{"title":"Micronucleus Formation in Oral Mucosal Cells Following Dental X-ray Exposure: A Systematic Review and Meta-analysis.","authors":"Yaxin Wang, Rozita Hassan, Liyana Ghazali, Shanshan Cai, Anani Aila Bt Mat Zin, Sanhui Yang, Linxian Zeng","doi":"10.1093/dmfr/twaf075","DOIUrl":"https://doi.org/10.1093/dmfr/twaf075","url":null,"abstract":"<p><strong>Background: </strong>Radiographic imaging is essential in dental diagnostics, yet concerns persist regarding its genotoxic impact. While digital advancements have reduced radiation doses, the effects of X-ray exposure on oral mucosal cells remain debated. This study systematically reviews and quantitatively analyzes the effects of X-ray exposure on micronucleus (MN) formation in oral epithelial cells, examining potential age-related variations.</p><p><strong>Methods: </strong>A thorough literature review was performed across PubMed, Web of Science, EBSCO, and Scopus (updated to November 2024), adhering to PRISMA criteria. Eligible studies examined cytogenetic changes in oral epithelial cells after X-ray exposure in healthy individuals. Data extraction covered study design, imaging modality, radiation dose, micronucleus frequency, and statistical methods. Risk of bias was assessed using a modified EPHPP tool. A random-effects model synthesized micronucleus frequency changes, and Fisher's Z-transformation analyzed age correlations.</p><p><strong>Results: </strong>Eighteen studies met the inclusion criteria, with 16 centered on panoramic imaging and two examining a combination of CBCT and lateral cephalometric X-rays. Meta-analysis confirmed a significant increase in micronucleus frequency post-exposure (SMD = 0.30, 95% CI: 0.07-0.52, p = 0.01), indicating genotoxic effects. However, age showed a weak correlation with micronucleus formation (r = 0.149, 95% CI: -0.009 to 0.3, p = 0.065).</p><p><strong>Conclusions: </strong>X-ray exposure induces measurable genotoxic damage in oral epithelial cells, though age-related effects remain inconclusive. Adhering to the ALARA principle is crucial to minimize unnecessary radiation. Future studies should employ larger cohorts and refined biomarkers to enhance risk assessment.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145250322","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":"-Diagnosis of Nasopalatine Duct and Nasopalatine Duct Cyst in CBCT Images: A Radiomics-Based Machine Learning Approach.","authors":"H Duyan Yüksel, B Büyük, B Evlice","doi":"10.1093/dmfr/twaf076","DOIUrl":"https://doi.org/10.1093/dmfr/twaf076","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to evaluate the diagnostic performance of machine learning (ML) algorithms based on radiomic features extracted from cone-beam computed tomography (CBCT) images in differentiating the nasopalatine duct (NPD) from the nasopalatine duct cyst (NPDC), and to compare their performance with that of a dentomaxillofacial radiologist.</p><p><strong>Methods: </strong>CBCT scans from 101 histopathologically confirmed NPDC cases and 101 age- and sex-matched controls with normal NPD were retrospectively analyzed. Manual segmentation was performed to extract 1037 radiomic features (original, Laplacian of Gaussian, and wavelet-transformed). After dimensionality reduction, five ML models (support vector machine (SVM), random forest (RF), decision tree (DT), k-nearest neighbors (KNN), and logistic regression (LR)) were trained using 5-fold cross-validation. Performance was evaluated using the area under the ROC curve (AUC), sensitivity, specificity, precision, recall, and F1-score.</p><p><strong>Results: </strong>Among the 11 optimal features identified through feature selection, large area high gray level emphasis and zone variance from the gray level size zone matrix (GLSZM) class were the most prominent. SVM achieved the highest performance in the test set (AUC and all other metrics = 1.00). The radiologist showed comparable but slightly lower overall performance than SVM (AUC = 0.94, with other metrics between 0.93 and 0.95).</p><p><strong>Conclusions: </strong>Machine learning algorithms based on radiomic features extracted from CBCT images can effectively differentiate NPD from NPDC. Unlike standard visual interpretation, this approach analyzes quantitative image features via mathematical models, yielding objective and reproducible results. It may serve as a non-invasive, complementary decision-support tool, particularly in diagnostically challenging cases.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145250319","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}
Han-Gyeol Yeom, Hyun-Gab Kim, Yeon-Tae Kim, Kyung-Hoe Huh, Won-Jin Yi, Min-Suk Heo, Sam-Sun Lee, Jo-Eun Kim
{"title":"Assessment of Vertical Magnification Ratios in Digital Panoramic Radiography Using Phantoms: Evaluation of DICOM Metadata and Calibration Consistency.","authors":"Han-Gyeol Yeom, Hyun-Gab Kim, Yeon-Tae Kim, Kyung-Hoe Huh, Won-Jin Yi, Min-Suk Heo, Sam-Sun Lee, Jo-Eun Kim","doi":"10.1093/dmfr/twaf074","DOIUrl":"https://doi.org/10.1093/dmfr/twaf074","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to investigate the vertical magnification ratios of various digital panoramic radiography devices and assess their consistency. It also examined the relationship between magnification ratios and Digital Imaging and Communications in Medicine (DICOM) header information to determine the potential use of key metadata in inferring or standardizing magnification corrections.</p><p><strong>Methods: </strong>A ball phantom with metal spheres and an implant phantom were used to assess vertical magnification ratios. Eleven panoramic radiography systems were tested, and three DICOM tags-pixel spacing, imager pixel spacing, and aspect ratio-were analyzed. Three specialists measured phantom lengths in randomized DICOM images using PACS software, repeating measurements after 4 weeks. Magnification ratios were calculated by averaging 24 measurements per sample and comparing them to actual lengths.</p><p><strong>Results: </strong>Intra- and interobserver reliability were high (ICC > 0.99). Most devices showed magnification ratios of 0.95-1.08, whereas those of devices 3 and 9 ranged from 1.21 to 1.30. Although some magnification ratios, which were used for system-based calibration, could be indirectly inferred by dividing the imager pixel spacing value by the pixel spacing value when both values were precisely recorded, no DICOM headers explicitly provided magnification ratios.</p><p><strong>Conclusions: </strong>This study demonstrated that many digital panoramic radiography devices apply software-based corrections to achieve a vertical magnification ratio close to 1.0; however, inconsistencies remain across different systems. Measurement accuracy and clinical reliability can be enhanced by standardization of magnification correction methods and improved documentation in product specifications and DICOM headers, which is clinically relevant for increasing the accuracy of vertical measurements in procedures such as dental implant planning and thereby enhancing treatment predictability and patient safety.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145231828","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}
Lucas Machado Maracci, Gabriela Salatino Liedke, Rubens Spin-Neto
{"title":"Detection of degenerative temporomandibular changes using cone beam CT: a scoping review on technical parameters, evaluation criteria, and calibration.","authors":"Lucas Machado Maracci, Gabriela Salatino Liedke, Rubens Spin-Neto","doi":"10.1093/dmfr/twaf056","DOIUrl":"10.1093/dmfr/twaf056","url":null,"abstract":"<p><p>To provide an overview of how Cone Beam Computed Tomography (CBCT) has been used in the assessment of degenerative changes of the temporomandibular joint (TMJ), with emphasis on image acquisition protocols, examiner calibration, and the criteria used for assessing and diagnosing TMJ structures. Searches were performed on PubMed, Embase, Scopus, and Web of Science databases on March 5, 2025. In vivo studies with a sample of adult individuals and which used CBCT to evaluate degenerative changes were included. Studies that did not discriminate voxel size, kV, or mA parameters and those without information on the degenerative changes assessed or the criteria used for image evaluation were excluded. Twenty-four studies were included. A wide variation in CBCT acquisition parameters was verified (voxel size varied from 0.076 mm to 0.3 mm, kV values were between 70 and 120, and mA between 3 and 38) which appear not to influence the detection of degenerative changes. The diverse criteria for CBCT assessment employed, many of which not validated, demonstrate a lack of standardization in TMJ assessment across the scientific literature. Furthermore, examiner calibration was not reported by 14 studies. Voxel size does not seem to significantly influence the detection of degenerative changes. The studies show a lack of examiner calibration, as well as inconsistencies in the standardization of acquisition parameters and evaluation protocols for CBCT imaging of the TMJ. Standardized and validated criteria are needed to enhance diagnostic accuracy and comparability among studies.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"517-528"},"PeriodicalIF":2.9,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144599690","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}
Joon Ha Park, Mustafa Hamimi, Joanne Jung Eun Choi, Carlos Marcelo S Figueredo, Andrew B Cameron
{"title":"Comparisons of artificial intelligence automated segmentation techniques to manual segmentation techniques of the maxilla and maxillary sinus for CT or cone-beam CT scans-a systematic review.","authors":"Joon Ha Park, Mustafa Hamimi, Joanne Jung Eun Choi, Carlos Marcelo S Figueredo, Andrew B Cameron","doi":"10.1093/dmfr/twaf042","DOIUrl":"10.1093/dmfr/twaf042","url":null,"abstract":"<p><strong>Objectives: </strong>Accurate segmentation of the maxillary sinus from medical images is essential for diagnostic purposes and surgical planning. Manual segmentation of the maxillary sinus, while the gold standard, is time consuming and requires adequate training. To overcome this problem, artificial intelligence (AI) enabled automatic segmentation software's developed. The purpose of this review is to systematically analyse the current literature to investigate the accuracy and efficiency of automatic segmentation techniques of the maxillary sinus to manual segmentation.</p><p><strong>Methods: </strong>A systematic approach to perform a thorough analysis of the existing literature using PRISMA guidelines. Data for this study was obtained from Pubmed, Medline, Embase, and Google Scholar databases. The inclusion and exclusion eligibility criteria were used to shortlist relevant studies. The sample size, anatomical structures segmented, experience of operators, type of manual segmentation software used, type of automatic segmentation software used, statistical comparative method used, and length of time of segmentation were analysed.</p><p><strong>Results: </strong>This systematic review presents 10 studies that compared the accuracy and efficiency of automatic segmentation of the maxillary sinus to manual segmentation. All the studies included in this study were found to have a low risk of bias. Samples sizes ranged from 3 to 144, a variety of operators were used to manually segment the cone-beam computed tomography (CBCT) and segmentation was made primarily to 3D slicer and Mimics software. The comparison was primarily made to Unet architecture softwares, with the dice-coefficient being the primary means of comparison.</p><p><strong>Conclusions: </strong>This systematic review showed that automatic segmentation technique was consistently faster than manual segmentation techniques and over 90% accurate when compared to the gold standard of manual segmentation.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"529-539"},"PeriodicalIF":2.9,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12474565/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144215238","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}
Chaeyeon Lee, Jae-Hoon Lee, Kug Jin Jeon, Jong-Ki Huh, Hye-Sun Kim, Young Hoon Ryu, Tae Joo Jeon, Jae-Young Kim
{"title":"Quantitative Assessment of Condylar Bone Changes in Osteoarthritis Patients Using Single-photon emission computed tomography/computed tomography and Magnetic resonance imaging.","authors":"Chaeyeon Lee, Jae-Hoon Lee, Kug Jin Jeon, Jong-Ki Huh, Hye-Sun Kim, Young Hoon Ryu, Tae Joo Jeon, Jae-Young Kim","doi":"10.1093/dmfr/twaf070","DOIUrl":"https://doi.org/10.1093/dmfr/twaf070","url":null,"abstract":"<p><strong>Objectives: </strong>This retrospective study aimed to investigate and evaluate the signal intensity ratio (SIR) on magnetic resonance imaging (MRI) and maximum Standard Uptake Value (SUVmax) and Hounsfield Unit (HU) values on Single-photon emission computed tomography/computed tomography (SPECT/CT) in relation to the diagnosis of Temporomandibular joint osteoarthritis (TMJ OA).</p><p><strong>Methods: </strong>Ninety-six TMJ from 63 patients who took SPECT/CT and MRI between January 2017 and September 2023were included. SUVmax and HUmedulla of TMJ were measured. SIR was measured and calculated based on the ratio of magnetic signal intensity of the condyle and cerebral cortex on proton density weight image (PDWI) and T2-weighted image (WI).</p><p><strong>Results: </strong>The TMJ OA group showed high SUV max (7.98 ± 4.09; median: 6.5), compared to the normal (3.21 ± 0.76; median: 3.1) with significant difference (p < 0.001). A significant difference was also observed in the HU, with the TMJ OA (457.14 ± 247.48) versus normal (296.91 ± 117.51) (p = 0.001). Both SIR measured by PDWI and T2-WI were lower in the TMJ OA (0.89 ± 0.28; median: 0.9 and 1.19 ± 0.26; median: 1.2) compared to the normal (1.23 ± 0.23; median: 1.2 and 1.00 ± 0.23; median: 1.0) with significant difference (p < 0.001).</p><p><strong>Conclusions: </strong>This study can provide the basis that SIR can be helpful in diagnosis in patients clinically suspected of having OA.</p><p><strong>Advances in knowledge: </strong>This study is the first to quantitatively evaluate condylar bone changes in TMJ OA by combining SUVmax from SPECT/CT, HU from CT, and SIR from MRI within the same cohort. This integrated imaging approach may contribute to more objective and reliable diagnosis of TMJ osteoarthritis.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145191430","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":"Influence of tube current, sharpening filters and metal artifact reducing filters on the diagnosis in the cone-beam computed tomographic diagnosis of carious lesion.","authors":"Lorena Esteves Silveira, Larissa Pereira Nunes, Lizandra Gonzaga Rodrigues, Mariana Carvalho, Isabella Caroline Fonseca Tavares, Thaygla Cristhina de Araújo Gandra, Diogo de Azevedo Miranda, Flávio Ricardo Manzi","doi":"10.1093/dmfr/twaf073","DOIUrl":"https://doi.org/10.1093/dmfr/twaf073","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate artifact-reducing filters as a means to optimize and ensure the accuracy of carious lesion diagnosis testing two experimental models (presence and absence of adjacent metallic objects).</p><p><strong>Methods: </strong>Fifty molar teeth were used, randomly divided into 5 groups (n = 10): G1-Sound teeth; G2-Carious teeth; G3-teeth with Class I cavity preparation restored with resin (Cl I + R); G4-Cl I + R with the use of a hyperdense lining material; and G5-Cl I + R with the use of a hypodense lining material. The Carestream CS 9600 tomograph was used, testing two experimental models (presence and absence of adjacent metallic objects), with tube voltages of 100 kV and 120 kV, voxel sizes of 75 and 150 µm, and applying the MAR filter. Three examiners scored according to the Likert Scale. The Fleiss' Kappa test was performed to analyze intra- and inter-examiner agreement, in addition to Cochran's Q test with a significance level of 5%, to compare the parameters of tube voltage, voxel size, and MAR filter.</p><p><strong>Results: </strong>The Fleiss' Kappa test showed excellent inter- and intra-observer agreement for all groups. All modalities of tube voltage, voxel size, and MAR filter showed very high accuracy, sensitivity, and specificity, providing diagnoses consistent with reality, achieving 99% accuracy when the model did not present adjacent metallic objects to the tooth, and 95% accuracy when such objects were present.</p><p><strong>Conclusions: </strong>It is concluded that, although CBCT is not the exam of choice for diagnosing carious lesions, optimizing acquisition parameters and using MAR filters allows a reliable concomitant diagnosis in exams already indicated for other purposes.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145191289","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}
S T Gokdeniz, A Buyuksungur, M E Kolsuz, I S Bayrakdar, K Orhan
{"title":"Detection of External Root Resorption in Periapical Radiographs Using YOLO-Based Deep Learning Model.","authors":"S T Gokdeniz, A Buyuksungur, M E Kolsuz, I S Bayrakdar, K Orhan","doi":"10.1093/dmfr/twaf072","DOIUrl":"https://doi.org/10.1093/dmfr/twaf072","url":null,"abstract":"<p><strong>Objectives: </strong>External root resorption is a destructive process that usually develops without any symptoms and, when diagnosed, can lead to tooth extraction because it causes serious tooth tissue loss. Therefore, it is aimed to develop artificial intelligence algorithms that can assist in the diagnosis of external root resorption.</p><p><strong>Methods: </strong>110 extracted teeth were demineralized by applying 40% nitric acid solution for 8 hours, 8% sodium hypochlorite for 10 minutes and then distilled water washing procedure. The prepared teeth were placed on a radioconjugate phantom model and imaged. The data set obtained from the teeth used in the study consists of a total of 584 periapical radiographs. YOLOv5x-cls and YOLOv5x-seg models were used to detect external root resorption.</p><p><strong>Results: </strong>The F1 score value of the YOLOv5x-cls model used for calcification of external root resorption was found to be 1.0, indicating that the model has a high success rate during the testing phase. In the YOLOv5x-seg model used for segmentation of external root resorption, the F1 score values were found to be 0.8593. This value is an indication that the model is working effectively during the testing phase. It has also been determined that the classification is more successful than the segmentation model.</p><p><strong>Conclusion: </strong>In this study, artificial intelligence algorithms were used in the radiological evaluation of teeth with chemical external root resorption using a phantom model compatible with jawbone radiopacity. High success rates have been achieved in the detection of external root resorption areas with artificial intelligence.</p><p><strong>Advances in knowledge: </strong>This study presents an innovative approach to detecting external root resorption using artificial intelligence. In addition, the reliability of the study was increased by using the radioconjugate phantom model.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174244","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}
Kyubaek Yoon, Yiseul Choi, Myoungho Lee, Jaeyeon Kim, Jun-Young Kim, Jin-Woo Kim, Jongeun Choi, Wonse Park
{"title":"Single-step prediction of inferior alveolar nerve injury after mandibular third molar extraction using contrastive learning and bayesian auto-tuned deep learning model.","authors":"Kyubaek Yoon, Yiseul Choi, Myoungho Lee, Jaeyeon Kim, Jun-Young Kim, Jin-Woo Kim, Jongeun Choi, Wonse Park","doi":"10.1093/dmfr/twaf069","DOIUrl":"https://doi.org/10.1093/dmfr/twaf069","url":null,"abstract":"<p><strong>Objective: </strong>Inferior alveolar nerve (IAN) injury is a critical complication of mandibular third molar extraction. This study aimed to construct and evaluate a deep learning framework that integrates contrastive learning and Bayesian optimization to enhance predictive performance on cone-beam computed tomography (CBCT) and panoramic radiographs.</p><p><strong>Methods: </strong>A retrospective dataset of 902 panoramic radiographs and 1,500 CBCT images was used. Five deep learning architectures (MobileNetV2, ResNet101D, Vision Transformer, Twins-SVT, and SSL-ResNet50) were trained with and without contrastive learning and Bayesian optimization. Model performance was evaluated using accuracy, F1-score, and comparison with oral and maxillofacial surgeons (OMFSs).</p><p><strong>Results: </strong>Contrastive learning significantly improved the F1-scores across all models (e.g., MobileNetV2: 0.302 to 0.740; ResNet101D: 0.188 to 0.689; Vision Transformer: 0.275 to 0.704; Twins-SVT: 0.370 to 0.719; SSL-ResNet50: 0.109 to 0.576). Bayesian optimization further enhanced the F1-scores for MobileNetV2 (from 0.740 to 0.923), ResNet101D (from 0.689 to 0.857), Vision Transformer (from 0.704 to 0.871), Twins-SVT (from 0.719 to 0.857), and SSL-ResNet50 (from 0.576 to 0.875). The AI model outperformed OMFSs on CBCT cross-sectional images (F1-score: 0.923 vs. 0.667) but underperformed on panoramic radiographs (0.666 vs. 0.730).</p><p><strong>Conclusions: </strong>The proposed single-step deep learning approach effectively predicts IAN injury, with contrastive learning addressing data imbalance and Bayesian optimization optimizing model performance. While artificial intelligence surpasses human performance in CBCT images, panoramic radiographs analysis still benefits from expert interpretation. Future work should focus on multi-center validation and explainable artificial intelligence for broader clinical adoption.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174226","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}
Bethânia Lara Silveira Freitas, Laura Silva Jerônimo, Ana Clara Coutinho Pires, Leandro Augusto Tanure, Débora Cerqueira Calderaro, José Alcides Almeida de Arruda, Lucas Guimarães Abreu, Tarcília Aparecida Silva, Maurício Augusto Aquino de Castro, Sílvia Ferreira de Sousa
{"title":"Shear wave elastography of the salivary glands in the diagnosis of Sjögren disease: a systematic review and meta-analysis.","authors":"Bethânia Lara Silveira Freitas, Laura Silva Jerônimo, Ana Clara Coutinho Pires, Leandro Augusto Tanure, Débora Cerqueira Calderaro, José Alcides Almeida de Arruda, Lucas Guimarães Abreu, Tarcília Aparecida Silva, Maurício Augusto Aquino de Castro, Sílvia Ferreira de Sousa","doi":"10.1093/dmfr/twaf071","DOIUrl":"https://doi.org/10.1093/dmfr/twaf071","url":null,"abstract":"<p><strong>Objective: </strong>Sjögren disease (SD) is characterized by lymphocytic infiltration and fibrosis of the salivary glands. Shear wave elastography (SWE), an ultrasound-based modality that quantifies tissue stiffness, may assist in SD diagnosis. This study aimed to systematically review and meta-analyze the diagnostic performance of SWE in evaluating major salivary glands in individuals with SD, based on studies applying the 2016 ACR/EULAR classification criteria.</p><p><strong>Methods: </strong>Six electronic databases and gray literature sources were searched. Cross-sectional and diagnostic accuracy studies were included. Risk of bias was appraised using the Joanna Briggs Institute tool. Quantitative synthesis was performed using random-effects meta-analyses.</p><p><strong>Results: </strong>Eleven studies comprising 1,029 participants (530 with SD; 499 controls; 90.67% female) were included. Meta-analyses revealed that SWE values were significantly higher in SD patients than in controls, with pooled mean differences of 0.78 m/s (95% CI: 0.54-1.02) and 12.37 kPa (95% CI: 8.65-16.10) in the parotid gland, and 0.48 m/s (95% CI: 0.33-0.63) and 9.09 kPa (95% CI: 4.88-13.31) in the submandibular gland. Parotid SWE values expressed in kPa showed the highest diagnostic accuracy (AUC=82.9%), followed by values in m/s (AUC=73.1%).</p><p><strong>Conclusions: </strong>SWE effectively differentiates SD from healthy individuals, particularly when applied to the parotid gland. Standardization of SWE protocols may enhance diagnostic accuracy and foster clinical integration.</p><p><strong>Advances in knowledge: </strong>This is the first meta-analysis focused exclusively on studies adopting the 2016 ACR/EULAR criteria for SD.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145136883","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}