Objectives To evaluate whether synthesized extraoral bitewing views generated from existing cone-beam CT (CBCT) scans can support posterior-tooth assessment when CBCT is the initial imaging modality, without additional radiographic acquisition.Methods We retrospectively assembled 60 CBCT scans from 3 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 Tomographic Iterative GPU-based Reconstruction (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 2 oral radiology experts served as the reference. Performance was evaluated with false-positive and false-negative rates, specificity, F1 score, and Area Under the Curve (AUC). Interobserver agreement was assessed with (weighted) kappa. Differences in AUC (Delta AUC) between CBCT and synthesized extraoral bitewing views were evaluated using bootstrap-derived 95% confidence intervals (CIs).Results 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 Delta AUC,-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.Conclusion When CBCT is the initial imaging modality, synthesized extraoral bitewing views derived from the existing scan may provide a complementary 2D 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.
Abstract Objectives This systematic review aims to evaluate the techniques and reported patterns of heatmap-based visual explanations in deep learning (DL) systems for dental radiographic classification tasks. Methods A literature search following PRISMA guidelines was conducted in PubMed, Scopus, IEEE Xplore Library, Oria.no and Google Scholar to retrieve studies using DL for dental classification tasks. Only articles with a visual explanation (heatmap) were selected. Risk of bias assessment was done with QUADAS-2, PROBAST-AI and CEBM. The heatmap technique, reasons for inclusion, explanations provided and patterns were analysed. Results In the 136 studies reviewed, Grad-CAM was the most commonly used technique. The predominant reason for using visual explanations was to understand the decision-making process of the DL model. Some heatmaps reflect established radiographic criteria, while others exhibit unique, label-dependent patterns that sometimes emphasise irrelevant areas. Cropping to the region of interest influences visual explanations. Conclusions Visual explanations seem clinically plausible to domain experts when aligned with domain knowledge, but clinical plausibility does not equal technical faithfulness. Formal faithfulness testing was rarely performed among the included studies. Therefore, explanations should not be assumed to accurately represent the model’s underlying reasoning. Limitations include the evaluation of studies not primarily designed for visual explanation assessment. No funding was received for this review. Authors declare no competing interests. Advances in knowledge Visual explanations, while clinically plausible when aligned with domain knowledge, remain insufficiently validated and should not be assumed to faithfully represent model reasoning. An implausible explanation does not necessarily indicate model failure. Domain/task-specific evaluation metrics for explainable AI in dentomaxillofacial radiology are needed.
Abstract Objectives To compare final-answer accuracy of web-based large language models (LLMs) on Turkish and English image-based dental examination multiple-choice questions (deMCQs), and to describe explanation quality, reference quality, output volume, and an exploratory word-normalized water-use scenario. Methods Fifty-two image-based deMCQs (2012–2025) were evaluated in Turkish and English using ChatGPT, Gemini, and Claude, yielding 312 responses. Accuracy was coded as correct or incorrect. Explanation and reference quality were assessed using a 5-point Likert scale and treated as exploratory descriptive outcomes. Accuracy was analyzed using question-clustered binomial generalized estimating equations (GEE) with model, language, and model×language interaction terms. Output word counts were summarized, and a study-specific exploratory word-normalized water-use scenario was derived from a published exchange-level estimate. Results Overall accuracy was 56.7% (177/312). Accuracy was 59.0% in Turkish and 54.5% in English. GEE analysis showed no significant effects of model, language, or model×language interaction (p > 0.05). Descriptively, Gemini had the highest accuracy (61.5%), whereas Claude had the highest mean explanation (3.95±1.31) and reference quality (4.85±0.38) scores. Across 312 prompt–response exchanges, the models generated 34,534 words, corresponding to an exploratory word-normalized water-use proxy of 3.12–7.80 L. Conclusions Freely accessible web-based LLMs demonstrated moderate accuracy on image-based deMCQs. The water-use proxy was derived from published exchange-level assumptions and should not be interpreted as a direct measurement or validated model-specific estimate of water consumption. Descriptive differences between models and languages should not be interpreted as evidence of superiority or equivalence. These systems may support dental education; however, outputs require expert verification before educational or clinical use. Advances in knowledge This study evaluates three widely accessible web-based multimodal LLMs using an entirely image-based dental examination question set, accounts for repeated observations through question-clustered GEE, compares Turkish and English performance without equating non-significance with equivalence, and presents a transparent word-normalized environmental scenario with explicit assumptions and limitations.
Abstract Objectives This study systematically evaluated imaging characteristics of primary jaw lymphoma using multiple modalities to improve diagnostic accuracy and differentiation from other maxillofacial pathoses. Methods Fifty-three patients with histopathologically confirmed jaw lymphoma (January 2000–March 2025) were retrospectively reviewed. Clinical data including chief complaints and misdiagnosis history were investigated. Imaging features—lesion location, soft-tissue swelling, cortical destruction pattern, internal structure, and metabolic activity—were assessed using panoramic radiography, CT, MRI, and PET. Results Initial misdiagnoses as odontogenic infection or inflammation led to inappropriate treatments in 27 of 53 cases (50.9%). Lesions most commonly involved the maxillary tuberosity (24.5%), with maxillary sinus extension in 74.2% of maxillary cases. Prominent soft-tissue swelling was observed in 50.9%, while severe cortical destruction predominated (61.2%). CT evaluation revealed cortical micro-perforations in 48.9% of cases occurring exclusively within the maxilla—though predominant in only 16.3%. PET imaging commonly demonstrated multi-site involvement with intense FDG uptake comparable to brain activity. Conclusions Primary jaw lymphoma demonstrated characteristic features including severe cortical destruction with micro-perforation and prominent soft-tissue swelling. Frequent cortical micro-perforations highlight the importance of careful CT evaluation for subtle cortical breakthrough. Recognition of these features, particularly with non-specific clinical symptoms, may improve early diagnostic suspicion, reduce misdiagnosis as odontogenic infection, and facilitate timely biopsy and management. Advances in knowledge This is the first study to systematically characterize cortical micro-perforation as a distinctive imaging feature of primary jaw lymphoma. This finding may help reduce misdiagnosis as an odontogenic infection.
Abstract Objectives Dental MRI provides soft-tissue contrast without ionising-radiation, but is susceptible to motion, particularly in paediatric imaging. Independent mandibular motion limits conventional single-rigid-model correction, while tailored strategies remain unexplored for dental MRI. We developed an automated, region-adaptive motion-corrected reconstruction method tailored to dental MRI. Methods The proposed method automatically defines the maxillary- and mandibular landmarks, performs region-specific joint motion-corrected reconstruction, and fuses the motion-corrected regions into a single motion-free image. The method has broadly sequence applicability without using external motion-free reference, navigator, or prospective tracking. It was validated with three multi-contrast 3D sequences at 0.55T in adult controlled-motion experiments and paediatric scans. Image quality was assessed using normalised gradient square (NGS) and blinded radiologist scoring. Uncorrected (No-MoCo), full field-of-view single-rigid-model correction (MoCo-fullFOV), and fused region-adaptive correction (MoCo-fused) were compared. Cross-correlation between maxillary and mandibular motion traces classified shared and independent mandibular motion pattern. Results Eight healthy adults and 11 paediatric patients, including 10 with traumatic dental injuries and one with delayed dental development, completed 42 acquisitions. Across all acquisitions, MoCo-fused improved NGS compared with No-MoCo (P<.0001) and MoCo-fullFOV (P=.0004). In mandibular-involved motion cases (n = 23), MoCo-fullFOV did not significantly improve image quality, whereas MoCo-fused improved both NGS and radiologist scores compared with No-MoCo. Lower cross-correlation between maxillary and mandibular motion traces was associated with greater NGS improvement for MoCo-fused over MoCo-fullFOV (Spearman r = −0.66, P<.0001). Paediatric examples showed improved visualisation of pulp signal and inflammatory change after motion correction. The method is open-sourced at https://github.com/ZihanNing/dental_MRI_motion_correction.git. Conclusions Automated region-adaptive motion-corrected dental MRI improved image quality, particularly with mandibular motion.
