Search Results (2,423)

Early non-invasive correction of neonatal auricular deformities is highly dependent on timely and precise diagnosis. However, clinical practice is often compromised by the subjectivity of visual assessments and the lack of objective tracking metrics, which frequently leads to missed optimal treatment windows. To address these challenges, we developed an interpretable deep learning-based diagnostic system for the automated screening and fine-grained classification of these deformities. Methodologically, a large-scale, multi-source dataset (n = 4644) was curated to support model training. The system pairs an automated object detector (YOLOv11) for background-reduced region-of-interest isolation with a cascaded classification pipeline optimized via ConvNeXt-Tiny. Crucially, we introduced a supervised contrastive learning module to project high-dimensional morphological features into a continuous severity score, enabling quantitative longitudinal tracking of therapeutic efficacy. To evaluate generalization and robustness, the framework underwent rigorous evaluation across three independent real-world cohorts and one controlled synthetic stress test. The system achieved 88.2% accuracy (Area Under the Curve (AUC): 0.949) in binary screening and 87.4% accuracy (macro-AUC: 0.976) in multi-class subtyping on the internal baseline. To enhance interpretability and build clinical trust, Gradient-weighted Class Activation Mapping (Grad-CAM) was utilized to explore the spatial distribution of the model’s attention, which frequently aligned with key anatomical landmarks. Furthermore, the learned severity scores robustly quantified post-intervention improvements (p = 0.0004), effectively capturing subtle anatomical normalization. While validation for rare subtypes remains underpowered, and the severity score currently functions mainly as a learned morphological similarity index requiring future clinical calibration, this study ultimately provides an objective and standardized web-based tool to facilitate the early intervention and precision management of neonatal auricular anomalies. Full article

Background/Objectives: Spontaneous intracranial hypotension (SIH) is caused by spinal cerebrospinal fluid (CSF) leakage and is typically diagnosed by clinical presentation and characteristic MRI signs; however, objective tools for monitoring physiological changes and treatment response remain limited. Cine phase-contrast MRI (PC-MRI) enables noninvasive quantification of aqueductal CSF dynamics, yet reliable analysis is challenging since the cerebral aqueduct is extremely small and susceptible to low contrast, partial volume effects, and ROI-dependent measurement variability—particularly in SIH where CSF pulsatility is often reduced. Methods: We propose an end-to-end automated framework that integrates (1) a cascade localization–segmentation strategy, consisting of Tiny YOLOv4 detection followed by MultiResUNet segmentation on a YOLOv4-derived cropped ROI; (2) physiology-informed pulsatility-based segmentation (PUBS) to refine anatomical masks into functional flow ROIs; and (3) one-dimensional convolutional neural networks (1D-CNNs) to extract exploratory waveform morphology features from 32-phase cardiac-cycle velocity waveforms. The study includes 39 participants, yielding 59 cine PC-MRI examinations: 11 controls, 28 Pre-treatment SIH scans and 20 Post-treatment Recovery scans. Results: The cascade model significantly improves segmentation robustness compared with a full-image baseline, achieving higher Dice scores and markedly lower boundary errors across cohorts (e.g., Pre-treatment SIH HD95: 1.66 ± 0.74 px vs. 15.37 ± 44.98 px). PUBS refinement reduces quantification deviation from expert manual references in SIH (mean relative error: 7.4% to 5.6%) and improves diagnostic performance for multiple hemodynamic parameters (e.g., downward mean flow AUC: 0.747 to 0.792). For waveform morphology analysis, the end-to-end 1D-CNN classifier was evaluated using repeated-seed participant-level grouped LOOCV. The repeated-seed ensemble prediction showed modest out-of-sample discrimination between Normal controls and Pre-treatment SIH scans, with an AUC of 0.646, a bootstrap 95% confidence interval of 0.455–0.826, and a permutation-test p-value of 0.072. Separately, exploratory analysis of the final baseline-trained 1D-CNN latent space showed marked, apparent Normal-versus-SIH separability and an intermediate recovery distribution in PCA space, suggesting that aqueductal waveform morphology may encode SIH-related physiological information. Conclusions: These findings suggest that SIH-related information may be reflected not only in flow magnitude but also in aqueductal CSF waveform morphology. However, the modest and statistically non-significant out-of-sample performance of the end-to-end 1D-CNN classifier indicates that morphology-based AI features should currently be regarded as exploratory biomarker candidates rather than validated stand-alone diagnostic tools. Larger independent cohorts are required to confirm their reproducibility, physiological meaning, and clinical utility. Full article

Sublobar pulmonary resection has become an increasingly adopted approach for early-stage non-small cell lung cancer, driven by evidence that anatomical segmentectomy can achieve oncological outcomes comparable to lobectomy in selected patients. Safe execution of sublobar resection depends on accurate preoperative identification of segmental bronchovascular anatomy, which demonstrates substantial variability. Conventional two-dimensional (2D) computed tomography (CT) imposes significant limitations on anatomical interpretation, particularly at the segmental and subsegmental level. Three-dimensional (3D) bronchovascular modelling provides patient-specific representations of segmental anatomy and relationships that address these limitations. This narrative review examines the current and emerging roles of 3D modelling in personalised thoracic surgery. It discusses the anatomical basis for its application, the limitations of conventional imaging, and the contribution of 3D modelling to preoperative planning and intraoperative decision making. It also considers broader applications, current limitations, and future directions, with emphasis on how patient-specific 3D modelling can support more tailored operative strategies and more individualised surgical care. Full article

Objectives: Peripheral nerve ultrasound is used to evaluate nerve enlargement in immune-mediated neuropathies; however, assessment can be challenging because the distribution and severity of nerve enlargement vary among patients and are often accompanied by indistinct nerve boundaries and heterogeneous echogenicity. Although deep learning-based segmentation has been reported, most studies have focused on limited regions or single anatomical sites, primarily in compressive neuropathies. This study aimed to evaluate the performance of temporal deep learning-based segmentation for assessing diffuse or focal nerve enlargement in immune-mediated neuropathies using continuous ultrasound scans. Methods: Twenty-five healthy participants and five patients with immune-mediated neuropathy and nerve enlargement were included. Continuous ultrasound scanning from the wrist to below the elbow was performed. A static DeepLabV3+ model and temporal models incorporating convolutional long short-term memory (ConvLSTM) or Temporal Mamba were constructed and compared. Results: In healthy participants, segmentation performance was comparable across models. In contrast, in patients with nerve enlargement, temporal models demonstrated higher Dice coefficients and reduced frame-to-frame variability. The ConvLSTM-based model showed the highest performance, with mean Dice coefficients ranging from 0.87 to 0.92. Conclusions: Temporal deep learning showed potential for nerve segmentation in selected cases with nerve enlargement associated with immune-mediated neuropathies. Temporal models achieved improved segmentation performance and reduced frame-to-frame variability in these preliminary cases. This approach may facilitate more consistent quantitative ultrasound evaluation and warrants further validation in larger cohorts. Full article

This review aims to evaluate the potential of endometriosis models, especially patient-derived iPSC models, to gain deeper insights into the disease, thereby advancing our understanding and treatment of endometriosis. This comprehensive narrative review utilized a structured search of the PubMed, Scopus, and Web of Science databases, primarily covering literature published between January 2000 and May 2025. An expansive search strategy was employed to capture the full breadth of the field using keywords such as “endometriosis,” “induced pluripotent stem cells (iPSCs),” “patient-derived organoids,” “disease modeling,” and “epigenetics” without restrictive filtering, ensuring the integration of both foundational theories and emerging biotechnological advances. In total, over 170 peer-reviewed publications were analyzed, ranging from landmark genomic meta-analyses that have identified significant risk loci to state-of-the-art 3D-culture systems for modeling patient-specific endometrial disease. By synthesizing these diverse sources, the review bridges the gap between traditional anatomical classifications and modern molecular modeling to evaluate the potential of iPSC platforms for personalized medicine and therapeutic discovery. Endometriosis is a multifactorial gynecological condition that affects 176 million women worldwide and can significantly impair quality of life. It occurs when endometrium-like tissue grows outside the uterus, responsive to ovarian hormones, causing inflammation, pain, and discomfort, and leading to fibrotic tissue. World Health Organization estimates indicate that 6–10% of women suffer from this disorder, which can cause infertility and increase the risk of developing various types of cancer and autoimmune disorders. The use of patient-derived iPSC models serves to gain deeper insights into the disease by mimicking the endometrial tissue or lesions observed in affected individuals, thereby advancing our understanding and treatment of endometriosis. Full article

Background/Objectives: A macular hole represents a significant surgical condition in an increasingly aging population. Advances in surgical techniques, particularly pars plana vitrectomy with inverted internal limiting membrane (ILM) flap, have established high anatomical closure rates exceeding 90%. The prognostic factors influencing visual recovery remain incompletely understood, and it is unclear which patients can be expected to achieve optimal functional outcomes. Methods: This retrospective longitudinal study included 35 eyes of 32 patients followed for 3–12 months. Preoperative OCT parameters (minimum linear diameter, basal diameter, and hole height) and derived indices were correlated with functional outcomes, including best-corrected visual acuity (BCVA) and microperimetry, stratified as central macular sensitivity (CMS) and sensitivity at 4° and 20°. Postoperative ellipsoid zone (EZ) and external limiting membrane (ELM) integrity were also analyzed. Predictive performance was assessed using root mean square error (RMSE) and coefficient of determination (R²). A linear regression model based on BCVA served as baseline, while Extreme Gradient Boosting (XGBoost) models incorporating OCT features were developed. Feature importance was evaluated using Shapley Additive Explanations (SHAP). Results: Overall closure rate was 100%, including 91.4% Type 1 and 8.6% Type 2 closure. Models incorporating OCT parameters outperformed BCVA-based models (lower RMSE, and higher R²). Minimum linear diameter and hole height were the strongest predictors of postoperative outcomes. Microperimetry detected functional improvement beyond BCVA and correlated with EZ and ELM restoration. Conclusions: Preoperative macular hole morphology represents a key determinant of postoperative functional recovery. These structural parameters provide meaningful prognostic value beyond visual acuity alone, supporting the role of combined OCT and microperimetric assessment in predicting surgical outcomes. Full article

Artificial intelligence (AI) is reshaping the field of diagnostic radiology; however, its applications in interventional radiology and pediatric interventional radiology (PIR) remain limited despite clear clinical needs and the rich multimodal data environment characteristic of pediatric procedural care. In this narrative review, I summarize the current state of AI technologies relevant to PIR and outline future perspectives for their clinical integration. Peer-reviewed literature and position statements identified through MEDLINE/PubMed, Embase, Scopus, and major society publications up to the first quarter of 2026 are synthesized, focusing on AI applications across the PIR care pathway, including dose-sparing image acquisition and reconstruction, automated image interpretation and computer-aided diagnosis, data-driven procedural planning and navigation, and post-procedural risk prediction and monitoring. After briefly introducing core machine learning and deep learning concepts, pediatric-specific challenges are discussed, including radiation sensitivity, growth-related anatomical variability, regulatory constraints, and the scarcity of large, annotated datasets, as well as existing and emerging applications along the PIR care pathway: AI-assisted dose reduction and image reconstruction, automated image interpretation, segmentation, and computer-aided diagnosis; data-driven procedural planning, including three-dimensional modelling, augmented reality, AI-enabled/AI-adjacent robotics, and AI-directed procedural navigation; and post-procedural risk prediction and outcome monitoring. Finally, emerging paradigms, including explainable AI, federated learning, and multimodal integration, are highlighted, and research priorities, collaborative frameworks, and governance principles required to ensure safe, equitable, and effective AI deployment in PIR are outlined. In doing so, this review delineates the current evidence gaps and priority directions for clinically meaningful AI adoption in PIR. Although AI has the potential to improve patient care, it has not yet been specifically designed, validated, or deployed in children. Existing work demonstrates feasibility across the PIR workflow, but most tools remain weakly linked to pediatric clinical endpoints. Full article

Background: Coronary anatomical complexity is commonly used for perioperative risk assessment in patients undergoing coronary artery bypass grafting (CABG), although it may not fully reflect systemic biological vulnerability. This study aimed to evaluate the association between the Prognostic Nutritional Index (PNI), a nutritional–immune marker derived from serum albumin and lymphocyte counts, and in-hospital mortality after CABG in relation to coronary anatomical complexity and established surgical risk scores. Methods: In this single-center retrospective cohort study, 324 consecutive patients who underwent isolated CABG between April 2024 and April 2025 were analyzed. The PNI was calculated according to the standard Onodera formula using preoperative serum albumin and total lymphocyte count. Associations with in-hospital mortality were evaluated using univariable and multivariable logistic regression analyses. Discriminative performance was assessed using receiver operating characteristic curve analysis, while exploratory analyses evaluating the additional prognostic contribution of the PNI beyond surgical risk scores were performed using nested model comparison and reclassification analyses. Internal validation and calibration analyses were also performed. Results: In-hospital mortality occurred in 26 patients. Preoperative and postoperative PNI values were significantly lower in patients who experienced in-hospital mortality. In multivariable analysis, the postoperative PNI remained independently associated with in-hospital mortality, whereas the preoperative PNI lost statistical significance after adjustment for clinical, renal, and surgical risk parameters. Receiver operating characteristic analysis demonstrated modest discriminative ability for the preoperative PNI (AUC: 0.742, 95% CI: 0.661–0.823). Exploratory analyses suggested a modest improvement in model discrimination and risk classification after the addition of the PNI to STS-based models; however, the overall incremental prognostic contribution remained limited. Calibration and internal validation analyses demonstrated acceptable agreement between predicted and observed mortality risk. Conclusions: The postoperative PNI demonstrated a stronger and independent association with in-hospital mortality than the preoperative PNI, suggesting that early postoperative nutritional–immune deterioration may reflect the magnitude of perioperative physiological stress and evolving clinical deterioration after CABG. Although lower preoperative PNI values were associated with mortality in univariable analyses, this association was no longer statistically significant after adjustment for clinical, renal, and surgical risk parameters. These findings indicate that postoperative nutritional–immune status may provide complementary biological information beyond conventional risk models; however, its clinical utility requires confirmation in larger prospective multicenter studies. Full article

Background: Advances in additive manufacturing and CAD/CAM technologies have expanded the use of 3D-printed orthodontic models in digital aligner workflows. Intraoral scanners (IOS) are critical for accurately capturing attachment geometries and dental morphology during these workflows. However, comparative evidence regarding IOS accuracy in models with complex orthodontic structures remains limited. Therefore, this study aimed to compare the trueness and precision of five IOS using 3D-printed orthodontic models with attachments. Methods: In this in vitro study, thirty independent single-arch 3D-printed models (either maxillary or mandibular) with orthodontic attachments were scanned twice with each IOS. The Smart Optics Vinyl laboratory scanner served as the reference scanner. Scans were aligned and superimposed in CloudCompare, and root mean square (RMS) deviation values were calculated to evaluate accuracy. Nonparametric Kruskal–Wallis and Dunn tests were applied (α = 0.05). Results: Significant differences were found among scanners for both trueness and precision (p < 0.001). Primescan, TRIOS 3, and iTero element 5D demonstrated comparable trueness (p > 0.05) and outperformed Rapideye MI-1000 (p < 0.001). iTero element 2 plus showed slightly lower accuracy but remained clinically acceptable. Primescan achieved the highest precision, significantly exceeding iTero element 2 plus, iTero element 5D, and Rapideye MI-1000 (p < 0.01). TRIOS 3 also exhibited excellent repeatability, comparable to Primescan (p = 1.000). Conclusions: All intraoral scanners, except Rapideye MI-1000, demonstrated accuracy levels generally considered clinically acceptable for digital orthodontic and additive manufacturing workflows. Primescan, TRIOS 3, and iTero element 5D exhibited similarly high trueness, while Primescan showed the most consistent precision. The ability of these scanners to reproduce fine anatomical details may improve the reliability of 3D-printed orthodontic models and in-office aligner production workflows. Full article

Background/Objectives: Optical coherence tomography (OCT) and OCT angiography (OCT-A) provide detailed measurements of retinal structure and vasculature; however, age-related differences in how these parameters correlate with one another remain poorly understood. We hypothesized that vascular–structural integration in the macula is more pronounced in adults than in children. Our aim was to characterize correlation patterns in pediatric and adult populations to inform the development of age-specific clinical interpretation guidelines. Methods: This prospective cross-sectional observational study enrolled 37 healthy children (age 1–17 years) and 28 healthy adults (age 18–65 years). Eyes with ocular or systemic conditions affecting the retina or prior intraocular surgery were excluded. Standardized OCT and OCT-A acquisition protocols provided structural and vascular measures. Univariable correlation analyses applied a stringent threshold (p < 0.001) to identify robust associations. Significant univariable results were entered into multivariable regression models adjusting for age, gender, intraocular pressure, and axial length. A Group-wise Linkage Proportion quantified the percentage of potential significant correlations among eight predefined anatomical parameter groups. Results: Ninety univariable correlations met p < 0.001. Fourteen correlations were shared across age groups, notably foveal avascular zone metrics and vessel density, showing very large negative correlations (r = −0.70 to −0.87). The pediatric cohort displayed 40 unique correlations, primarily linking optic nerve head flow indices to retinal nerve fiber layer thickness. Adults exhibited 36 unique correlations, dominated by macular vascular–thickness coupling concentrated in the parafoveal region. After multivariable adjustment, 52 of 90 associations remained significant. Adult-specific associations lost significance more frequently (58%) than pediatric-specific associations (43%), whereas correlations shared across both groups showed complete stability (100%). The Group-wise Linkage Proportion indicated pronounced macular vascular–structural coupling in adults (48.4%) versus near absence in children (1.2%). Conclusions: Retinal parameter correlation patterns show fundamental differences between pediatric and adult eyes. While optic nerve head-macular thickness relationships remain consistent across ages, adults exhibit mature, localized integration of macular vascular and structural parameters absent in children. These findings suggest that pediatric and adult OCT/OCT-A measurements may benefit from separate reference standards, although prospective validation is required before clinical implementation. Full article

Background/Objectives: Implant placement in transnasal and paranasal regions of the severely atrophic maxilla is challenged by complex anatomy and proximity to critical structures, particularly the nasolacrimal duct (NLD). While cortical anchorage is considered important for implant stability, structured methods for evaluating anatomical eligibility and anatomical risk during planning remain limited. This proof-of-concept study aimed to describe a segmentation-assisted workflow for anatomical assessment of potential paranasal implant trajectories. Methods: A single-case proof-of-concept workflow was developed using CBCT imaging and multi-component anatomical bone segmentation (MCABS). Segmented anatomical structures were used to selectively visualize cortical pathways within the anterior maxilla. Implant planning was performed using axial, non-tilted trajectories. Particular attention was directed toward visualization of the spatial relationship between the planned implant pathway and the nasolacrimal duct. Workflow feasibility was further explored through study-model fabrication, guided implant insertion, and axis-based verification. Results: The proposed workflow enabled selective visualization of cortical structures and facilitated identification of anatomically favorable implant trajectories within the paranasal region. The relationship between the planned implant pathway and the nasolacrimal duct could be directly assessed using the segmented anatomical model. Guided insertion in the study model demonstrated concordance between planned and executed implant axes, supporting the technical feasibility of the workflow. Conclusions: Within the limitations of a single-case proof-of-concept study, the proposed segmentation-assisted workflow may contribute to preoperative anatomical assessment of potential paranasal implant trajectories and their relationship to adjacent anatomical structures. The workflow should be regarded as a methodological demonstration rather than a validated clinical protocol. Further anatomical, reproducibility, biomechanical, and clinical studies are required before broader clinical adoption can be considered. Full article

Dental diseases have long been taught and treated as separate entities: cariology, operative dentistry, endodontics, and periodontology, each working within its own boundaries. However, increasing biological and clinical evidence suggests that this classified view does not fully reflect how disease progresses in the mouth. Instead, dental disease should be understood as a continuum within the interconnected tooth–pulp–periodontium complex. This review provides current evidence showing how dental caries can serve as the starting point of a process that can progress through pulpitis and apical periodontitis and eventually affect surrounding periodontal tissues. Caries is now widely known as a biofilm-driven and host-influenced condition shaped by ecological imbalance rather than specific pathogens alone. As lesions penetrate deeper into dentin, the structure becomes more permeable, permitting diffusion of microbial metabolites and signaling molecules toward the pulp. This initiates a multifaceted inflammatory reaction within the pulp tissue. At this stage, pulpitis becomes a critical turning point, where the outcome depends on microbial load, lesion activity, host response, and quality of clinical intervention. If the disease is not well controlled, it may lead to pulp necrosis, allowing infection to spread beyond the root canal and initiate periapical inflammation. Through anatomical pathways such as apical foramina and lateral canals, these processes can extend further, sometimes resembling or overlapping with periodontal disease. This overlap creates diagnostic challenges, as conventional tests may not always distinguish between conditions. A structured, pathway-based diagnostic approach is therefore essential. From a treatment perspective, this continuum model highlights early intervention, minimally invasive care, preservation of pulp vitality when possible, and maintenance of a strong coronal seal. Ultimately, stronger integration across dental disciplines can improve diagnosis, guide treatment decisions, support long-term tooth preservation, and promote unified dental education. This article presents a narrative review supported by a structured literature search and proposes a clinically actionable framework that extends established endodontic–periodontal concepts upstream to include caries initiation and restorative modulation. Full article

In this study, we evaluate the diagnostic performance of a U²-Net-based artificial intelligence (AI) model for identifying the pterygomaxillary fissure on dental panoramic radiographs and investigate its potential utility as a supportive tool for preliminary anatomical landmark identification and pre-surgical screening. A total of 270 panoramic radiographs showing at least one fully visible pterygomaxillary fissure were retrospectively selected. In these anonymized images, 501 pterygomaxillary fissures were identified and manually annotated by two independent examiners using CVAT v1.7.0 labeling software. On the test dataset, the segmentation model achieved a Dice coefficient of 0.904 (95% CI: 0.876–0.930) and an Intersection over Union (IoU) of 0.846 (95% CI: 0.810–0.879). Precision and recall values were 0.921 and 0.902, respectively, yielding an F1-score of 0.911. During training, the highest validation Dice coefficient reached 0.910, with a validation IoU of 0.844 and validation accuracy of 0.998. These findings demonstrate that the proposed model shows strong performance in accurately segmenting the pterygomaxillary fissure on panoramic radiographs and may serve as a supportive tool for preliminary anatomical landmark identification during initial anatomical assessment. Full article

Impaction of the mandibular third molar in proximity to the mandibular canal increases the risk of inferior alveolar nerve injury. Panoramic radiography is routinely used to assess this relationship. Automated classification of molar–canal overlap could support clinical triage and reduce unnecessary CBCT referrals, while Federated Learning (FL) enables multi-center collaboration without sharing patient data. We compared Local Learning (LL), FL, and Centralized Learning (CL) for binary overlap/no-overlap classification on cropped panoramic radiographs partitioned across eight independent labelers in a simulated heterogeneous multi-center setting. A pretrained ResNet-34 was trained under each paradigm and evaluated using per-client metrics with locally optimized thresholds and pooled test performance with a global threshold. Performance was assessed using area under the receiver operating characteristic curve (AUC) and threshold-based metrics, alongside training dynamics, Grad-CAM visualizations, and server-side aggregate monitoring signals. On the test set, CL achieved the highest performance (AUC 0.831; accuracy ≈ 0.782), FL showed intermediate performance (AUC 0.757; accuracy ≈ 0.703), and LL generalized poorly across clients (AUC range ≈ 0.619–0.734; mean ≈ 0.672). Training curves suggested overfitting, particularly in LL models, and Grad-CAM indicated more anatomically focused attention in CL and FL. Overall, centralized training provided the strongest performance, while FL offers a privacy-preserving alternative that outperforms LL. Full article

Background: Selenium (Sel) supplementation has been proposed as an antioxidant adjunct in Graves’ orbitopathy (GO), with early randomized evidence suggesting benefits in quality of life (QoL), ocular involvement, and disease progression in mild GO. However, subsequent trials across populations with different Sel status and disease severity have yielded inconsistent findings. This systematic review and meta-analysis of randomized controlled trials (RCTs) reassessed the efficacy of Sel supplementation in GO. Methods: PubMed, Scopus, and the Cochrane Library were searched from inception to 1 May 2026 for RCTs, comparing Sel supplementation with placebo or no Sel supplementation in patients with GO (PROSPERO “CRD420261395074”). Heterogeneity was assessed using I² statistics and Cochran’s Q test. Risk ratios (RRs) were calculated using the Mantel–Haenszel method, and mean differences (MDs) using the Inverse-Variance method. Random-effects models with restricted maximum-likelihood estimation were applied. Results: Five RCTs including 303 patients were analyzed, of whom 165 (56%) received Sel. Sel supplementation was associated with a significant reduction in clinical activity score (MD −1.05; 95% CI −1.61 to −0.48; I² = 52%; p < 0.01). No significant differences were observed in palpebral aperture (MD −0.12; 95% CI −1.22 to 0.98; I² = 58%; p = 0.83), although this anatomical parameter should be interpreted cautiously because it may be influenced by thyroid functional status and hyperthyroidism-related Müller muscle hyperfunction. No significant differences were observed in QoL improvement (RR 1.72; 95% CI 0.43 to 6.92; I² = 86%; p = 0.24) or visual function (MD 6.31; 95% CI −1.40 to 14.03; I² = 45%; p = 0.11). Conclusions: Sel supplementation may improve clinical activity score in patients with Graves’ orbitopathy, but this finding should be interpreted cautiously given the small number of trials, limited sample size, and clinically relevant heterogeneity. Current evidence does not show consistent benefits for palpebral aperture, quality of life, or visual function. Larger RCTs stratified by baseline Sel status and disease severity are needed before firm conclusions can be drawn. Full article