI accuracy ranged from 28.5% to 100%. Due to the unavailability of essential 2 × 2 contingency data, only ten studies (six bitewing, three panoramic, and one periapical) were eligible for meta-analysis, yielding a pooled sensitivity of 76% (95% CI: 70%-80%), specificity of 94% (95% CI: 90%-96%), and Summary Receiver Operating Characteristic (SROC) AUC of 0.90 (95% CI: 0.87-0.92). Substantial heterogeneity was observed.</p><p><strong>Conclusion: </strong>AI models show promising diagnostic accuracy for proximal caries, with bitewing radiographs yielding slightly better performance than panoramic views. While AI holds potential as a clinical decision-support tool, high heterogeneity and limited external validation remain significant barriers to clinical translation. Future work should prioritize prospective, multicenter validation and open datasets to support clinical translation.</p><p><strong>Advances in knowledge: </strong>This systematic review covers studies up to October 2025, simultaneously evaluate AI performance of different modalities, enabling direct cross-modal comparison. By stratifying analyses by task type, dataset size, and imaging modality, this study identifies specific sources of performance heterogeneity that have previously confounded pooled estimates in the field. This review also establishes evidence thresholds for clinical implementation, serving as a methodological checkpoint to guide future research.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148390203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of misfits at the abutment-crown interface: comparison between stationary intraoral tomosynthesis and periapical radiography acquired with different vertical angulations.","authors":"Marcela Tarosso Réa, Thaísa Pinheiro Silva, Leandro Cardoso, Camila Tirapelli, Gustavo Machado Santaella, Christiano de Oliveira-Santos, William C Scarfe, Sergio Lins de-Azevedo-Vaz","doi":"10.1093/dmfr/twag013","DOIUrl":"10.1093/dmfr/twag013","url":null,"abstract":"<p><strong>Objectives: </strong>To compare the diagnostic accuracy of stationary intraoral tomosynthesis (s-IOT) with periapical radiography (PA) for misfit detection at the abutment-crown interface, across different misfit magnitudes and vertical angulations.</p><p><strong>Methods: </strong>Twenty prototype sets of maxillae and mandibles with implants placed in the maxillary central incisor region were used, and ceramic copings were fabricated. Misfits of 50, 100, and 150 μm were simulated by interposing 50-μm-thick polyester strips at the abutment-crown interface. The group without +simulated misfit had no strips. PA and s-IOT images were acquired using 3 different vertical X-ray tube angulations: perpendicular to the implant (0°), positioned inferiorly (-10°), and superiorly (+10°). Five oral radiologists evaluated 480 images using a 5-point scale. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were analysed using repeated measures ANOVA and Tukey's post-hoc test (α = 5%).</p><p><strong>Results: </strong>No significant differences were observed between PA and s-IOT (P > .05). AUC at 50 µm was significantly lower than 100 µm for all vertical angulations, and than 150 µm for -10° and +10° (P < .05); 100 µm was also lower than 150 µm for +10° (P < .05). +10° showed lower AUC than 0° and -10° at 50 µm, than 0° at 100 µm, and than -10° at 150 µm (P < .05). Sensitivity increased with misfit magnitude; 100 µm and 150 µm were higher than 50 µm for -10° and +10° (P < .05). +10° showed lower sensitivity than 0° at 50 µm and -10° at 150 µm (P < .05). Specificity varied only by vertical angulation; 0° showed the lowest values (P < .05).</p><p><strong>Conclusion: </strong>PA and s-IOT demonstrated comparable performance, +10° exhibited the lowest accuracy, and larger misfits were more easily detected.</p><p><strong>Advances in knowledge: </strong>s-IOT provides additional bucco-lingual information; however, PA demonstrated comparable diagnostic accuracy in detecting misfits at the abutment-crown interface while exposing patients to lower radiation doses. Additionally, when ideal parallelism cannot be achieved, directing the X-ray beam towards the implant apex, rather than the prosthetic crown, may optimize misfit detection.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"439-449"},"PeriodicalIF":4.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146219266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic multi-class classification of 3D relationships between the mandibular third molar and canal on cone-beam computed tomography using a geometry-aware network.","authors":"Hyomin Kim, Ji Yong Han, Su Yang, Jo-Eun Kim, Kyung-Hoe Huh, Sam-Sun Lee, Min-Suk Heo, Jeong Joon Han, Joo-Young Park, Won-Jin Yi","doi":"10.1093/dmfr/twag010","DOIUrl":"10.1093/dmfr/twag010","url":null,"abstract":"<p><strong>Objectives: </strong>Accurate 3D evaluation of the spatial relationship between the mandibular third molar (M3) and the mandibular canal (MC) is critical for assessing the risk of nerve injury during M3 extraction. The purpose of this study was to automatically classify the diverse spatial relationships between M3 and MC into 5 distinct categories based on the degree of anatomical contact or involvement as well as spatial proximity on cone-beam computed tomography (CBCT) images using a geometry-aware deep learning framework.</p><p><strong>Methods: </strong>The 3D spatial relationships between M3 and MC were categorized into 5 distinct types. The proposed framework consisted of 2 stages: first, the modified mAttUNet, an improved 3D U-Net architecture augmented with an attention mechanism was used for segmentation of M3 and MC; second, the proposed DenseAttNet was developed for multi-class classification. By incorporating dense attention mechanisms and signed distance map (SDM) inputs, the proposed network effectively captured both geometric and anatomical features, leading to more accurate and reliable multi-class classification.</p><p><strong>Results: </strong>The mAttUNet outperformed other conventional models, achieving the highest segmentation performance with average precision scores of 0.96 for MC and 0.84 for M3. The proposed DenseAttNet demonstrated superior and consistent performance, achieving an overall AUC of 0.97 and maintaining high accuracy across all 5 relationship types, effectively and reliably distinguishing the various spatial relationships between MC and M3.</p><p><strong>Conclusions: </strong>This automated and accurate classification of M3-MC spatial relationships offers valuable clinical utility, supporting enhanced risk evaluation and optimized surgical planning, and ultimately helping to reduce complications such as inferior alveolar nerve injury.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"460-476"},"PeriodicalIF":4.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147510482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantifying cross-site effect in AI-based dental age estimation: evidence from Brazilian panoramic radiographs.","authors":"Willian Oliveira, Matheus L Oliveira, Francisco Haiter Neto, Mariana Albuquerque Santos, Maria Luiza Dos Anjos Pontual, Ricardo V Beltrão, Andrea A Pontual, Flávia Maria M Ramos-Perez, Deborah Queiroz Freitas, Cleber Zanchettin","doi":"10.1093/dmfr/twag014","DOIUrl":"10.1093/dmfr/twag014","url":null,"abstract":"<p><strong>Objectives: </strong>To quantify cross-regional generalization of dental age-estimation models, identify practical strategies to improve their performance, and report uncertainty in a transparent manner.</p><p><strong>Methods: </strong>A total of 21 722 panoramic radiographs from 2 Brazilian regions were acquired using distinct equipment. A robust Inception-v4 model was evaluated under 4 scenarios: (1) training on Northeast data and testing on Southeast data; (2) fine-tuning using Southeast data only or both regions; (3) training from scratch on pooled data; (4) pooled training with augmentation. Model performance was assessed using mean absolute error (MAE), mean signed error (bias), R2, Bland-Altman analysis, and calibration metrics.</p><p><strong>Results: </strong>A marked performance drop was observed when the model trained on Northeast data was applied to Southeast radiographs (MAE 4.97 years vs 3.10 years in-region), with negative bias and wider Bland-Altman limits at older ages. Training with pooled regions and modest fine-tuning improved accuracy and calibration across both cohorts (MAE 3.24-3.69; R2 0.93-0.95). Data augmentation yielded only small additional improvements and did not eliminate large residual errors. Heatmaps highlighted clinically relevant anatomical structures commonly used by dental experts for age estimation.</p><p><strong>Conclusions: </strong>Cross-site and domain shifts significantly impact the performance of AI models for dental age estimation. Multi-regional training combined with light model adaptation provides robust, well-calibrated, and interpretable results across regions, whereas data augmentation alone has limited effectiveness. This study offers a 2-region benchmark, code, and data-access protocols to support reproducible evaluation and guide clinical deployment.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"477-486"},"PeriodicalIF":4.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146225892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of the generalizability of an artificial intelligence-based software for tomographic segmentation of posterior teeth-an external validation study.","authors":"Erielma Lomba Dias Julião, Gabriel Cunha Adiverci, Fernanda Bulhões Fagundes, André Ferreira Leite, Frederico Sampaio Neves, Deborah Queiroz de Freitas, Rocharles Cavalcante Fontenele, Reinhilde Jacobs, Francisco Haiter-Neto, Sergio Lins de-Azevedo-Vaz","doi":"10.1093/dmfr/twag018","DOIUrl":"10.1093/dmfr/twag018","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the generalizability of an artificial intelligence (AI)-based software for automated segmentation of posterior teeth in cone beam CT (CBCT) scans and to identify the variables that influence the need for refinement of automatic segmentations (AS).</p><p><strong>Methods: </strong>A total of 190 scans from 190 patients, acquired using 5 CBCT systems were imported into the Virtual Patient Creator (Relu, Leuven, Belgium) for AS. Two dental surgeons qualitatively assessed the segmentations of posterior teeth and refined those requiring correction. Manual segmentation (MS) of 20% of the sample was performed using Mimics software (Materialise, Leuven, Belgium). Performance was analyzed through voxel-by-voxel and surface-based comparisons, in addition to the evaluation of time efficiency. Associations between independent variables and the need for refinement were analyzed using mixed logistic regression (α = 5%).</p><p><strong>Results: </strong>Among the 1005 teeth evaluated, only 12.7% required refinement. Age and the presence of brackets were significant predictors (P < .001). The unexplained variability was attributed mainly to the patients, with minimal influence from the CBCT systems. AS showed agreement with refined segmentations (R-AI) (IoU: 0.93-0.96; DSC: 0.96-0.98; precision: 0.99-1.00; recall: 0.94-0.96; accuracy: 0.98-0.99; MAD: 0.05-0.07; RMSE: 0.06-0.14) and excellent performance compared to MS (IoU: 0.94; DSC: 0.97; precision: 0.98; recall: 0.95; accuracy: 0.98; MAD: 0.05; RMSE: 0.09). AS was more time-efficient (12 [AIQ: 5]) compared to R-AI (202 [AIQ: 334]) and MS (1726 [AIQ: 863]).</p><p><strong>Conclusion: </strong>The AI-based software demonstrated high accuracy and generalizability for automated segmentation of posterior teeth in CBCT scans.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"508-519"},"PeriodicalIF":4.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147662390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel cross-attentive network for classifying cervical metastatic lymph nodes on B- and D-mode ultrasound images in oral squamous cell carcinoma.","authors":"Yu-Ri Kim, Ji Yong Han, Su Yang, Jong Woo Kim, Kyung-Hoe Huh, Min-Suk Heo, Sam-Sun Lee, Won-Jin Yi, Jo-Eun Kim","doi":"10.1093/dmfr/twaf082","DOIUrl":"10.1093/dmfr/twaf082","url":null,"abstract":"<p><strong>Objectives: </strong>This study proposes a deep convolutional neural network model that integrates B-mode and D-mode ultrasound images to classify metastatic lymph nodes in patients with oral squamous cell carcinoma.</p><p><strong>Methods: </strong>A shared backbone network incorporating a cross-attention mechanism was employed to enhance feature-level interactions between dual-input ultrasound images. A total of 6 convolutional neural network architectures (VGG16, SqueezeNet, ResNet50, EfficientNet B3, ConvNext, and DenseNet121) were implemented within a shared backbone framework to investigate optimal performance. For each network, diagnostic performance was compared between dual-input and single-input ultrasound. In addition, model performance was evaluated against human observers with different levels of experience.</p><p><strong>Results: </strong>The model using DenseNet121 as a shared backbone with an integrated cross-attention layer (LNM-Net) achieved the highest classification accuracy (85.3%) when utilizing dual-input images, surpassing the diagnostic performance of residents. The cross-attention module improved feature fusion, reducing false positives by suppressing modality-specific noise.</p><p><strong>Conclusions: </strong>LNM-Net demonstrates strong potential as a clinical decision-support tool for preoperative lymph node metastasis assessment in oral squamous cell carcinoma. Despite current limitations such as dataset size and cross-institutional variability, the model offers a promising supplementary aid, particularly in settings with limited radiological expertise.</p><p><strong>Advances in knowledge: </strong>This study develops a novel cross-attentive network using dual-input B- and D-mode ultrasound images to classify metastatic lymph nodes in oral squamous cell carcinoma.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"450-459"},"PeriodicalIF":4.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145480573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cardiovascular events and mortality among patients and controls with calcified carotid artery atheromas on panoramic radiographs: a 10-year follow-up of the PAROKRANK study.","authors":"Hessamoddin Faghihian, Eva Levring Jäghagen, Jan Ahlqvist, Kåre Buhlin, Anna Norhammar, Ulf Näslund, Nils Gustafsson","doi":"10.1093/dmfr/twag016","DOIUrl":"10.1093/dmfr/twag016","url":null,"abstract":"<p><strong>Objectives: </strong>This study investigated the long-term risk of cardiovascular events and all-cause mortality among participants with calcified carotid artery atheroma (CCAA) on panoramic radiographs (PRs) in the Periodontitis and its Relation to Coronary Artery Disease (PAROKRANK) study.</p><p><strong>Methods: </strong>In the multicenter, multidisciplinary PAROKRANK study, 805 patients with a first myocardial infarction (MI) and 805 matched controls without MI were recruited at 17 hospitals in Sweden. At baseline, the participants were examined with PR, and in 737 patients and 739 controls, the carotid artery region was assessable. Calcified carotid artery atheromas were identified in 251 (34%) patients and 205 (28%) controls at baseline. The primary endpoint was defined as the first occurrence of all-cause mortality, non-fatal MI, non-fatal stroke, or hospitalization following heart failure after a mean follow-up of 10 years. The risks of cardiovascular events and death were evaluated using event survival analysis and regression models.</p><p><strong>Results: </strong>Participants with bilateral CCAAs, regardless of whether they were patients or controls, had significantly higher mortality and morbidity than those without CCAA (P < .001). The risk of cardiovascular events was increased in the presence of bilateral CCAAs among both controls (hazard ratio = 1.96 [95% CI, 1.21-3.16], P = .006) and patients (1.67 [1.15-2.43], P = .007).</p><p><strong>Conclusion: </strong>Bilateral CCAAs on PRs were an indicator of an increased risk of future cardiovascular events and early death among both controls and patients in the PAROKRANK study. Therefore, dentists can detect CCAA on PR and contribute to identifying individuals in need of medical attention and treatment of cardiovascular disease to prevent morbidity and early death.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"487-496"},"PeriodicalIF":4.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13317948/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147467352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"JADE: jawbone lesion diagnosis and decision supporting system.","authors":"Soroush Baseri Saadi, Jonas Ver Berne, Rocharles Cavalcante Fontenele, Peter Claes, Reinhilde Jacobs","doi":"10.1093/dmfr/twag017","DOIUrl":"10.1093/dmfr/twag017","url":null,"abstract":"<p><strong>Objectives: </strong>To develop and evaluate JADE, a proof-of-concept retrieval-augmented generation (RAG) diagnostic assistive system, designed to enhance large language model (LLM) reasoning for jawbone lesion assessment. This study examined whether RAG improves diagnostic accuracy and stability compared with standalone LLMs and ORAD, a supervised learning-based system.</p><p><strong>Methods: </strong>JADE was developed as a cloud-based RAG system integrating an expert-curated oral radiology database embedded using text-embedding-3-large and indexed in Qdrant Cloud. Structured clinical inputs were encoded as prioritized vector queries. Hybrid semantic and keyword-based retrieval appended relevant evidence to prompts for differential diagnosis generation across LLM backbones. Performance was evaluated in 25 validation cases and compared with GPT-5, Claude Sonnet 4.5, DeepSeek-R1, Gemini 2.5 Flash, their RAG configurations, and ORAD. Diagnostic accuracy was analyzed using Cochran's Q test, with post-hoc McNemar's tests and Bonferroni correction. Intra-model stability and response time were assessed.</p><p><strong>Results: </strong>RAG-GPT-5 achieved the highest diagnostic accuracy (20/25), followed by RAG-Claude Sonnet 4.5 (18/25), RAG-DeepSeek R1 (17/25), and RAG-Gemini 2.5 Flash (15/25). Standalone models achieved 9-13/25 correct diagnoses, ORAD achieved 17/25. No significant differences were observed among standalone models or RAG-based models and ORAD. A significant improvement was observed for GPT-5 when integrated with RAG (P = .002). RAG configurations showed higher intra-model stability, with RAG-GPT-5 achieving mean stability of 0.90 ± 0.11. Mean response times ranged from 3 to 10 s.</p><p><strong>Conclusions: </strong>JADE improved diagnostic accuracy and stability compared with standalone LLMs, underscoring value of RAG reasoning in jawbone lesion assessment and marking the first RAG application in dentomaxillofacial radiology.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"497-507"},"PeriodicalIF":4.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13317976/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147503462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}