Search Results (9,666)

Purpose: This paper aimed to identify dosimetric, clinical, and CT-based densitometric predictors of radiation-induced pulmonary events in breast cancer patients treated with moderately hypofractionated radiotherapy. Materials and Methods: A single-institution cohort of 1172 consecutive patients treated with 3D conformal whole-breast radiotherapy (40 Gy/15 fractions) before 2017 was analyzed. Ipsilateral lung DVHs and CT densitometry metrics were extracted. Clinical variables and cardiac calcification (CAC) scores (Agatston_score, CAC_volume, Max_HU_Heart) were included. Univariable and multivariable logistic regressions were performed; collinearity was assessed via Spearman correlation and VIF. Optimal thresholds were derived using the Youden index. Internal validation used bootstrap resampling. Results: After a median follow-up of 6.5 years, 18 patients developed moderate/severe pulmonary events. The univariable analysis showed associations with lung densitometric features (median/mean HU, 10th percentile, the lung volume with HU < −850 (V850)), V37 Gy, lung volume, and CAC scores. Lower lung HU values and larger lung volumes were linked to higher risk. The best models combined V850 (or lung volume) with a CAC metric. The model including V850 > 175 cc and continuous Max_HU_Heart achieved an optimism-corrected AUC of 0.68, with good fit and calibration (Hosmer–Lemeshow p = 0.33, R² = 0.847). Conclusions: The baseline cardiopulmonary status, captured by lung and heart densitometry, predicts pulmonary toxicity better than dosimetry. V850 > 175 cc was associated with a 4-fold higher risk, consistent with air trapping, known as a marker of emphysema. Full article

Background: This study aimed to develop a fully nested, information leakage-free machine-learning workflow to predict the volumetric response of meningioma to Gamma Knife radiosurgery (GKRS) from pre-treatment MRI and to compare the predictive value of radiomic, fractal, lacunarity and clinical/radiosurgical features. GKRS is widely used for treating meningiomas because of its high precision and efficacy. Variability in tumor volumetric response highlights the need for reliable predictors of treatment outcome. Methods: This retrospective cohort study included 204 patients treated with GKRS for grade I meningioma. Radiomic, fractal and lacunarity features were extracted from pre-treatment CE-T1w 3-Tesla MRIs. Feature signatures were generated using a machine-learning workflow incorporating five feature selectors based on a consensus principle to reduce spurious feature selection, followed by five classifiers to predict binary outcome. Results: The models demonstrated consistent predictive performance in the test folds, with AUC values from 0.77 to 0.84. Supplementing radiomic features with clinical, fractal or lacunarity features did not improve predictive performance. Conclusions: Radiomic features showed the strongest predictive value for meningioma volumetric response to GKRS. Darker intratumoral intensity values were associated with a favorable volumetric response, possibly reflecting biologically less active tumor regions. The supplied code enables individual-level prediction for newly encountered patients. Full article

Objective: Metabolic dysfunction-associated steatotic liver disease (MASLD) is a global public health crisis, progressing to hepatic cirrhosis and hepatocellular carcinoma. This study investigated the causal role of systemic iron status in MASLD progression. Methods: A two-sample Mendelian randomization (MR) design was implemented, with genetic variants serving as instrumental variables for four core systemic iron biomarkers. Outcome data for hepatic steatosis (8785 cases; 912,105 controls) and hepatic fibrosis/cirrhosis (3798 cases; 904,599 controls) were extracted from the FinnGen and UK Biobank databases. Multiple complementary MR methodologies and three instrumental variable selection strategies were applied to ensure robust causal inference. Results: Genetically predicted higher serum iron (odds ratio, OR: 1.42, 95% confidence interval, 95% CI: 1.34, 1.50), ferritin (OR: 1.84, 95% CI: 1.55, 2.18), and transferrin saturation (TfSat, OR: 1.24, 95% CI: 1.19, 1.30), together with lower total iron-binding capacity (TIBC, OR: 0.81, 95% CI: 0.77, 0.85), were significantly associated with increased hepatic steatosis risk (p < 0.00625). Similar associations were observed for hepatic fibrosis/cirrhosis: serum iron (OR: 1.66, 95% CI: 1.29, 2.14), ferritin (OR: 2.52, 95% CI: 1.52, 4.18), TfSat (OR: 1.40, 95% CI: 1.19, 1.63), and reduced TIBC (OR: 0.70, 95% CI: 0.60, 0.81). MR-Bayesian model averaging prioritized serum iron (MIP: 0.85, ${\widehat{\theta }}_{\mathrm{MACE}}$: 0.295; PP: 0.725; ${\widehat{\theta }}_{\mathsf{\lambda }}$: 0.344) as the top-ranked factors for steatosis and TIBC (MIP: 0.604, ${\widehat{\theta }}_{\mathrm{MACE}}$: −0.240; PP: 0.476, ${\widehat{\theta }}_{\mathsf{\lambda }}$: −0.358) for fibrosis/cirrhosis. Conclusions: Elevated systemic iron status causally drives MASLD onset and progression, highlighting iron homeostasis and ferroptosis as potential targets for prevention and clinical management. Full article

Background: Nasopharyngeal carcinoma (NPC) presents significant diagnostic and therapeutic challenges, often due to late-stage detection and its complex anatomical location. The increasing integration of artificial intelligence (AI) into oncology offers potential opportunities to enhance the precision of NPC management. This systematic review aims to synthesise the current evidence of AI applications in NPC diagnosis, prognostication, and treatment planning. Methods: A systematic literature search was conducted following PRISMA guidelines across multiple databases (PubMed, Scopus, Embase, Google Scholar, IEEE Xplore) for studies published up to June 2025. From an initial pool of 2549 articles, 55 studies meeting the inclusion criteria were selected for qualitative analysis. The review focuses on AI models applied to key diagnostic modalities: computed tomography (CT), magnetic resonance imaging (MRI), and histopathological whole-slide images (WSI). Results: AI, particularly deep learning (DL), shows promising performance in automating critical tasks across all modalities. For CT and MRI, models have been reported to achieve accurate tumor and organ-at-risk segmentation, potentially supporting radiotherapy planning, and show strong performance in predicting survival outcomes and treatment toxicity. In digital pathology, AI enables automated diagnosis and facilitates the extraction of prognostic “pathomic” features from WSIs, with some studies suggesting performance comparable to or exceeding traditional radiomics. The most significant advances are seen in multimodal AI systems that integrate radiological, pathological, and clinical data, which, in some studies, show modest improvements in prognostic performance compared to single-modality approaches. However, these findings are preliminary, as none of the reviewed multimodal models underwent rigorous external validation in large, multi-center cohorts. Reported performance varies considerably across studies, and claims of superiority should be interpreted with caution. Full article

Background: Response to neoadjuvant therapy in locally advanced rectal cancer (LARC) is heterogeneous, and early identification of non-responders may help optimize treatment strategies and reduce unnecessary toxicity. This study aimed to develop and internally validate a machine learning model based on radiomic features extracted from baseline magnetic resonance imaging (MRI) to predict treatment response defined according to MRI tumor regression grade (mrTRG) at restaging MRI. Methods: In this retrospective single-center study, 86 patients with histologically confirmed LARC who underwent baseline and restaging MRI, neoadjuvant therapy, and surgery were included. Primary tumors were manually segmented on oblique axial T2-weighted images. A total of 107 radiomic features were extracted using PyRadiomics (vrs 3.0.1), with and without N4 bias field correction. Feature selection was performed using LASSO, followed by elastic net–regularized logistic regression. Model performance was evaluated using repeated stratified 5-fold cross-validation (20 repetitions). Treatment response was defined according to MRI tumor regression grade (mrTRG) at restaging, dichotomized into responders (mrTRG ≤ 2) and non-responders (mrTRG ≥ 3). Results: The model achieved a mean area under the receiver operating characteristic curve (AUC-ROC) of 0.73, with an accuracy of 72.5%, sensitivity of 79.2%, and specificity of 50%. Conclusions: Baseline MRI-based radiomics shows potential for identifying patients at higher risk of non-response to neoadjuvant therapy in LARC. However, limited specificity and the absence of external validation restrict immediate clinical applicability. Further validation in larger multicenter cohorts and integration with clinical variables are warranted to improve model robustness and generalizability. Full article

Background: Sarcopenia, characterized by progressive loss of skeletal muscle mass and function, is becoming increasingly prevalent with the global population aging. Computed tomography (CT) is widely used for muscle assessment; however, concerns regarding radiation exposure have prompted interest in lower-dose imaging protocols. This study investigated the performance of radiomics-based machine learning (ML) models for sarcopenia detection using abdominal CT (APCT) and low-dose CT (LDCT). Methods: Radiomics features were extracted from CT images following skeletal muscle segmentation, and ML models were developed using logistic regression, support vector machine, and random forest. Model performance was evaluated using fivefold cross-validation with out-of-fold predictions. Results: The random forest model demonstrated the best performance among the evaluated models, achieving an area under the receiver operating characteristic curve of 0.720 (95% CI: 0.532–0.881) for APCT and 0.692 (95% CI: 0.573–0.801) for LDCT. Model interpretation using SHapley Additive exPlanations analysis identified several intensity-based radiomics features, including TotalEnergy, as important contributors to sarcopenia prediction. Conclusions: These findings suggest that radiomics features derived from LDCT images may provide useful information for sarcopenia detection. Because LDCT is widely used in clinical settings such as lung cancer screening, radiomics analysis of LDCT images may offer an additional opportunity for opportunistic sarcopenia assessment. Full article

Background and Objectives: The systemic inflammatory response is important in cancer prognosis and progression. The inflammatory burden index (IBI) provides information about both inflammation and the immune response. Urothelial carcinomas are immunogenic; therefore, it has been suggested that inflammatory indices may predict disease prognosis. The aim of this study was to investigate the effects of systemic inflammatory indices, particularly the inflammatory burden index, on disease progression and overall survival in patients with metastatic urothelial cancer (affecting the bladder and upper urinary system) before first-line treatment and to demonstrate their prognostic importance. Materials and Methods: Within the scope of the study, the medical records of 130 patients who received systemic treatment for metastatic urothelial carcinoma at the medical oncology clinic were retrospectively reviewed. Receiver operating characteristic (ROC) curve analysis was performed to determine the optimal threshold values for IBI. Survival rates were calculated using the Kaplan–Meier method, and survival differences between groups were compared with the log-rank test. Univariate and multivariate analyses were performed using the Cox proportional hazards regression model to evaluate prognostic factors. Results: A total of 130 patients were included in the study. The median age was 64.9 years (IQR: 57.2–70.5). The primary tumor location was the bladder in 84.6% of patients, while the remaining 15.4% originated from the ureter and renal pelvis. In first-line systemic treatment, patients received a median of 4 cycles (IQR: 3–6). The median number of total treatment lines administered for metastatic disease was 1 (IQR: 1–2). In progression-free survival (PFS) analyses, the median PFS was 9.20 (95% CI 6.55–11.85) months in the IBI-low group (n = 47) and 5.82 (95% CI 4.56–7.07) months in the IBI-high group (n = 83) (p < 0.001). The median OS was calculated to be 18.96 (95% CI 16.61–21.30) months in the IBI-low group (n = 47), while it was found to be 9.50 (95% CI 7.70–11.29) months in the IBI-high group (n = 83) (p < 0.001). In multivariate analysis, high IBI and the presence of brain metastasis were found to be associated with the risk of progression. In terms of overall survival, the presence of brain metastasis, the presence of visceral metastasis, ECOG PS status, receipt of maintenance therapy, LMR, and the IBI score showed statistically significant prognostic effects. Conclusions: In metastatic urothelial carcinoma, the IBI was identified as an independent prognostic factor associated with progression-free and overall survival. These findings suggest that the IBI may have potential utility as a prognostic biomarker; however, larger, multicenter, and prospective studies are required to further validate its clinical applicability. Full article

Background: Metabolic syndrome (MetS) affects over 30% of the global population and is closely linked to higher cardiovascular (CV) morbidity and mortality. Although MetS is recognized as a significant CV risk factor, limited studies have examined which specific combinations of MetS components are associated with long-term predicted CV risk. Furthermore, limited evidence exists using established 10-year CV risk-prediction models in Asian populations. Methods: We analyzed data from 111,695 Taiwanese adults aged 30–75 years who underwent health screenings from 2007 to 2022. Predicted CV risk was estimated using the Framingham Risk Score (FRS) and Atherosclerotic Cardiovascular Disease (ASCVD) Risk Estimator at baseline and at 5- and 10-year follow-ups. Cox regression models adjusted for clinical variables were applied to evaluate the association between different MetS patterns and progression in estimated 10-year CV risk. Results: Of the 111,695 participants, 4435 had persistent MetS with the same exact three components at both baseline and follow-up. Among the MetS combinations, the TFB pattern (elevated triglycerides, fasting glucose, and blood pressure) was consistently associated with greater progression in predicted 10-year CV risk over 5- and 10-years follow-up periods in both the FRS (HR = 1.189–1.204) and ASCVD (HR = 1.144–1.146) models (all p < 0.05). Although the effect sizes were modest, the associations were consistent across models and time points. Conclusions: The TFB pattern was consistently associated with greater progression in predicted 10-year cardiovascular risk across both the FRS and ASCVD models. These findings suggest that evaluating specific MetS patterns may provide additional value beyond the total number of components and may help clinicians prioritize high-risk individuals for targeted screening and early intervention. Full article

Healthcare analytics is often limited by data silos and strict privacy requirements, which make it difficult to share patient-level records across organisations and to build robust predictive models. Federated learning (FL) provides an alternative by keeping data local and exchanging model updates instead of raw records. However, many existing FL solutions remain difficult to deploy in healthcare settings, as they provide limited support for auditability, governance-oriented evidence, and system-level transparency. This paper presents MediVault, an auditable and security-aware federated learning-based system for privacy-preserving healthcare collaboration. MediVault combines round-based federated training, prototype-level protected update exchange, audit-ready telemetry, and an interactive dashboard that exposes non-sensitive evidence of collaboration, model progress, and protocol execution. In addition, the system supports controlled reporting to improve stakeholder communication during pilot deployments. We evaluate MediVault on two public healthcare classification datasets, Breast Cancer Wisconsin (Diagnostic) and Heart Disease, under IID and label-skewed Non-IID settings. Experiments are conducted using logistic regression, linear SVM, and an additional lightweight MLP under matched settings. The observed results suggest that federated training remains competitive with centralised training under the evaluated settings. A prototype-level overhead analysis further shows that protected update exchange introduces measurable computational and communication costs, especially for larger update vectors. These findings indicate that MediVault can support initial system-level validation of auditable, privacy-preserving healthcare FL workflows, while further work is needed for larger-scale deployment, stronger adversarial evaluation, and real-world clinical validation. Full article

Objectives: Diminished ovarian reserve (DOR) significantly compromises in vitro fertilization (IVF) success. Although systemic markers such as anti-Müllerian hormone (AMH) serve as valuable clinical indicators of the ovarian reserve, they lack the sensitivity to reflect the qualitative deterioration of the follicular microenvironment. Therefore, in this study, we aimed to characterize the inflammatory proteome of follicular fluid (FF) to establish a high-performance auxiliary diagnostic model for DOR. Methods: Utilizing the ultra-sensitive Olink proximity extension assay, we quantified 92 inflammation-related proteins in the FF of 88 participants (67 with DOR and 21 normal controls). Differentially expressed proteins (DEPs) were identified, and their relationships with key clinical indices were evaluated. A robust predictive signature was refined through integrated Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest algorithms, with diagnostic performance assessed via 10-fold cross-validation. Results: Thirty-five DEPs were significantly dysregulated in the FF of patients with DOR, demonstrating strong associations with serum AMH and basal estradiol concentrations. A minimized diagnostic panel comprising four core proteins, adenosine deaminase (ADA), vascular endothelial growth factor A (VEGFA), eukaryotic translation initiation factor 4E-binding protein 1 (4E-BP1), and matrix metalloproteinase-1 (MMP-1), was established. This multivariable model achieved an excellent area under the receiver operating characteristic curve (AUC) of 0.953. Conclusions: The identified four-protein signature reflects localized chronic inflammation and early pathophysiological shifts in the DOR follicular microenvironment. As a high-performance molecular index, this panel could complement conventional systemic assessments, provide a reliable means of evaluating follicular viability, and optimize individualized therapeutic strategies. Full article

Background: Radiofrequency ablation of liver tumors relies on tightly coupled electromagnetic–thermal dynamics. However, conventional computational models oversimplify tissue heterogeneity and the dynamic evolution of biophysical properties, limiting their intraoperative diagnostic utility. Methods: We developed a patient-specific, three-dimensional multiphysics framework for liver RFA that integrates spatially varying tissue porosity with a modified local thermal equilibrium formulation. Advective heat transfer is computed via a supplementary finite-element equation, fully coupled with quasi-static electromagnetic simulations and Arrhenius-based tissue damage kinetics. Results: Simulations revealed three distinct voltage-dependent regimes: stable thermal–electromagnetic coupling at 50 V, optimal lesion expansion at 75 V, and premature electrical conductivity collapse at 100 V. Dynamic conductivity reduction, driven by dehydration and coagulative necrosis, provides a mechanistic basis for interpreting real-time impedance rises as an early indicator of peri-electrode desiccation. Geometry-constrained porosity mapping accurately reproduced anisotropic lesion morphologies, yielding simulated necrotic diameters of 2.8 ± 0.4 cm, closely aligning with MRI-validated clinical benchmarks. Conclusions: By linking microstructural heterogeneity to electromagnetic feedback, this framework transforms intraoperative impedance monitoring into a quantitative, predictive diagnostic tool. Imaging-derived spatial porosity mapping represents a robust biomarker for patient-specific liver RFA planning, significantly reducing procedural uncertainty and improving ablation precision. Full article

Background: Lipid peroxidation is a primary driver of biological membrane damage and mediates the relationship between environmental exposure and adverse health outcomes. Malondialdehyde (MDA) is a widely recognized biomarker for quantifying oxidative stress intensity. Despite numerous studies on oxidative stress and metal exposure, nonlinear relationships between physiological characteristics, serum metal profiles and MDA levels in pubertal children remain insufficiently studied. Methods: The study included 105 conditionally healthy children aged 12–14 years from urban and rural regions of Tatarstan, Russia. Serum MDA concentrations were determined spectrophotometrically using the thiobarbituric acid assay, while Zn, Cu, Fe, Sr and Pb concentrations were measured by atomic absorption spectrometry. A multilayer perceptron neural network was applied to model nonlinear relationships between MDA levels, environmental exposure indicators and morphophysiological characteristics. Because the original relational dataset contained partially replicated participant-derived relational structures, primary validation was performed using independently reconstructed datasets without repeated observations. Additional repeated cross-validation and SHAP-based feature importance analysis were performed. Results: Urban-residing children demonstrated significantly higher serum MDA levels than rural counterparts, independent of sex, with girls consistently showing higher values. Reduction of predictor dimensionality improved model generalization behaviour. Validation using independently reconstructed datasets without repeated observations demonstrated reproducible exploratory predictive behaviour of the reduced neural network model, with independently reconstructed validation datasets yielding mean R² values of 0.901 ± 0.052 and 0.914 ± 0.046, respectively. SHAP analysis demonstrated that zinc, copper and iron consistently represented the dominant contributors to the nonlinear model, although substantial variability in the relative ranking of zinc and copper was observed between validation datasets. Conclusions: The proposed neural network model demonstrated the ability to capture reproducible nonlinear relationships between oxidative stress markers and environmental exposure parameters in a limited biomedical dataset. The model should primarily be interpreted as an exploratory explanatory tool rather than an individual clinical prediction instrument. Because of the limited dataset size, partially reconstructed relational structure and exploratory study design, the findings require cautious interpretation and further external validation. Full article

The clinical reliability of swabs is affected by their ability to collect and elute biological samples for further detection. Since elution is particularly critical for swab functionality, the goal of this work was to develop a nasopharyngeal swab prototype that could potentially facilitate the release of biological specimens through controlled elastic deformation. To this end, a helical swab-head geometry was designed and 3D-printed by means of stereolithography (SLA). A dual post-curing process combining UV and thermal treatment was employed to maximize the mechanical stiffness of the resin—up to about 750 MPa. Microtomography of the 3D-printed prototypes demonstrated the accuracy of SLA printing, with only 0.12% closed porosity due to printing defects. The mechanical deformation of the prototype under compression was then investigated through numerical modeling and experimental analysis. The results of Finite Element (FE) simulations revealed stress localization in the upper coils, with global mechanical integrity. Experimental compression tests validated the predicted deformation behavior, as supported by video tracking and displacement analysis at multiple nodes, showing good agreement between numerical and experimental displacement. Furthermore, preliminary functional tests with P. aeruginosa and S. aureus, both in saline solution and artificial mucus, demonstrated that the swab-tip prototype per se, without any coating or any applied compression, could perform comparably to commercial cotton and flocked swabs. About a 2-log reduction in bacterial load was detected for all swabs compared to the inoculum when used in saline solution, while a bacterial load roughly matching the inoculum was found when the swabs were used in artificial mucus. Overall, these findings demonstrate the feasibility and the potential of the designed swab prototypes. Full article

Background/Objectives: This paper aims to design an explainable and accurate ML framework to support the automatic classification of Carpal Tunnel Syndrome (CTS) severity from structured patient data. Methods: For the experiment, an open-source dataset of 1037 samples was used. Following stratified partitioning, 305 samples were held out as the test set; the remaining training set (n = 732) was augmented to 1216 balanced samples via ADASYN, yielding an 80/20 train/test ratio relative to the final dataset (n = 1521). In order to solve the problem of imbalance associated with CTS cases of moderate and severe severity, the Adaptive Synthetic Sampling (ADASYN) technique was employed. The model’s predictive capacity was increased by means of feature engineering methods, such as polynomial transformations and clinically relevant interactions. Specifically, four ensemble learning models (XGBoost, Random Forest, LightGBM, and CatBoost) were optimized and ensembled with the use of a stacking approach with a base algorithm of LightGBM. The explainability of the model was ensured through SHAP and LIME analysis. Results: As a result, the stacking ensemble was able to reach a test accuracy of 91.15%, an F1-score of 91.13%, and an ROC-AUC of 0.9708. The proposed ensemble performed superiorly compared to any other individual algorithm while having stable performance across all severity categories. Conclusions: Through the explainability analysis, it was observed that such a classification model relies on important clinically relevant predictors, including cross-sectional area (CSA), duration of symptoms, pain level measured by the numeric rating scale of pain (NRS), and palmar bowing (PB). Full article

Advanced imaging is the cornerstone of modern radiation oncology, contributing to each phase of patient care, from diagnosis and treatment planning to delivery and follow-up. It has evolved from providing purely geometric guidance to enabling biological and dynamic precision, capturing detailed spatial and functional information about tumors and surrounding tissues. This progress has also generated vast amounts of complex data that remain largely underexplored. AI-based methods have shown promises to unlock the potential of these data, ensuring quality and standardization while extracting previously inaccessible insights. AI-driven tools can enhance accuracy, efficiency, and personalization of radiation oncology through precision diagnosis, automated segmentation, adaptive treatment planning, real-time image guidance, and predictive response assessment. In this review, we conducted a systematic bibliometric analysis of relevant literature published in the last decade and explored current advancements in AI and radiomics applications across radiation oncology. We also addressed ongoing challenges, such as data heterogeneity, model interpretability, and clinical implementation, and discussed future directions for integrating AI-powered imaging solutions into routine practice to advance precision cancer care. Full article