Dento maxillo facial radiology最新文献

{"title":"From CBCT to Synthesized Extraoral Bitewing: A Patient-Specific Pipeline for Dose- and Cost-Free 2D Information Presentation and Clinical Decision Support.","authors":"Kemal Selcuk Yucel, Alp Pinarbasi, Beyza Yalvac Pinarbasi, Sedat Ozdogan, Ferhat Aydin, Kadir Yilmaz, Osman Furkan Cakmak, Duygu Polat, Busranur Yavuz, Emin Murat Canger, Dan Ruan","doi":"10.1093/dmfr/twag066","DOIUrl":"https://doi.org/10.1093/dmfr/twag066","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate whether synthesized extraoral bitewing views generated from existing CBCT scans can support posterior-tooth assessment when CBCT is the initial imaging modality, without additional radiographic acquisition.</p><p><strong>Methods: </strong>We retrospectively assembled 60 CBCT scans from three datasets encompassing diverse posterior jaw morphologies. We developed a computational pipeline to compute a patient specific dental arch, define a focal trough, and simulate extraoral bitewing acquisition using a panoramic inspired rotating source trajectory. Synthetic projections were generated using a Beer-Lambert forward model implemented in TIGRE and reconstructed into right and left synthesized extraoral bitewing views. Eight observers, including dental students and residents in endodontics, periodontics, and oral radiology scored posterior teeth for caries, periapical lesions, and periodontal bone loss using original CBCT images and synthesized extraoral bitewing views in separate sessions. A consensus of two oral radiology experts served as the reference. Performance was evaluated with false positive and false negative rates, specificity, F1 score, and AUC. Inter observer agreement was assessed with (weighted) kappa. Differences in AUC (ΔAUC) between CBCT and synthesized extraoral bitewing views were evaluated using bootstrap-derived 95% confidence intervals.</p><p><strong>Results: </strong>Compared with CBCT alone, synthesized extraoral bitewing views were associated with lower overdiagnosis for dental caries and periapical lesions (95% CI, 5.87-12.00 and 3.87-8.12,respectively) and reduced underdiagnosis for periodontal bone loss (95% CI, 10.12-18.37). Synthesized extraoral bitewing views showed higher ordinal AUC for dental caries and periodontal bone loss (mean ΔAUC,-0.12 to - 0.05 and -0.11 to - 0.04,respectively). No consistent improvement was observed for periapical lesion AUC, possibly due to small sample size and limited power.</p><p><strong>Conclusion: </strong>When CBCT is the initial imaging modality, synthesized extraoral bitewing views derived from the existing scan may provide a complementary two-dimensional visualization for posterior-tooth assessment. In this reader study, the derived views were associated with shorter interpretation time and task-dependent changes in diagnostic performance.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149105693","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":"Effect of quaternary ammonium disinfection on image quality and structural integrity of photostimulable phosphor plates.","authors":"Pedro Henrique Pereira da-Silva-Costa, Débora Costa Ruiz, Tárcila Mathiasso Nascimento da Silva, Rafael de Queiroz Ferreira, Teresa Cristina Rangel Pereira, Sergio Lins de-Azevedo-Vaz","doi":"10.1093/dmfr/twag030","DOIUrl":"10.1093/dmfr/twag030","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the effect of quaternary ammonium compound (QAC) disinfection on the radiographic image quality and chemical integrity of photostimulable phosphor (PSP) plates.</p><p><strong>Methods: </strong>Radiographic image quality was assessed using 2 radiographs of an acrylic-block and 2 radiographs of an aluminum step-wedge acquired before disinfection and after 10 groups with 10 disinfections each. These radiographs were acquired with 2 PSP plates. Brightness, noise, uniformity, contrast, and presence of artifacts were analyzed. Analysis of variance compared gray values between disinfections (α = 0.05). Chemical integrity was assessed using mid-infrared Fourier-transform infrared (FTIR) spectroscopy on the PSP plates tube side, comparing disinfected plates with a non-disinfected control. Metal disk corrosion of the plates was visually inspected.</p><p><strong>Results: </strong>Brightness decreased after 100 disinfections compared with radiographs obtained after 20 disinfections (P = .026). Uniformity increased for all disinfection groups compared with baseline radiographs (P < .001). Radiographs obtained after 100 disinfections showed higher contrast than those acquired after 20 disinfections (P = .005). Noise did not differ (P > .05). Artifacts were observed after 40 disinfections. Fourier-transform infrared analysis showed hydration followed by degradation of the PSP plates after 100 disinfections. Metal disk corrosion occurred after 10 disinfections.</p><p><strong>Conclusions: </strong>Quaternary ammonium compound disinfection affected brightness, uniformity, contrast, produced artifacts, chemical changes, and metal disk corrosion of the PSP plates.</p><p><strong>Advances in knowledge: </strong>This study is the first to assess the impact of disinfecting PSP plates with QAC. Results showed that QAC is not a viable option since its use produced changes in image quality and integrity degradation.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"732-742"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147962745","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":"Diagnostic performance of a novel wireless direct-conversion intraoral sensor versus complementary metal-oxide semiconductor and photostimulable storage phosphor systems for proximal caries detection: an ex vivo study.","authors":"Matheus Barros-Costa, Gustavo Machado Santaella, Gabriela Gavilan Hadid, Christiano Oliveira-Santos, Deborah Queiroz Freitas, Francisco Carlos Groppo, William C Scarfe","doi":"10.1093/dmfr/twag031","DOIUrl":"10.1093/dmfr/twag031","url":null,"abstract":"<p><strong>Objectives: </strong>To compare the diagnostic accuracy of a new wireless direct-conversion digital intraoral sensor to current indirect-conversion complementary metal-oxide semiconductor (CMOS) and photostimulable storage phosphor (PSP) sensors for detecting proximal caries.</p><p><strong>Methods: </strong>The sample in this ex vivo study were 28 human premolars with 21 micro-CT verified non-cavitated proximal dental carious lesions. Images were obtained using 3 digital intraoral systems: a wireless direct-conversion sensor, a wired indirect-conversion CMOS sensor, and a PSP sensor. A custom phantom was constructed providing a limited dental arch segment comprising a molar, first premolar, and canine. The premolar was substituted and the phantom imaged using each intraoral system with (filtered) and without (raw) the application of a manufacturer-recommended enhancements, providing 168 images. Eight oral radiologists assessed the images using a 5-point scale. Receiver operating characteristic analysis was performed to calculate sensitivity, specificity, and the area under the curve (AUC) and compared across modalities using 2-way analysis of variance (ANOVA) with post hoc Tukey's test at an a priori level of significance of 0.05.</p><p><strong>Results: </strong>The AUC ranged from 0.58 to 0.73 (sensitivity range: 0.21-0.68, specificity range: 0.69-0.92). The wireless direct-conversion sensor (0.72 ± 0.06) showed diagnostic performance comparable to CMOS (0.72 ± 0.06) and superior to PSP (0.58 ± 0.07) for raw images (P < .001). The direct-conversion sensor without image enhancement (0.68 ± 0.18) demonstrated the highest sensitivity, whereas the PSP without image enhancement (0.21 ± 0.09) had the lowest sensitivity. Application of image enhancement improved PSP performance (0.48 ± 0.16), approximating that of the other systems.</p><p><strong>Conclusions: </strong>Based on this ex vivo study, the wireless direct-conversion and CMOS sensors demonstrated similar diagnostic performance, superior to PSP in unfiltered conditions. These findings should be interpreted in light of the ex vivo design and modest sample size.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"743-750"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147986958","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":"Low-dose cone-beam CT in implant dentistry: a clinical validation of diagnostic sufficiency.","authors":"Ruiyang Ni, Xuhui Luo, Nuo Han, Ziyang Hu, Zitong Lin","doi":"10.1093/dmfr/twag035","DOIUrl":"10.1093/dmfr/twag035","url":null,"abstract":"<p><strong>Objective: </strong>To validate the diagnostic sufficiency of a low-dose (LD) cone-beam CT (CBCT) protocol for dental implant assessment by comparing it to a standard-dose (SD) protocol in a clinical setting. The study evaluated linear measurement accuracy, subjective clarity of anatomical landmarks, and the impact on bone microarchitecture assessment.</p><p><strong>Methods: </strong>This retrospective study analyzed preoperative (SD) and postoperative (LD) CBCT scans from 37 patients (37 SD and 37 LD scans for both maxillary and mandibular sites). The LD protocol achieved a 76.7% dose reduction by decreasing tube current and exposure time. The diagnostic utility was assessed: (1) subjective clarity scoring of the mandibular canal and maxillary sinus floor; (2) objective linear measurements of key anatomical dimensions; and (3) quantitative analysis of bone microstructural parameters (trabecular number [Tb.N], trabecular separation [Tb.Sp], trabecular thickness [Tb.Th], bone volume fraction [BV/TV]). Reliability assessment was also performed for clarity scoring and quantitative measurements. Statistical comparisons were performed using Chi-square and paired-samples t-tests.</p><p><strong>Results: </strong>No statistically significant differences were found between the LD and SD protocols in the subjective clarity of anatomical structures (P > .05) or in the accuracy of linear measurements (P > .05). However, all 4 bone microstructural parameters showed statistically significant differences between the 2 protocols in both the maxilla and mandible (P < .05 for all). Intra- and inter-examiner assessments demonstrated substantial to good consistency across all qualitative (weighted Kappa >0.611) and quantitative (intra-class correlation coefficient [ICC] >0.702) parameters.</p><p><strong>Conclusion: </strong>This study provides clinical evidence that for the specific CBCT unit tested, the optimized LD CBCT protocol reduces patient radiation exposure by over 76.7% for dental implant assessment without compromising the diagnostic accuracy required for linear measurements and visualization of key anatomical landmarks. Therefore, for the tested model, the LD protocol is sufficient for preoperative CBCT scanning in implant dentistry. This offers a clinically validated method for enhancing patient safety in this specific context, effectively applying the As Low As Diagnostically Acceptable, Indication-oriented, and Patient-specific (ALADAIP) principle.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"751-761"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148013602","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":"Novel marker-based cone-beam CT registration for enhanced accuracy in dental implant planning.","authors":"Maryam Buholayka, Rama Zouabi, Santiago F Cobos, Aditya Tadinada","doi":"10.1093/dmfr/twag041","DOIUrl":"10.1093/dmfr/twag041","url":null,"abstract":"<p><strong>Objectives: </strong>Accurate image registration is essential for successful digital dental implant planning. Surface-based registration, commonly used in clinical software, is sensitive to cone-beam CT (CBCT) artifacts and relies on manual landmark selection, potentially reducing accuracy. Marker-based registration offers improved precision but is underused due to its technical complexity and time demands. The purpose of this ex-vivo study was to evaluate the accuracy of a novel marker-based registration method using limited-view CBCT reconstructions derived from 2 orthogonal projection images and to compare it with a conventional surface-based registration method.</p><p><strong>Methods: </strong>An ex-vivo model consisting of a maxillary arch with removable 3D-printed teeth and a radiographic guide containing radiographic markers was used to simulate 5 metal artifact conditions. Full-view CBCT scans were acquired for each condition. For the conventional method, 3 examiners independently performed dual-scan registrations using user-defined surface landmarks on full CBCT reconstructions. For the proposed method, examiners selected orthogonal projection images where markers were clearly visible and limited-view reconstructions were generated to identify marker centroids. Registration error was measured as the point-to-point distance between corresponding surface reference points, standardized to a common frame of reference. Inter-rater reliability was also assessed.</p><p><strong>Results: </strong>Both methods maintained consistent performance across all artifact conditions. The proposed method demonstrated greater accuracy, with lower point-to-point registration errors and less spatial variation. Inter-rater reliability was excellent for the proposed method and good for the conventional approach.</p><p><strong>Conclusion: </strong>The proposed marker-based registration method using orthogonal projection images and limited-view CBCT reconstructions showed higher accuracy than conventional surface-based registration under controlled ex-vivo conditions. Although the workflow currently requires additional examiner input, it may improve precision in dual-scan protocols for implant planning. Future clinical studies and software developments are required to support clinical implementation.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"796-805"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13624506/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148175415","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":"Lamina dura thickening in patients on antiresorptive therapy as a radiographic risk indicator of medication-related osteonecrosis of the jaw: a retrospective longitudinal cohort study.","authors":"Sonya Radi, Samy El Bachaoui, Ilya Tsiklin, Constanza Pastenes, Hanne De Backer, Ruxandra Coropciuc, Tim Van den Wyngaert, Benoit Beuselinck, Reinhilde Jacobs","doi":"10.1093/dmfr/twag029","DOIUrl":"10.1093/dmfr/twag029","url":null,"abstract":"<p><strong>Aims: </strong>This study investigated whether antiresorptive drug (ARD) therapy is associated with lamina dura (LD) thickening, defined as a radiographic increase in the thickness of the normally thin, radiopaque cortical line surrounding the tooth root. It further evaluated whether LD thickening serves as a radiographic marker and risk indicator for medication-related osteonecrosis of the jaw (MRONJ).</p><p><strong>Methods: </strong>Panoramic radiographs from 65 ARD-treated patients (University Hospital Leuven) and 65 age- and sex-matched controls were analyzed. Inclusion criteria were prior oncological diagnosis, high-dose intravenous ARD, and radiographs before and after therapy. Three blinded oral and maxillofacial radiologists categorized LD appearance into 4 grades: (0) not/barely visible, (1) normal, (2) mild thickening, and (3) marked thickening. Group differences and longitudinal changes were evaluated using appropriate non-parametric and time-to-event analyses.</p><p><strong>Results: </strong>Among 130 participants, LD thickness remained stable in controls but increased in ARD-treated patients (P < .001). Within the ARD group, LD thickening changed over time (P < .001): 30.6% showed no change, 55.4% developed mild thickening, and 13.8% marked thickening. Controls showed minimal change (P = .011), with 9.2% developing mild thickening. Kaplan-Meier analysis estimated a median time to LD thickening of 27 months, with a higher thickening probability in ARD-treated patients than controls (P < .001). Lamina dura thickening was not directly associated with MRONJ (P = .39).</p><p><strong>Conclusion: </strong>Lamina dura thickening is strongly associated with long-term ARD exposure and shows progressive changes. Although not directly associated with MRONJ in this cohort, it may still represent a potential risk indicator, warranting confirmation in further studies.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"722-731"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13624511/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147971366","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":"Image sharpening improves the visibility of reference points on low-dose lateral cephalometric radiographs: a phantom study.","authors":"Ikuho Kojima, Arata Ito, Yusuke Shimada, Naoko Tagaino Watanabe, Manami Ikawa, Shu Onodera, Hiroyasu Kanetaka, Masahiro Iikubo","doi":"10.1093/dmfr/twag047","DOIUrl":"10.1093/dmfr/twag047","url":null,"abstract":"<p><p>This phantom study aimed to determine whether a novel non-artificial intelligence image-sharpening approach improves the visibility of reference points on low-dose lateral cephalometric radiographs. Lateral cephalometric radiographs were obtained using an adult human bone phantom at 100% of the routine dose. Low-dose imaging was performed using 60%, 40%, and 20% of the routine dose. Each low-dose image underwent a 2-level image-sharpening process using the Medical Image Enhancer software. Six reviewers evaluated the visibility of the 5 reference points in the first and second sets of sharpened and 100% radiation-dose images. Using Scheffé's method of paired comparisons, odds ratios (ORs) were reported as relative values for a standard cephalometric radiograph (100% radiation dose) to compare the visibility of reference points among imaging conditions. For the first set of mildly sharpened 60%-dose images, the ORs for the 4 reference points were >1.0, Point A (OR 1.12, P = .83), Nasion (OR 2.26, P = .11), posterior nasal spine (OR 2.35, P = .1), and incisal edge of the maxillary central incisor (OR 1.35, P = .53), indicating visibility comparable to or better than the 100%-dose images. For the second set of markedly sharpened images, rated visibility was significantly higher for all reference points at 60% and 40% doses and for several reference points at 20% dose. Image-sharpening algorithms improved the visibility of reference points on low-dose phantom radiographs, suggesting their technical feasibility as a post-acquisition approach for dose-reduced cephalometric imaging.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"812-819"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13624509/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148390188","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":"Methodological quality of dental cone-beam CT diagnostic reference levels: a systematic review.","authors":"Bharathraj Arunmani, Keith Horner, Ronan Coleman, Isabel Fleischmann, Margarete B McGuigan","doi":"10.1093/dmfr/twag036","DOIUrl":"10.1093/dmfr/twag036","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the methodological quality of dental cone-beam CT (CBCT) diagnostic reference levels (DRLs) studies and reports, identify factors that limit DRL comparison, assess the level and methods of dose optimization, and clarify obstacles, both in dose optimization and DRL establishment.</p><p><strong>Methods: </strong>A systematic search was applied across 5 databases and gray literature with International Atomic Energy Agency (IAEA) member countries contacted, to identify dental CBCT DRL studies and national reports. Studies/reports containing DRL establishment procedures, insufficient methodological detail, and adopted DRLs were excluded. Methodological quality was assessed using a modified Effective Public Health Practice Project tool, aligned with a checklist developed in accordance with International Commission on Radiological Protection (ICRP) 135.</p><p><strong>Results: </strong>Of 320 reports screened, 19 were included. Diagnostic reference levels were clinical indication or field of view (FOV) based, using dose/kerma-area-product (DAP/KAP) metrics. Overall, 63% of studies had moderate methodological quality; DRL comparability was limited due to gaps or inconsistencies in reporting of exposure parameters, FOV, and heterogeneous indication grouping. Substantial dose variability was observed within the same clinical indications (2- to 10-fold) and FOV categories (3- to 10-fold), reflecting routine use of large FOVs irrespective of indication, reliance on manufacturer default protocols, limited understanding/education/training of exposure settings or optimization strategies, non-standardized system FOV settings, and unauthorized CBCT operators.</p><p><strong>Conclusions: </strong>The majority of CBCT DRL studies are not of high quality. Improving DRL reporting quality requires interdisciplinary collaboration; digitized-dose recording with robust retrospective management of protocols, dose, indications; national dose registries for periodic dose audit; improved clinician education/engagement, strengthened regulatory oversight, and potentially international standardized frameworks.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"705-721"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13624500/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148013669","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":"Automatic detection of panoramic positioning errors and development of an objective image quality scoring system using deep learning.","authors":"Sijia Hu, Erkang Tian, Xinze Wu, Juan Li","doi":"10.1093/dmfr/twag038","DOIUrl":"10.1093/dmfr/twag038","url":null,"abstract":"<p><strong>Objectives: </strong>To develop a deep learning model capable of automatically detecting common positioning errors in panoramic radiographs and to establish an error-based objective 10-point image quality scoring system aligned with expert evaluation.</p><p><strong>Methods: </strong>A total of 4390 panoramic radiographs were retrospectively annotated for 7 clinically relevant positioning errors (including chin position, head rotation/tilt, bite position, tongue position, cervical spine positioning, and anatomical coverage) associated with diagnostically meaningful geometric distortion or anatomical superimposition by 2 experienced oral radiologists. A multi-label deep learning model based on a modified residual network was trained to detect all errors simultaneously. An independent dataset of 510 radiographs was scored for subjective image quality on a 10-point scale. Multiple linear regression was used to estimate the independent contribution of each positioning error to subjective image quality and to derive an objective scoring system established by converting regression-derived weights of significant errors into standardized point deductions.</p><p><strong>Results: </strong>High annotation and scoring reliability were achieved (Kappa: 0.879-0.953; ICC: 0.838). The model achieved high performance across all error types, with accuracy ranging from 88.40% to 96.00% and area under the curve values between 98.17 and 99.37. Several positioning errors were associated with lower subjective image quality scores (P < .001). The resulting error-weighted objective score showed moderate correlation with expert ratings (r = 0.673, P < .001).</p><p><strong>Conclusions: </strong>The proposed system enables accurate detection of positioning errors and provides a structured and interpretable, error-based surrogate measure of perceived panoramic image quality.</p><p><strong>Advances in knowledge: </strong>This study presents an error-specific, data-driven framework for objective assessment of panoramic image acquisition quality, enhancing the interpretability and standardization of image quality evaluation.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"774-782"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148210499","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":"Assessment of pre-trained deep learning models in the detection of metal artifacts in axial cone-beam tomography slices.","authors":"Shishir Shetty, Wael Talaat, Natheer Al-Rawi, Sausan AlKawas, Mais Sadek, Renita Rego, Kamis Gaballah, Sangeetha Narasimhan, Mohammed Amjed Alsaegh, Zaid Hamdoon","doi":"10.1093/dmfr/twag037","DOIUrl":"10.1093/dmfr/twag037","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to evaluate the performance of 3 pre-trained deep learning models (ResNet50, MobileNetV2, and EfficientNetB0) in the detection of metal artifacts (MAs) in axial cone-beam CT (CBCT) slices.</p><p><strong>Methods: </strong>Two researchers calibrated, examined, and collected 1000 axial CBCT slices having crown and restoration-related artifacts (CRS) (n = 200), orthodontic bracket-related artifacts (OB) (n = 200), implant-related artifacts (IMP) (n = 200), root canal filling-related artifacts (RC) (n = 200) and 200 axial slices without artifacts (N) from a single CBCT unit. The image dataset was split at a 70:20:10 ratio for training, validation, and testing. Data augmentation was applied to the training data. Three pre-trained models (ResNet50, MobileNetV2, and EfficientNetB0) were trained, validated, and tested for the ability to classify data. The best-performing model was externally validated using axial images from different CBCT units from the same institution.</p><p><strong>Results: </strong>EfficientNetB0 was the best-performing model with 0.96 (95% CI, 0.93-0.98) test accuracy. Its precision, recall and F1 score were 0.98 (95% CI, 0.96-0.99), 0.96 (95% CI, 0.93-0.97), and 0.97 (95% CI, 0.95-0.99), respectively. EfficientNetB0 showed a significantly higher area under curve (AUC) value (0.98, 95% CI, 0.96-0.99) compared to other models. Its average classification time was 7.1 s. Gradient-weighted class activation mapping attention confirmed the focus of the model on MAs in the images. During external validation, EfficientNetB0 showed an accuracy of 0.93 (95% CI, 0.90-0.96) and an AUC-ROC of 0.95 (95% CI, 0.94-0.96). There was no significant difference in the performance metrics of EfficientNetB0 between test dataset and external validation dataset.</p><p><strong>Conclusions: </strong>EfficientNetB0 demonstrated consistent and acceptable performance across all evaluation stages for the detection and classification of MAs in axial CBCT slices.</p><p><strong>Advances in knowledge: </strong>The study describes the performance of pre-trained model in the detection and classification of MAs. The model can be used by the clinician as a decision-support and quality-assessment tool in the CBCT imaging workflow.</p>","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":"762-773"},"PeriodicalIF":4.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148028108","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}