Search Results (1,376)

Background/Objectives: Accurate and reproducible lymph node (LN) measurement is essential for oncologic staging and therapy monitoring but is subject to inter-reader variability. This study evaluated the accuracy and reproducibility of a fully automated artificial intelligence (AI)-based LN measurement workflow in contrast-enhanced chest CT, using multi-reader manual measurements as reference. Methods: Sixty thoracic LNs from seven patients were independently measured by 13 radiologists in two reading rounds. The median of all measurements served as the ground truth (GT). Automated short- and long-axis diameters were derived from fully automated 3D CNN-based segmentations. Agreement between AI and manual measurements was assessed using Friedman testing, intraclass correlation coefficients (ICCs), and concordance correlation coefficients (CCCs). Measurement stability was evaluated across repeated runs on different hardware systems. Results: A total of 2280 manual measurements were analyzed. Manual assessment showed significant inter-reader variability (p < 0.01), while intra-reader agreement was high. No significant differences were observed between AI-based measurements and the GT (all p > 0.01). Agreement was good, with CCC values of 0.86 (SAD) and 0.79 (LAD). AI-based measurements were numerically stable across hardware configurations. Conclusions: Fully automated AI-based LN measurements in chest CT scans provide strong agreement with multi-reader consensus and high numerical stability. Automated measurement may support more standardized and reproducible oncologic imaging assessment. Full article

Background/Objectives: Contrast-associated acute kidney injury (CA-AKI) remains an important cause of morbidity and mortality in patients undergoing procedures that require intravascular contrast administration. Therefore, the early identification of high-risk individuals is paramount, above all for ST-segment elevation myocardial infarction (STEMI) patients in need of urgent percutaneous coronary intervention (PCI). Methods: This retrospective study evaluated the prognostic value of the Pan-Immune-Inflammation Value (PIV), a composite inflammatory index, in predicting CA-AKI among patients presenting with STEMI who received urgent PCI within a 12 h window from the onset of symptoms. Results: This study recruited 2325 patient. CA-AKI was defined as a >25% or ≥0.5 mg/dL increase in serum creatinine within 48–72 h after the procedure. Patients were categorized into CA-AKI (+) and CA-AKI (−) groups. PIV levels were significantly higher in patients who developed CA-AKI (502.5 ± 324.5 vs. 264.7 ± 165.8; p < 0.001). ROC analysis identified a PIV cutoff value of >320, yielding an AUC of 0.753 (95% CI: 0.740–0.787; p < 0.001), with 67% sensitivity and 66.9% specificity. Multivariate logistic regression confirmed that PIV > 320 independently predicted CA-AKI (OR 2.118; 95% CI: 1.329–3.790; p < 0.001). In multivariable analysis, age, Killip class, contrast volume, and PIV > 320 were identified as independent predictors of CA-AKI. Conclusions: Elevated admission PIV serves as an independent and practical biomarker for predicting CA-AKI in STEMI patients undergoing PCI. Full article

Background and Objectives: Substance use disorders (SUDs) are associated with maladaptive neuroplasticity and chronic dysregulation of cortical arousal. EEG provides a non-invasive tool for quantifying these neurophysiological alterations through spectral power and reactivity indices. Prior research consistently reports elevated beta and diminished alpha activity in SUD, reflecting cortical hyperarousal and reduced inhibitory control. This study sought to identify EEG-based markers of dependence-related neurophysiological alterations by integrating rule-based and score-based models incorporating the theta/beta ratio (TBR), alpha and beta powers, the hyperarousal index, and alpha-blocking measures. Materials and Methods: EEG recordings from 47 individuals with SUD were systematically analyzed, focusing on frontal and central cortical regions. Spectral parameters were derived using power spectral density estimation, and composite indices were computed via Python-based signal analysis. A rule-based Dependence Likelihood variable and a continuous Dependence Score (0–1 scale) classified cases as dependence-related (≥0.7), borderline (0.5–0.7), or normal (<0.5). Results: Low alpha power and an elevated hyperarousal index (mean = 3.45) characterized most participants. Dependence-related EEG profiles were identified in 87.2% of cases (mean score = 0.86). Alpha blocking remained intact in 46.8% of cases, whereas post-hyperventilation recovery was attenuated in 61.7% of cases. Segmental analysis indicated sustained cortical activation with low TBR (0.37) and elevated beta across all conditions. Conclusions: Quantitative EEG analysis revealed consistent hyperarousal and inhibitory deficits in SUD. The combined Dependence Likelihood and Score framework provides an interpretable, reproducible approach for identifying dependence-related EEG signatures and holds promise as a biomarker in addiction neurophysiology. Full article

Background/Objectives: Odontogenic cysts and ameloblastomas (AB) are mostly asymptomatic, often discovered later due to severe symptoms, and only histopathological examination provides definitive diagnosis. AI-assisted diagnostics offer a fast, noninvasive, painless diagnostic tool. To our knowledge, this is the first meta-analysis aiming to evaluate the classification, detection, and segmentation performance of artificial intelligence (AI) for odontogenic cysts and ABs as distinct entities and to determine if it can achieve clinically acceptable accuracy. Methods: Our systematic search was conducted on 11 January 2026, in Medline, EMBASE, and Cochrane Central Register of Controlled Trials without restrictions or filters. Studies comparing AI diagnostics with histopathological diagnostics for odontogenic cysts and ABs were included. Diagnostic parameters, including sensitivity, specificity, and accuracy, were extracted and analyzed; additionally, diagnostic odds ratios were calculated. Risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. Recommendations of the GRADE workgroup were followed to determine the certainty of evidence. Results: Thirteen articles were found eligible, of which seven were included in our meta-analysis. The group with the highest sensitivity (Se) was the “no lesion” (N) group (0.9726, 95% CI 0.9284–1; I2 = 46%), followed by the radicular cyst (RC) (mean 0.9054, 95% CI 0.8051–1; I2 = 89%), dentigerous cyst (DC) (mean 0.8788, 95% CI 0.7828–0.9749; I2 = 93%), odontogenic keratocyst (OKC) (0.763, 95% CI 0.6999–0.8262; I2 = 14%) and AB (mean 0.4369, 95% CI 0.231–0.6429; I2 = 79%) groups. Results for AB, RC, and DC were statistically significant. The AB achieved the highest specificity (Sp) (mean 0.9889, 95% CI 0.9736–1; I2 = 0%), followed by RC (mean 0.9724, 95% CI 0.9431–1; I2 = 79%), DC (mean 0.9516, 95% CI 0.9116 0.9917; I2 = 90%), N (mean 0.9226, 95% CI 0.8385–1; I2 = 95%) and OKC (mean 0.8991, 95% CI 0.8683–0.9298; I2 = 8%) groups. DC, N, and RC had statistically significant results. Diagnostic odds ratios (DOR) showed that classification was better than chance for all lesion types. Conclusions: AI demonstrated high specificity, and is therefore effective in identifying healthy individuals. However, its sensitivity in detecting diseased patients remains suboptimal and requires further improvement. Full article

Background/Objectives: Anterior segment optical coherence tomography (AS-OCT) and optical coherence tomography angiography (AS-OCTA) have enhanced the evaluation of the cornea, ocular surface, and ocular surface diseases (OSD), offering high-resolution structural and anterior segment vascular imaging. This review summarizes recent advances in these modalities and their clinical applications. Methods: A comprehensive literature search was conducted using PubMed, Web of Science, and Google Scholar with the terms OCT, OCTA, anterior segment, and ocular surface disease. Studies published in the past five years were included, emphasizing more recent developments such as ultra-high-resolution AS-OCT (UHR-AS-OCT) and swept-source AS-OCTA technologies. Results: UHR-AS-OCT provides non-invasive, sub-micron imaging of the cornea and the ocular surface, including tear film morphology and epithelial thickness to correlate with clinical tests such as tear break-up time, and fluorescein staining. Advances in AS-OCTA allow dye-free, depth-resolved imaging of corneal and conjunctival vasculature. These vascular biomarkers have shown promising utility in conditions such as limbal stem cell deficiency, chemical ocular injury, and ocular surface squamous neoplasia. Improvements in image acquisition, motion correction, and segmentation algorithms have enhanced accuracy and repeatability, supporting broader clinical translation. Conclusions: AS-OCT and AS-OCTA have become useful adjunctive imaging tools for the cornea and ocular surface evaluation. Their non-invasive, quantitative, and reproducible metrics may enable earlier diagnosis, objective staging, and longitudinal monitoring of OSD. Integration of OCT-based imaging with artificial intelligence and multimodal data, including tear proteomics and meibography, may optimize personalized treatment for ocular surface disorders. Full article

Background/Objectives: Translating brain volumetric biomarkers to individual-level Alzheimer’s disease (AD) diagnosis remains challenging due to difficulty interpreting raw volumes without longitudinal monitoring or matched controls. We tested a classification model using population-referenced volumetric percentiles to distinguish AD from cognitively normal (CN) subjects and evaluated its generalization across independent cohorts. Methods: Brain volumes from 95 regions were extracted using an automated segmentation pipeline and converted to age and sex adjusted percentiles using a reference population (N = 1833). A logistic regression classifier was trained on ADNI subjects (N = 873; AD = 183, CN = 690) split into training (60%), validation (20%), and test (20%) sets. The model was evaluated on two independent validation datasets: the held-out ADNI validation set and an external Korean cohort (N = 72; AD = 36, CN = 36) acquired with different scanner protocols and demographic characteristics. Results: The model achieved excellent discrimination across all evaluation sets: ADNI validation (AUC = 0.963, accuracy = 90.3%), ADNI test (AUC = 0.960, accuracy = 89.7%), and Korean external validation (AUC = 0.981, accuracy = 87.5%). The minimal validation gap (0.018) demonstrated robust generalization. Positive coefficients for ventricular regions reflected AD-associated atrophy patterns, while negative coefficients for medial temporal structures indicated their contribution within multivariate patterns distinguishing AD from normal aging. Conclusions: Population-referenced brain volumetric percentiles enable accurate AD classification with robust generalization across populations and scanner protocols. By contextualizing individual brain structure relative to normative populations while accounting for age and sex, this approach demonstrates potential for clinical translation as an accessible neuroimaging-based diagnostic tool. Full article

Background/Objectives: Differentiating minimal change disease (MCD) from focal segmental glomerulosclerosis (FSGS) remains a diagnostic challenge. We hypothesised that differences in glomerular protein selectivity could translate into distinct serum protein electrophoresis (SPEP) profiles, particularly in severe nephrotic syndrome. Methods: We retrospectively analysed SPEP profiles of adults with biopsy-proven MCD (n = 27), primary FSGS (n = 27), and secondary FSGS (n = 20). Diagnoses were established according to KDIGO guidelines and the Mayo Clinic classification. A severe subgroup was defined by a relative albumin fraction <40% to evaluate patterns in marked hypoalbuminaemia. Results: Secondary FSGS demonstrated significantly higher albumin-to-globulin (A/G) ratios compared with immune-mediated podocytopathies (MCD and primary FSGS), yielding excellent discrimination (AUC > 0.98). In contrast, discriminatory performance between MCD and primary FSGS in the overall cohort was limited (AUC = 0.657). However, within the severe subgroup, the A/G ratio provided clinically meaningful separation (AUC = 0.787). An A/G ratio > 0.49 identified primary FSGS with 86.7% sensitivity and 81.2% specificity. Correlation analysis revealed a strong inverse association between albumin and α2-globulin fractions in immune-mediated podocytopathies (ρ < −0.8), whereas this relationship was attenuated in secondary FSGS (ρ = −0.57). Conclusions: The A/G ratio may represent a practical adjunctive biomarker in the evaluation of podocytopathies. Values > 1.0 strongly favour secondary FSGS, while markedly reduced ratios in severe nephrosis are characteristic of MCD. These findings suggest that differences in glomerular selectivity and the hepatic compensatory response are reflected in routine electrophoretic profiles. Full article

Background/Objectives: Federated learning has emerged as a promising paradigm for enabling collaborative artificial intelligence in healthcare while preserving data privacy. However, most existing frameworks focus on isolated tasks and lack integrated pipelines that combine classification, segmentation, explainability, and automated clinical reporting. Methods: This study proposes FedIHRAS, a privacy-preserving federated learning framework designed for multi-institutional radiological analysis. The system integrates multi-task deep learning modules, including pathology classification using a modified ResNet-50 backbone, anatomical segmentation, explainability through Grad-CAM, and automated report generation supported by semantic aggregation using SNOMED CT. The framework employs confidence-weighted aggregation, differential privacy mechanisms, and secure aggregation protocols to ensure privacy and robustness across heterogeneous institutional datasets. Results: Experimental evaluation was conducted across four large-scale chest X-ray datasets representing simulated institutional nodes, totaling approximately 874,000 images. FedIHRAS achieved high diagnostic performance with strong cross-institutional generalization and demonstrated improved robustness under non-IID data distributions. Additional experiments showed favorable communication efficiency, effective privacy–utility trade-offs, and strong agreement with expert radiologist assessments. Conclusion: The proposed FedIHRAS framework demonstrates that federated learning can support scalable, privacy-preserving, and clinically meaningful radiological AI systems. By integrating multi-task learning, explainability, and automated reporting within a unified federated architecture, the framework addresses key limitations of existing approaches and contributes to the development of collaborative AI in healthcare. Full article

Background/Objectives: The combination of hearing loss and visual impairment in a single patient strongly suggests a genetic aetiology. However, after conventional testing, a considerable proportion of deafblindness cases remain without a genetic diagnosis. The aim of this study was to address this diagnostic gap. Methods: We developed an enhanced exome strategy that uses a whole-exome backbone complemented by spike-in capture probes for (i) low-coverage coding segments and clinically validated, non-coding regions (including deep intronic splice-altering sites and untranslated exonic sequences) across 659 genes associated with hearing loss and/or visual impairment, and (ii) mitochondrial DNA. Results: With 66.6 million paired-end reads per sample, this methodology achieved coverage of at least 20 reads per base at 99.3% of target coding and non-coding positions of genes associated with deafness and/or blindness, as well as 98.8% of the whole exome. The enhanced exome approach correctly identified the genetic variants causative of deafness and/or blindness in 10 out of 10 cases with a previously known genetic cause, in 3 out of 10 additional cases that remained undiagnosed after extensive panel sequencing, and in 4 out of 4 cases that had not been genetically studied before. Comparison of the performance of two commercial bioinformatics platforms for enhanced exome interpretation revealed that eVAI consistently prioritised causative variants higher than, or as high as, VarSome Clinical, resulting in a tendency toward shorter interpretation times using the former. Both platforms offered the same diagnostic yield and both failed to correctly call one of the causative variants. Conclusions: In an era where many centres operate exome analysis through virtual panels, enhanced exome sequencing leverages the advantages of whole-exome and custom panel sequencing: it provides panel-like sensitivity for clinically actionable loci, while offering the flexibility to periodically reanalyse data and discover candidate genes. Full article

China is one of the world’s major lychee producers, and the fruit’s soft texture, small size, and thin peel make non-destructive robotic harvesting particularly challenging. Accurate fruit detection, branch segmentation, and precise picking-point localization are critical for enabling automated harvesting in complex natural orchard environments. This study proposes an integrated perception framework for lychee harvesting that combines object detection, density-based clustering, and semantic segmentation. An improved YOLO11s-based detection network incorporating SimAM attention, CMUNeXt feature enhancement, and MPDIoU loss is developed to enhance robustness under illumination variation, occlusion, and scale changes. The proposed detector achieves a precision of 84.3%, recall of 73.2%, and mAP of 81.6%, outperforming baseline models. Density-based clustering is employed to group individual detections into fruit clusters. Comparative experiments demonstrate that MeanShift achieves the highest clustering consistency, with an average Adjusted Rand Index (ARI) of 0.768, outperforming k-means and other baselines. An improved DeepLab v3+ semantic segmentation network with a ResDenseFocal backbone and Focal Loss is designed for accurate branch extraction under complex backgrounds. Finally, a rule-based geometric picking-point localization algorithm is formulated in the image coordinate system by integrating detection, clustering, and branch segmentation results. Experimental validation demonstrates that the proposed framework can reliably localize picking points in two-dimensional images under natural orchard conditions. The proposed method provides a practical perception solution for intelligent lychee harvesting and establishes a foundation for future 3D robotic manipulation and field deployment. Full article

Background/Objectives: Tidal volume is determined by height and sex in adults under mechanical ventilation, and it serves as the foundation for implementing a lung-protective ventilation strategy. In children, tidal volume is often calculated based on actual body weight, without established guidelines regarding the predictors of lung volume. The aim of this study was to identify the key predictors of lung volume in children aged 0–5 years. Methods: This retrospective study involved 51 children aged 0–5 years who underwent chest computed tomography (CT) and surgery under general anesthesia between 2014 and 2024. The total lung volume was calculated using three-dimensional segmentation of the CT images. Linear regression models were used to assess predictors, including height, weight, age, sex, and body mass index (BMI). Model performance was evaluated using the adjusted R-squared and Akaike Information Criterion (AIC). Bootstrap validation with 2000 iterations was used to validate model reliability. Results: Height was the strongest predictor of lung volume (adjusted R-squared: 0.5621), and it showed a collinearity with age. The final model included age and sex as the covariates. The Bootstrap validation confirmed the model’s reliability. Conclusions: Age and sex are key predictors of the CT-derived total lung volume in children aged 0–5 years. Further studies are required to validate these findings. In addition, research is needed to derive and validate a tidal volume equation based on these predictors and assess the influence of this equation on clinical outcomes such as atelectasis, oxygenation, and inflammatory markers in pediatric surgery. Full article

Background/Objectives: Virtual surgical planning (VSP) and CAD/CAM technologies have revolutionized complex maxillofacial reconstruction. While high-resolution imaging is critical for these workflows, the specific clinical impact of photon-counting computed tomography (PCCT) remains to be fully established. This prospective pilot study evaluates the feasibility and clinical utility of integrating PCCT into the preoperative planning and surgical workflow of complex maxillofacial reconstructive cases. Methods: This feasibility study included ten patients requiring complex maxillofacial reconstruction with microvascular free flaps. All underwent preoperative imaging with photon-counting CT. Primary endpoints included clinical assessment of osseous invasion, reliability of donor-site vascular mapping from a single acquisition, and compatibility of PCCT datasets with VSP/CAD-CAM platforms. Secondary endpoints included resection margin status, flap survival, and short-term oncologic outcomes. Results: PCCT provided high-resolution visualization of cortical and medullary bone, enabling detailed assessment of tumor-related osseous involvement. In selected cases, findings supported refinement of resection planning when prior imaging had been inconclusive. Spectral reconstructions reduced metal artifacts and facilitated precise segmentation for multi-segment osteotomies. Donor-site vascular anatomy was successfully evaluated within the same scan, supporting operative planning without additional imaging. PCCT datasets were fully compatible with the virtual surgical planning (VSP) software used in this study (CMX Portal, version 2.6.1158, Medartis AG, Basel, Switzerland; or ProPlan CMF, version 5.7.8.025, Materialise NV, Leuven, Belgium) in all cases (100%). Reconstruction was completed successfully in all patients, with 100% flap survival and R0 margins in all malignant cases. No technical failures occurred during imaging transfer or CAD/CAM fabrication. Conclusions: The integration of PCCT into the surgical workflow proved technically feasible and clinically impactful. This pilot data supports its potential to enhance surgical precision and preoperative planning in complex jaw reconstruction. Full article

Background/Objectives: The rise of artificial intelligence is injecting intelligence into the healthcare sector, including surgery. Vision-based intelligent systems that assist surgical procedures can significantly increase productivity, safety, and effectiveness during surgery. Surgical instruments are central components of any surgical intervention, yet detecting and locating them during live surgeries remains challenging due to adverse imaging conditions such as blood occlusion, smoke, blur, glare, low-contrast, instrument scale variation, and other artifacts. Methods: To address these challenges, we developed an advanced segmentation architecture termed the frozen-filters-based morphology-aware segmentation network (FFMS-Net). Accurate surgical instrument segmentation strongly depends on edge and morphology information; however, in conventional neural networks, this spatial information is progressively degraded during spatial processing. FFMS-Net introduces a frozen and learnable feature pipeline (FLFP) that simultaneously exploits frozen edge representations and learnable features. Within FLFP, Sobel and Laplacian filters are frozen to preserve edge and orientation information, which is subsequently fused with learnable initial spatial features. Moreover, a tri-atrous blending (TAB) block is employed at the end of the encoder to fuse multi-receptive-field-based contextual information, preserving instrument morphology and improving robustness under challenging conditions such as blur, blood occlusion, and smoke. Datasets focused on surgical instruments often suffer from severe class imbalance and poor instrument visibility. To mitigate these issues, FFMS-Net incorporates a progressively structure-preserving decoder (PSPD) that aggregates dilated and standard spatial information after each upsampling stage to maintain class structure. Multi-scale spatial features from different encoder levels are further fused using light skip paths (LSPs) to project channels with task-relevant patterns. Results/Conclusions: FFMS-Net is extensively evaluated on three challenging datasets: UW-Sinus-surgery-live, UW-Sinus-cadaveric, and CholecSeg8k. The proposed method demonstrates promising performance compared with state-of-the-art approaches while requiring only 1.5 million trainable parameters. In addition, an open-source large language model is integrated for non-clinical summarization of the surgical scene based on the predicted mask and deterministic descriptors derived from it. Full article

Background/Objectives: Inclusion complexes among drugs and cyclodextrin-modified polymers are a topic of recent interest in pharmaceutical research and industry as they might expand the solubility, bioavailability, and stability of the guest molecules. Polyurethanes derived from cyclodextrins show some biomedical applications. In this study, two cross-linked polyurethane networks based on hydroxypropyl-β-cyclodextrin (HPβCD) and polyethylene glycols (PEG 2000 or PEG 6000) were synthesized with NCO/OH molar ratio 4.3 and 6.3 by the typical two-step polymerization method. Methods: Inclusion complexes of clotrimazole (CLOT) with two HPβCD-modified polyurethane networks and their corresponding physical mixtures were prepared using kneading methods and physical mixing in a 1:6 weight ratio of CLOT:HPβCD. Results: Obtained prepolymers, previously end-capped with isocyanate groups forming urethane links with HPβCD, which were confirmed by FTIR analysis. TGA results indicate a slight increase in thermal stability of the prepared complexes. The characteristic endothermic peak of the CLOT at around 145.90 °C did not appear in the DSC curve of the drug-loaded inclusion complexes. The XRD patterns of physical mixtures showed specific peaks corresponding to pure clotrimazole. SEM micrographs confirmed an elliptical/spherical- and plate-shaped particles without phase segregation, indirectly confirming that CLOT is not separately present due to inclusion into HPβCD and entrapment into polyurethane networks. Novel complexes PUR2/HPβCD-CLOT-IC and PUR3/HPβCD-CLOT-IC were applied as drug carriers, and diffusion-controlled kinetics of CLOT release were best described using Higuchi model. Conclusions: The obtained in vitro results showed surprisingly slow/prolonged clotrimazole release from modified polyurethane networks due to the significant influence of NCO/OH molar ratio and the chosen polyol soft segments chain length with potential in vivo applications. Full article

Scientific flood season segmentation serves as the foundation for determining the flood-limited operating water levels across different periods, providing crucial support for reservoir flood control safety operations and optimal water resource utilization. Under the background of climate change, the traditional static flood-limited water level management model based on fixed dates struggles to adapt to variations in flood season patterns. This study aims to establish a scientifically sound flood season segmentation scheme, providing a basis for dynamic control of flood-limited water levels across different periods, thereby improving water resource utilization efficiency while ensuring flood control safety. This study focuses on the Wuluwati Reservoir and employs the circular distribution method and the Fisher optimal partition method to conduct its flood season segmentation calculations. First, the circular distribution method is used to analyse the concentration and periodic characteristics of flood occurrences in the basin. Subsequently, the Fisher optimal partition method is applied to perform statistical segmentation of the historical hydrological series. Based on this analysis, the flood season of the Wuluwati Reservoir is comprehensively determined as: the pre-flood season from 1 June to 2 July, the main flood season from 3 July to 27 August, and the post-flood season from 28 August to 30 September. To objectively evaluate the rationality of the segmentation results, the improved Cunderlik method was employed to examine the rationality of 15 segmentation schemes based on relative superiority degree. The results show that the scheme with the main flood season from 3 July to 23 August achieves the highest relative superiority degree (0.930). The comprehensively determined segmentation of this study (3 July–27 August) encompasses this optimal interval, demonstrating that the flood season segmentation for the Wuluwati Reservoir is reasonable and effective. Full article