To determine whether longitudinal skeletal muscle assessment improves prognostic evaluation for head and neck cancer-specific survival (HNC-Surv) and recurrence outcomes in radiotherapy-treated patients, and secondarily to compare prognostic performance of C3- versus L3-derived skeletal muscle indices. This prognostic study included 206 patients with HNC treated with curative-intent radiotherapy. Skeletal muscle index (SMI) was assessed at baseline and post-treatment imaging, and longitudinal metrics (percentage change and change rate) were calculated. Fine-Gray competing-risk regression was used for HNC-Surv, and Cox regression for locoregional recurrence-free survival (LRFS) and distant recurrence-free survival (DRFS). Discrimination was evaluated using time-dependent ROC analysis and compared using the DeLong test. Over a median follow-up of 5.6 years, 68 deaths occurred, including 52 HNC-related deaths; 59 patients (29
The aim of this study was performed to investigate the salivary gland SPECT/CT of parotid glands in patients with lymphoepithelial sialadenitis including preliminary study on clinical and pathological features. The study was performed in 5 patients with lymphoepithelial sialadenitis who underwent salivary gland SPECT/CT. Correlation between maximum standardized uptake value (SUV) at ratio of pre- to post-stimulation and clinicopathological parameters in lymphoepithelial sialadenitis were performed by Pearson correlation coefficient. The maximum SUV of 10 parotid glands in 5 patients with lymphoepithelial sialadenitis using salivary gland SPECT/CT was 23.8 ± 16.9 at pre-stimulation, 10.5 ± 5.1 at post-stimulation, and 2.06 ± 0.66 at ratio of pre- to post-stimulation. Furthermore, the maximum SUV at ratio of pre- to post-stimulation was significantly correlated with Saxon test score (r = 0.637, p = 0.048). The salivary gland SPECT/CT can be useful in clinical practice for the quantitative management of parotids in patients with lymphoepithelial sialadenitis.
To develop and validate a logistic regression model that integrates clinical and fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT)-derived radiomic features to predict cervical lymph node metastasis in tongue squamous cell carcinoma. This retrospective study included 316 patients who underwent preoperative FDG-PET/CT between December 2013 and December 2023, classified into analysis (n = 250) and validation (n = 66) cohorts. Primary tumours were segmented using standardised uptake value (SUV)-based thresholds (≥ 40
To evaluate the performance and potential utility of generative artificial intelligence (AI) in oral and maxillofacial radiology using the board-certification examination administered by the Japanese Society for Oral and Maxillofacial Radiology (JSOMR). The responses generated by ChatGPT for multiple-choice questions from the board-certification examination of the JSOMR over the three-year period from 2020 to 2022 were assessed. The questions were manually entered individually as prompts for GPT-3.5, GPT-4, and GPT-5, which are the models available from ChatGPT. The accuracy was calculated according to examination year, question format, and level of taxonomy. GPT-3.5 achieved an accuracy of 40.3
Cone-beam computed tomography (CBCT) is the reference standard for detecting osseous changes in temporomandibular joint osteoarthritis (TMJ-OA) but involves ionizing radiation. MRI avoids radiation exposure and enables simultaneous soft and hard tissue evaluation; however, its sensitivity for osseous abnormalities remains limited. This study aimed to develop and evaluate a proof-of-concept two-stage deep learning framework for automated MRI-based TMJ-OA detection. A retrospective dataset of 200 bilateral TMJ MRI examinations (400 condyles; 113 osteoarthritic, 287 non-osteoarthritic) was collected from two academic dental institutions. Stage 1 employed a U-Net architecture for automated mandibular condyle segmentation using manually annotated masks. Stage 2 applied ResNet-50 and ResNet-101 to classify segmented condylar regions as absent, normal, or osteoarthritic. Labels were established by two experienced oral and maxillofacial radiologists using CBCT-confirmed osseous findings and DC/TMD clinical criteria. Patient-level partitioning (70/15/15
To develop and evaluate the feasibilityof a nationwide registry-based automated dose monitoring system for dental cone-beam computed tomography (CBCT). A CBCT dose monitoring system was developed to automatically extract dose-related parameters from Digital Imaging and Communications in Medicine (DICOM) headers. The system was implemented at participating dental institutions across the Republic of Korea, and data were collected from CBCT examinations performed between March and November 2025. Device-reported dose-area product (DAP) values were categorized according to field-of-view (FOV) size, patient age group, and institution type. Category-specific DAP distributions were summarized using the minimum, 25th percentile, median, 75th percentile, and maximum values. A total of 22,781 CBCT examinations from 120 participating dental institutions were included. Medium FOV examinations were the most common (21,390; 93.9
To determine whether two-dimensional B-mode ultrasound radiomics of the masseter muscle can differentiate individuals with a clinically defined probable bruxism phenotype from those without clinical evidence of bruxism. Eighty-six participants were included: 44 with clinically defined probable bruxism and 42 without clinical evidence of bruxism. Bilateral masseter ultrasound images were obtained at rest and during clenching, yielding four images per participant and 344 manually segmented regions of interest. Two-dimensional radiomic features were extracted from calibrated exported B-mode images and aggregated into participant-level representations. LASSO logistic regression was used for exploratory feature selection and internal validation. Intraobserver segmentation reproducibility was assessed in 80 images using Dice similarity coefficients and feature-wise intraclass correlation coefficients. Feature extraction was completed for all 344 images without failed cases or missing values. The highest-ranking configuration used the participant-level overall mean of bilateral rest and clench images with texture plus two-dimensional shape features. This configuration achieved a nested cross-validation AUC of 0.926 ± 0.090. Aggregated participant-level cross-validated predictions for the primary model yielded an AUC of 0.941 (95
This study aimed to classify sella turcica morphologies using lateral cephalograms, analyze craniofacial skeletal pattern differences among distinct morphologies, and investigate their associations. This retrospective study included 240 adults (120 males and 120 females; mean age, 20.0 ± 1.6 years) selected through stratified random sampling from 729 eligible records obtained between 2023 and 2024. Sella turcica morphology was classified on lateral cephalograms into four groups: normal sella turcica, anterior wall/floor abnormality, posterior wall abnormality, and sella turcica bridging. Associations between morphology groups and skeletal pattern distributions were evaluated using chi-square or Fisher–Freeman–Halton exact tests. Group differences in continuous variables were analyzed using one-way analysis of variance or Kruskal–Wallis tests with appropriate post hoc comparisons. Correlations were assessed using Pearson or Spearman coefficients. Statistical significance was set at α = 0.05. Sagittal skeletal pattern distribution differed significantly among the four morphology groups (p < 0.001). The bridging group showed the highest proportion of skeletal Class III subjects (36.7
Pituitary neuroendocrine tumors (PitNET) comprise 15
This study evaluated the safety and efficacy of an iodinated contrast agent for videofluoroscopic swallowing studies (VFSS) in patients with swallowing disorders, compared with barium sulfate contrast agents. The study included 20 patients who underwent VFSS at Hiroshima University Hospital in 2025 for dysphagia evaluation. Iodixanol (Visipaque 270®; GE Healthcare Pharma Co., Ltd., Chicago, Illinois) was used as the iodinated contrast agent. For comparison, VFSS images obtained with Barytester® (FUSHIMI Pharmaceutical Co., Ltd., Kagawa, Japan) in the same patients served as barium sulfate controls. The frequency of adverse events associated with oral Visipaque 270® administration was assessed. VFSS images obtained with Barytester® and Visipaque 270® in the same patients were compared to evaluate imaging performance. To determine whether image evaluation outcomes were equivalent between Visipaque 270® and Barytester®, an equivalence test was performed using the two one-sided tests procedure. Visipaque 270® was associated with no adverse events, including gastrointestinal or other adverse events. Image evaluations using Visipaque 270® and Barytester® were statistically equivalent. VFSS was performed using the iodinated contrast agent Visipaque 270®. No adverse events related to oral Visipaque 270® administration were observed, and contrast enhancement on VFSS images was comparable to that achieved with Barytester®. Japan Registry of Clinical Trials, jRCTs061240040; registered 26 July, 2024.
Cone Beam Computed Tomography (CBCT) is a widely used imaging technology in dentistry, requiring specialized training and a specific license in Germany. This study aimed to evaluate the effectiveness of an e-learning platform for acquiring CBCT knowledge and to examine participant satisfaction and experiences. The study included German dentists, half with CBCT license and half without. The participants completed an online pre-test with 15 image-based questions to assess basic knowledge and then were given access to the e-platform containing 104 annotated CBCT cases (e.g. implant planning, cysts, or impacted teeth). After 8–10 weeks, a post-test similar to the pre-test was conducted. An 11-item questionnaire recorded participant experience. Data were analysed using independent and paired t-tests, and Fisher’s exact test; p < 0.05 was considered statistically significant. Between May and October 2025, 32 dentists participated in the study (16 with and 16 without CBCT license). Learning with the e-learning platform led to a significant increase in knowledge (p < 0.001). Participants with CBCT license had higher baseline scores than those without (75.8
Basaloid squamous cell carcinoma (BSCC) is a rare, high-grade variant of SCC. In the oral cavity, BSCC predominantly originates from the floor of the mouth and base of the tongue and is characterized by aggressive behavior, with frequent nodal and distant metastases. To date, no case has comprehensively reported BSCC findings across multiple imaging modalities in a single patient. A 78-year-old male presented with persistent erythema, swelling, and pain in the anterior mandible. Clinical examination revealed exposed bone with an exophytic soft tissue mass and cutaneous fistula. The lesion was initially suspected to represent osteoradionecrosis following prior management of SCC (pT1N0M0) with laser resection, neck dissection, and radiotherapy. However, disease recurrence could not be excluded. Panoramic radiography showed an ill-defined radiolucency in the anterior mandible. CT revealed a 55 × 20 × 48 mm inhomogeneously enhancing mass with associated bone destruction and extending to the skin. MRI demonstrated alveolar and labial cortical bone destruction, with soft tissue component isointense to muscle on T1-weighted images and heterogeneous high signal on T2-weighted and T1-weighted contrast enhanced images. PET-CT showed high FDG uptake (SUVmax: 17.2) without nodal or distant metastasis. Biopsy findings were suggestive of BSCC, which was confirmed by histopathologic examination of the resected lesion. This report highlights the utility of multimodal imaging in lesion characterization and supporting clinical decision-making, while the histopathological examination remains the gold standard for the definitive diagnosis. It also underscores the importance of vigilant follow-up in patients with oral BSCC for early detection of local recurrence and distant metastases.
In patients with multiple myeloma (MM), the use of contrast agents is generally contraindicated owing to the risk of acute renal failure. Despite precautionary statements in package inserts, guidelines note that the supporting evidence is limited. We report the case of a patient diagnosed with MM following contrast-enhanced computed tomography (CT) and discuss the clinical implications of contrast agent use. A 77-year-old woman presented with numbness of the right lower lip. Panoramic radiography revealed a radiolucent lesion with an unclear border in the right mandible. Contrast-enhanced CT, performed for suspected jaw carcinoma, demonstrated enhancing masses not only in the right mandible but also in the right skull, raising suspicion for MM. No adverse events were reported following contrast administration. A biopsy of the right mandibular lesion revealed plasma cell myeloma, and bone marrow aspiration confirmed symptomatic MM. Systemic chemotherapy resulted in tumor regression without renal dysfunction. Although renal failure occurs in approximately half the patients with MM, the risk of contrast-induced nephropathy is low in patients with normal creatinine levels, and contrast-enhanced CT does not appear to worsen renal function. When malignancy of the oral cavity is suspected, contrast-enhanced imaging may improve diagnostic accuracy. Further studies are needed to clarify the risk–benefit balance of contrast use in patients with MM without renal dysfunction, considering disease prevalence and the potential loss of diagnostic capability.
To evaluate the influence of blue-light filtering on the diagnosis of different dental conditions (internal and external root resorptions, horizontal and vertical root fractures, and furcation defects) in intraoral digital radiographs. The study used 10 mandibles, 8 dry skulls, and 60 single-rooted teeth distributed according to the induction of the different pathological conditions. The conditions were simulated using specific methodologies for each type of lesion with mechanical processes or combined with chemical processes. Digital radiographs were acquired using the KaVo eXam digital system. The obtained images were randomized and evaluated individually by 11 evaluators, using a 5-point scale, as to the absence or presence of each condition. The images were evaluated using Windows 11 blue-light filtering with four intensities: 0
The aim is to present a dental-dedicated magnetic resonance imaging (ddMRI)-based diagnosis and follow-up in a clinical case of apical periodontitis (AP) on a root canal treated (RCT) tooth. Persistent AP in RCT teeth can be difficult to distinguish from scar tissue or incomplete healing. In the absence of symptoms, no currently known imaging method can verify the presence of inflammation. ddMRI is a novel imaging modality proposed for dentistry, that has the potential to reveal inflammation. A 50-year-old male presented with mild symptoms from a previously RCT 36. ddMRI suggested mild inflammation, and an intraoral image revealed a periapical radiolucency. The tooth was non-surgically endodontically retreated. During follow-up, no exacerbation of the inflammation was detected on ddMRI. However, one year after retreatment, a periapical radiolucency persisted, and the ddMRI indicated that the inflammation had not resolved. Surgical endodontic retreatment was performed, and a tissue sample was retrieved from the periapical area. A histopathological analysis revealed inflammation as suspected from the hyperintense signal seen on ddMRI. Despite treatment, the inflammation did not resolve, and after development of a fistula, the tooth was extracted.
OBJECTIVES:Cone Beam Computed Tomography (CBCT) provides detailed anatomical information for treatment planning in dentistry. However, manually identifying tooth and jawbone structures is time-consuming and can vary depending on the observer. The aim of this study is to analyze the performance of U-Net, DeepLab V3+, and YOLO V3 deep learning architectures for automatic segmentation of tooth and jawbone structures in CBCT images. METHODS:This study utilized CBCT data from seven different patients. A total of 1,155 axial images were expertly labeled in terms of tooth and jawbone regions. The dataset was trained with U-Net, DeepLab V3+, and YOLO V3-based semantic segmentation models. The learning rate, number of epochs, and batch size parameters of the models were optimized using the GridSearch method. Dice Similarity Coefficient (DSC), Intersection over Union (IoU), precision, and recall performance evaluation metrics were used in the performance assessment. RESULTS:Successful results were obtained in tooth and jawbone segmentation in all deep learning models used in the study. Among the models used in the article, the most successful performance was obtained from the U-Net architecture. The U-Net model achieved DSC=0.9289, IoU=0.8671, precision=0.9213, and recall=0.9365 values with a learning rate of 0.001, 70 epochs, and 16 batch size parameters. The DeepLab V3+ deep learning algorithm also yielded similar results, while YOLO V3 showed lower performance compared to other models. CONCLUSION:Deep learning-based segmentation methods provide high accuracy in the automatic determination of tooth and jawbone structures in CBCT images. Among the deep learning models used in the study, U-Net was identified as the most successful model. The approach developed in this study has the potential to support treatment planning in dental applications and reduce the burden of manual segmentation. However, the method needs to be validated with larger, multi-center datasets before it can be put into clinical use.
Pleomorphic adenoma (PA) is the most common benign parotid tumour. Magnetic resonance imaging (MRI) and fine-needle aspiration cytology (FNAC) are routinely used during preoperative work up. However, there is insufficient evidence to support the use of MRI alone to diagnose a PA. This paper aims to evaluate the diagnostic performance of MRI and FNAC in the diagnosis of PA and develop an MRI assessment tool to potentially reduce an invasive biopsy. A retrospective cohort study was conducted in 155 patients with histopathologically confirmed parotid tumours with preoperative MRI and/or FNAC between 2015 and 2020. Two experienced head and neck radiologists, both with over 20 years’ experience, blinded to final histopathology, evaluated 100 MRIs. Diagnostic values for detecting PA with MRI and FNAC were evaluated. An MRI assessment tool was developed based on clinical criteria and MRI characteristics typical for a PA. The sensitivity, specificity, positive predictive value (PPV), negative predictive value, (NPV) and diagnostic accuracy for predicting PA were 93
Objectives Undiagnosed anterior disc displacement (ADD) and anterior disc displacement without reduction (ADDwoR) during orthodontic treatment can compromise treatment outcomes and long-term stability. This study aimed to establish quantitative decision-support models for stratifying ADD and its subtypes based on the temporomandibular joint (TMJ) radiological morphology in order to address the diagnostic challenges in orthodontic patients with dentofacial deformities. Methods In this retrospective diagnostic study, 72 patients (144 TMJs) awaiting orthodontic treatment were allocated to a modeling group (n = 61) and an independent internal validation group (n = 11), with TMJ imaging indicators (joint space, disc thickness, condylar dimensions, and condylar volume) quantified using CBCT and MRI. TMJs were stratified into normal, anterior disc displacement with reduction (ADDwR), or ADDwoR groups according to MRI disc-condylar angle. Diagnostic models were developed using Spearman’s correlation analysis, logistic regression, and were visualized as nomograms, with internal validation via the Bootstrap method and independent internal validation using the validation group. Model reliability was evaluated using the intraclass correlation coefficient (ICC), goodness-of-fit tests, and McNemar tests, while discriminative ability was assessed via receiver operating characteristic (ROC) curve analysis. Results Two logistic regression models were developed. The ADD diagnosis model (AUC = 0.925) included anterior joint space, posterior band thickness, and condylar diameters (APCD and MLCD); the ADDwoR subclassification model (AUC = 0.898) incorporated anterior band thickness, middle band thickness, and condylar volume. Optimized thresholds (0.629, 0.748) had sensitivities (75.8%, 90.6%), specificities (87.1%, 78.2%), and good consistent calibration curves (P > 0.05), with no validation group-reference differences (P = 0.063, 0.125). Conclusions The developed logistic regression models could be explored as a potential imaging-based tool for ADD subtyping, offering supplementary information in orthodontic clinical decision-making for ambiguous TMD cases and potentially aiding treatment planning in orthodontic and craniofacial practice.
To investigate demographic, morphologic, and morphometric variables associated with early or subclinical imaging-based osteoarthritic structural changes of temporomandibular joint (TMJ). Cone-beam computed tomography scans of 396 TMJs from 198 asymptomatic individuals (75 males, 123 females) were analyzed. TMJs were classified as normal-appearing, indeterminate for osteoarthritis (OA), or affected by OA based on condyle, and fossa/eminence morphology. Univariate and multivariate logistic regression models assessed the association of 5 patient-level and 20 TMJ-level variables with the indeterminate or affected by OA status, adjusting for confounding. Prevalence rates of the indeterminate and affected by OA statuses were 25.80
Artificial intelligence and deep learning have expanded dental imaging analysis by enabling automated detection, classification, localization, segmentation, and tooth identification in routinely acquired radiographs. This review provides a practice-oriented synthesis that links the clinical question and required output type to what reported performance actually implies for use in dental care. Using a structured, semi-systematic literature search with quantitative eligibility criteria, we synthesize findings across major application areas including odontogenic cysts and tumors, periapical and apical radiolucencies, dental caries, periodontal bone loss assessment and staging, oral cancer screening, multi-condition diagnosis, and automated tooth numbering. Across these tasks, studies consistently report stronger results for clearly visible pathology and well-defined boundaries, while early-stage disease, small lesions, overlapping anatomy, and restoration-related artifacts drive the most important failure modes. We also highlight why cross-study comparisons are often unreliable due to differences in reference standards, class taxonomies, units of analysis, preprocessing and region-of-interest assumptions, and the frequent absence of external validation. Clinically, the most credible near-term role is calibrated decision support for case prioritization and clinician verification, supported by auditable spatial outputs. Future progress is most directly enabled by multi-center validation, severity-aware reporting, and calibration or uncertainty handling that is aligned with workflow use.
