The journal retracts the article titled “Empirical Study of Autism Spectrum Disorder Diagnosis Using Facial Images by Improved Transfer Learning Approach” [...]
The clinical translation of automated HPV detection in Whole Slide Images (WSIs) is challenged by staining variability, sparse viral effects, and the biological continuum between cytology and histology. This work presents a fully automated pipeline for binary patch-level classification of HPV-induced lesions on H&E-stained tissue. The core contribution is a domain-adaptive transfer learning strategy: a ResNet50 backbone is pretrained on the SIPaKMeD cervical cytology dataset rather than ImageNet, then fine-tuned on a target histological cohort. Preprocessing includes adaptive tissue segmentation, blur rejection, and Macenko stain normalization to ensure vendor-agnostic inputs. Evaluated using a strict Leave-One-Patient-Out cross-validation on 42 diagnostic specimens, the SIPaKMeD-based initialization significantly outperforms the ImageNet baseline. This approach achieves higher AUC-ROC scores and superior stability across folds, demonstrating that domain-specific pretraining effectively mitigates data scarcity and class imbalance in digital cervical cancer screening. Under a complementary 5-fold patient-level cross-validation covering all 19 patients of the cohort (133,704 patches, 7181 HPV-positive, prevalence 5.37%), the SIPaKMeD-pretrained model attains a mean test AUC-ROC of 0.694 with a 95% patient-aware bootstrap confidence interval of [0.681, 0.705], consistently above the ImageNet baseline mean of 0.656 obtained on the controlled three-fold ablation.
Occupational mental-health risk in knowledge-work settings is an important public-health and psychosocial-support concern because workload demands, career insecurity, limited mentoring, uneven institutional support and barriers to care can increase psychological risk, including in early-career academic environments. Workplace well-being assessments rely on aggregate survey summaries or conventional prediction models, limiting calibration, interpretability, subgroup evaluation and transfer validation. This study develops a computational-intelligence framework for public mental-health decision support using heterogeneous workplace survey data with early-career academics treated as a motivating knowledge-work context rather than as the direct empirical cohort. The proposed approach combines attention-based tabular learning, variational autoencoder latent profiling, stacked ensemble prediction, probability calibration, feature attribution, perturbation analysis, fairness assessment and cross-dataset adaptation. Calibrated probabilities are converted into a transparent 0-100 risk index to support preventive outreach, psychosocial-support planning and resource-allocation decisions. The model is compared with baselines, including logistic regression, support vector machine, random forest, XGBoost, LightGBM, CatBoost, TabNet, FT-Transformer, NODE and DCN. Results show strong held-out performance with AUC = 0.885, average precision = 0.872, F1 = 0.808, Brier score = 0.145 and expected calibration error = 0.022, outperforming tested baselines. Five-fold robustness analysis produced a conservative mean test AUC of 0.809±0.044, indicating moderate partition sensitivity. Key predictors include work interference, perceived stress, care access and support variables. Latent profiling identifies two behavioural subgroups with distinct risk patterns. After feature harmonization, target-domain adaptation and recalibration, external evaluation on an occupational burnout dataset achieves AUC = 0.941 and average precision = 0.936, supporting calibrated, interpretable and subgroup-aware decision support under dataset shift.
Objective: Dysregulation of Toll-like receptor signaling and increased proportions of Th17 and other T helper cells can facilitate esophageal squamous cell carcinoma (ESCC) progression. Methods: By integrating WGCNA, Limma, and artificial intelligence (AI, including LASSO-Cox regression and SOM) frameworks, we first identified a Toll-like receptor signaling and Th17 and T helper cell (ThpT)-related prognostic model and Thp molecular subgroups for ESCC patients in bulk transcriptomic profiles. Next, Thp-associated hub genes were identified, followed by evaluation of corresponding molecular and immune features. Indeed, the heterogeneity of ESCC was estimated using a single-cell transcriptomic dataset acquired from the GEO database. Furthermore, we also evaluated Thp-associated hub gene molecular and biological functions in spatial and temporal manners on targeted cells via pseudotime trajectory and AI-driven targeted gene knockout (KO). ESCC therapeutic agents targeting Thp-associated hub genes were enriched via a drug-gene network and then examined by ridge regression-driven drug sensitivity estimation and molecular docking. To enhance the robustness of our study, we performed in vitro studies to quantify the relationship of the targeted gene with Th17 and ESCC progression. Results: Based on Thp, we successfully identified a prognostic model and molecular subgroups of ESCC patients. DDX39A and PBK should be considered ThpT-related hub genes involved in ESCC progression and decreased infiltration of Th17 cells. Based on drug sensitivity estimation and molecular docking, bleomycin and talazoparib may be potential drugs for treating esophageal squamous cell carcinoma. Conclusions: ThpT can guide personalized and precision medicine for ESCC patients. Our study provides a novel clinical translation strategy for combating ESCC.
Prostate cancer (PCa) is one of the most common malignancies in men and remains a major cause of cancer-related death worldwide. Radiotherapy is a well-established treatment modality for PCa, offering clinical outcomes comparable to surgical approaches. In recent years, stereotactic body radiotherapy (SBRT), characterized by the delivery of high radiation doses in a limited number of fractions, has been increasingly adopted as a standard approach in the treatment of prostate cancer, due to its favorable efficacy and toxicity profile. CyberKnife (CK) is one of the most commonly used hypofractionated radiotherapy techniques. This preliminary study aimed to evaluate and compare the radiation dose delivery and treatment time of CK-based SBRT using two different collimation systems: the multileaf collimator (MLC) and the IRIS variable aperture collimator, a dynamic device that adjusts its opening to simulate different circular field sizes. A total of 19 patients with low-to-intermediate-risk PCa were selected and treated at the Radiation Oncology Department of the National Cancer Institute IRCCS Fondazione G. Pascale in Naples between January 2024 and January 2025. For each patient, two treatment plans were generated—one with the IRIS collimator and one with the MLC. The results demonstrated that the use of the MLC significantly reduced treatment time while maintaining dosimetric quality comparable to IRIS-based plans. These findings support the clinical benefit of MLC implementation in prostate SBRT with the CK system.
This study evaluates the mechanical behavior of bone-implant assemblies used in treating complex proximal humerus fractures, a clinical challenge due to the anisotropic nature of bone and variability in patient-specific conditions. The aim of this study was to compare the stability and stress distribution of three fixation methods: polyaxial locking plates, monoaxial locking plates, and intramedullary nails. Using 4th-generation composite humerus models, a four-part fracture (Neer IV) was simulated. The assemblies underwent axial compression testing using a universal testing machine, complemented by finite element analysis (FEA) and stereomicroscopy. The results indicate that while both plate types exhibited similar mechanical behavior-with stiffness values around 113-115 N/mm and failure initiated by plastic deformation of the implant-the intramedullary nail configuration demonstrated higher stiffness values under the tested experimental conditions (1084 N/mm), approximately 9.5 times higher than that of the plates. However, the nail assembly failed through brittle fracture of the bone rather than implant deformation. We conclude that while the intramedullary nail configuration demonstrated higher stiffness under the tested experimental conditions, its performance is heavily dependent on bone quality. In contrast, locking plates may provide a more gradual load-transfer behavior by transferring a greater proportion of the mechanical load to the implant, potentially making them more suitable for osteoporotic bone conditions, where reducing excessive stress concentration within the bone tissue may be beneficial.
Stroke is a leading cause of chronic disability, with heterogeneous sensorimotor impairments that are not well captured by standard clinical assessments. While advanced motion capture and robotic systems provide precise measurements, they are not scalable for widespread clinical use. We developed C-MORE (Computer Vision for Movement Observation and Recovery Enhancement), a smartphone-based framework that uses computer vision and machine learning to automatically score the Box and Blocks Test (BBT) and extract quantitative kinematic metrics. The system combines hand tracking with a custom machine learning (ML) architecture to identify valid block transfers and segment task phases. We evaluated C-MORE in 7 individuals with chronic stroke and a cohort of 10 healthy adults. The system achieved 99.0% agreement with ground-truth scoring, with errors below clinically meaningful thresholds. Kinematic measures derived from the system were sensitive to stroke-related impairments, including reduced movement velocity and increased task duration in affected limbs. Exploratory analyses indicated that grasp-related metrics, particularly the ratio of grasp-to-transfer duration, were correlated with independent measures of proprioception. These findings demonstrate that smartphone-based computer vision can provide accurate, scalable assessment of upper-extremity function. C-MORE offers a practical approach for enhancing clinical evaluation and enabling more precise, individualized rehabilitation strategies.
Breast cancer remains the leading cause of cancer-related deaths among women globally. Early detection through mammography is vital for improving survival rates; however, the large volume of medical images and subtle variations in lesion characteristics pose significant challenges to manual interpretation. Recent automated diagnostic models based on deep learning have shown strong potential for breast cancer classification, but challenges such as overfitting, high computational complexity, limited generalization, and insufficient interpretability remain unresolved. This paper proposes a computationally efficient and context-aware deep learning framework for breast cancer classification using transformer-based multi-scale attention mechanisms and explainable artificial intelligence (XAI). The proposed architecture integrates the Hierarchical Multi-Scale Transformer (HMT) and Edge-Aware Local Transformer (ELT) modules to jointly capture global contextual dependencies and boundary-sensitive local representations from mammographic images. ELT improves feature refinement in high-entropy regions, while HMT models global semantic interactions across multiple feature scales. In addition, an Adaptive Contextual Refinement (ACR) module is introduced to preserve semantically consistent feature representations across spatial resolutions. A Meta-Ensemble Classification (MEC) framework combining weighted SVM and K-Nearest Neighbors (KNN) classifiers is further employed using validation-guided class-adaptive weighting. The proposed framework is evaluated on four benchmark mammography datasets, namely CBIS-DDSM, DDSM, INBreast, and MIAS. The proposed model has demonstrated superior accuracy of over 99% across all breast cancer datasets. The model surpassed transformer-based baselines including Swin-T and ViT while maintaining lower parameter complexity and achieving approximately 7% higher accuracy on the CBIS-DDSM dataset. The proposed framework also demonstrated strong cross-dataset generalization and consistently achieved high precision, recall, and F1-score values across all benchmark datasets. To improve model interpretability, Grad-CAM, SHAP, Occlusion Sensitivity Analysis (OSA), and the proposed TIxAI consistency analysis framework are incorporated to provide preliminary explainability assessment for mammographic classification. The explainability analysis demonstrated spatially consistent saliency behavior across benchmark datasets; however, the current evaluation is based on internal saliency consistency rather than external clinical validation using expert lesion annotations. Overall, the proposed framework provides an effective and computationally efficient approach for automated breast cancer classification while improving model explainability and interpretability.
Ischemic heart disease (IHD) is the leading cause of death worldwide, accounting for over eight million deaths each year. IHD encompasses a spectrum of conditions, including atherosclerosis (AS), myocardial infarction (MI), and ischemia/reperfusion (I/R) injury. Programmed cell death (PCD) of endothelial cells (ECs) plays a critical role in IHD pathogenesis, causing microvascular dysfunction, barrier disruption and exacerbation of cardiac injury. PCD involves different signaling pathways, but they are interconnected. Therefore, it is crucial to understand the mechanisms underlying the various forms of PCD in ECs to develop therapeutic strategies for IHD. This review focuses on the molecular mechanisms of PCD of ECs in IHD and provides comprehensive summary of potential cell and gene therapy therapeutic strategies for the treatment of IHD.
Glioblastoma has a high recurrence rate, yet conventional single-time-point imaging fails to capture the dynamic tumor evolution before and after surgery. This study aims to develop a deep learning model based on preoperative and postoperative longitudinal MRI to predict postoperative recurrence risk by capturing imaging dynamics. We propose MambaDiff-Net, which employs a dual-stream encoder to extract multi-scale features from preoperative and postoperative T2WI. It also includes a feature discrepancy computation module to model longitudinal imaging changes, outputting individualized recurrence risk probabilities. We included 139 patients with glioblastoma (59 training, 40 internal validation, 40 external test), with recurrence within 6 months post-surgery as the prediction target. Performance was evaluated using AUC, accuracy, and F1. MambaDiff-Net achieved AUCs of 0.887 and 0.762 in internal and external validation, respectively, significantly outperforming single-time-point models. Kaplan-Meier analysis demonstrated effective risk stratification, and decision curve analysis confirmed superior clinical net benefit. Grad-CAM visualization showed the model’s focus shifting from preoperative tumor parenchyma to postoperative resection cavity margins, consistent with clinical knowledge. A deep learning model based on preoperative-postoperative longitudinal MRI can accurately predict postoperative recurrence risk in glioblastoma. By modeling dynamic imaging changes before and after surgery, it supports individualized treatment decisions.
Atrial fibrillation (AF) is a major cardiac arrhythmia characterized by impaired hemodynamics caused by irregular ventricular activation and loss of coordinated atrial contraction. However, the coupled effects of rhythm irregularity and progressive atrial remodeling on cardiovascular hemodynamics have not been sufficiently quantified. In this study, a closed-loop lumped-parameter cardiovascular framework was developed to investigate hemodynamic alterations under normal sinus rhythm (NSR) and AF conditions. Time-varying elastance functions were used to represent cardiac chamber mechanics, while stochastic RR interval sequences reproduced the irregular ventricular response characteristic of AF. Progressive atrial remodeling was represented through systematic increases in atrial elastance to simulate increasing chamber stiffness. The results demonstrated that AF produced irregular left atrial pressure fluctuations and pronounced beat-to-beat variability in ventricular pressure and volume. Ventricular stroke volume decreased from 70-75 mL under NSR to 55-65 mL under AF conditions. With progressive remodeling, left atrial volume decreased by 36.4%, while ventricular end-diastolic volume increased from 130 to 134 mL, indicating compensatory ventricular adaptation. These findings suggested that atrial stiffening impaired atrial compliance and reservoir function, whereas ventricular adaptation partially compensated for the impairment in atrial mechanical function.
BACKGROUND:This study evaluated the effects of flattening the side of the bending resistance and torsional resistance of nickel-titanium files through finite element analysis of a novel flattened file and a standard nonflattened file. METHODS:For torsion analysis, the tip of the file was fixed at 3 mm, generating a torque of 2.5 N·mm at the handle. For bending analysis of curved root canals (45° and 60°), the handle was kept fixed, a force of 1 N was applied at the tip, and the file was fixed at 3 mm. RESULTS:The standard nonflattened file exhibited better torsional resistance. In contrast, the novel flattened file showed improved flexibility under 45° bending. Under this condition, lower maximum von Mises stress was observed in the flattened design compared with the standard file. At 60° bending, stress distribution varied with loading orientation, and higher stress concentrations were observed in the flattened file under specific bending directions, indicating reduced bending resistance under large deformation conditions. CONCLUSIONS:Since lateral flattening may reduce the cyclic resistance of files, caution should be exercised in the clinical use of such files.
Background: Nuclear medicine healthcare professionals (NMHP) sustain chronic occupational exposure to iodine-131 (I-131), conferring an elevated risk of radiation-induced solid thyroid cancer. Established radiobiological prediction tools derive risk coefficients from atomic bomb survivor data but are not configured for rapid individualized risk assessment in occupational exposure settings. This study examined whether machine learning algorithms can serve as high-precision computational surrogates for excess relative risk estimation in NMHP. Aim: The study aimed to (i) develop and validate three machine learning algorithms for predicting the excess relative risk per unit absorbed dose for radiation-induced solid thyroid cancer (ERR/Gy.RST), (ii) characterize relationships between dosimetric and demographic features and predicted risk, and (iii) identify the optimal algorithm for deployment in occupational health surveillance. Methods: A dataset of 4657 observations was constructed from Life Span Study-derived ERR/Gy parameters, adapted to occupational low-dose conditions, using a dose-and-dose-rate effectiveness factor of 2.0, per ICRP Publication 103. Five features (gender, age at exposure, current age, distance from the I-131 source, and cumulative absorbed dose in the thyroid) were used to train a decision tree regressor (dtcr), a random forest regressor (rfr), and a multilayer perceptron (MLP) neural network algorithm. Results: Cumulative absorbed dose in the thyroid correlated positively with ERR/Gy.RST (r = 0.63, p < 0.01), while radiation source distance demonstrated a strong inverse association (r = -0.38, p < 0.01). The MLP algorithm achieved R-2 score = 0.999, MSE = 0.002, and MAE = 0.010, substantially outperforming the rfr (R-2 score = 0.700, MSE = 0.410, MAE = 0.295) and the dtcr (R-2 score = 0.510, MSE = 0.654, MAE = 0.289). Conclusions: The MLP algorithm provides a high-fidelity surrogate for established ERR/Gy.RST projection tools in the NMHP context, enabling computationally efficient, feature-integrated occupational radiation-induced thyroid cancer risk quantification. These findings suggest that machine learning-based surrogate modeling is a practical, scalable complement for occupational health practitioners and radiation protection officers to support individualized surveillance of radiation-induced thyroid cancer risk in nuclear medicine departments.
This study presents a validation-aware EEG framework based on Chaotic Pattern of Prime Numbers (CPPN) features for depression treatment-response modelling across one SSRI cohort and two rTMS cohorts. CPPN features were evaluated through a seven-protocol validation hierarchy spanning random segment splitting, segment-level cross-validation, nested segment-level cross-validation, leave-N-subjects-out, fixed-feature leave-one-subject-out (LOSO), nested leave-N-subjects-out, and nested LOSO, with normalisation, NCA ranking, feature-count selection where applicable, and model fitting confined to the appropriate training partitions. In the representative K-nearest neighbour (KNN) comparison, segment-level 10-fold CV achieved accuracies of 98.79% for Mumtaz SSRI, 99.32% for small Atieh rTMS, and 99.42% for big Atieh rTMS, demonstrating strong discriminative structure in the CPPN feature space. In the available segment-level KNN comparison, CPPN features with fold-internal NCA-selected feature sets exceeded conventional statistical EEG features by 29.53, 16.33, and 11.45 percentage points across the three cohorts. Subject-wise validation produced lower and more cohort-dependent estimates, with the best fixed-feature LOSO accuracy of 80.00% and the best nested LOSO accuracy of 73.33% in the small Atieh rTMS cohort. These results show that CPPN provides a compact, inspectable and computationally accessible EEG feature representation, while the validation hierarchy gives a transparent account of how performance changes from segment-level separability to held-out-subject evaluation. The main contribution is methodological: this study combines an original CPPN feature representation with explicit validation-depth analysis, leakage-aware feature selection, and interpretable channel/bin inspection. It therefore provides a rigorous basis for future externally validated EEG treatment-response studies without claiming prospective clinical deployment from the present retrospective cohorts.
The application of functional electrical stimulation (FES) to restore hand motor function remains challenging due to the difficulty of calibrating multi-channel stimulation to produce coordinated finger movements. This study proposes a compositional FES calibration framework to customize the stimulation of isolated finger actions and enable their combination into functional hand gestures. The proposed method was validated through a two-session experimental study involving thirteen participants. In the first session, subject-specific stimulation sites and parameters were identified for eight individual finger movements using a structured spatial grid defined over the forearm. The second session, conducted on a subset of five participants, evaluated the generation of seven hand gestures derived from combinations of the isolated movements. Results showed that ten of the thirteen participants achieved at least six movements, while three participants successfully elicited all targeted motions. Successfully elicited movements were generally well isolated, although thumb and ring/little finger extensions proved more difficult to isolate. The second session demonstrated that individually calibrated finger activations can be combined to produce coordinated multi-finger movement patterns, with average finger excursions matching the expected motions. Overall, these preliminary results support the use of compositional calibration strategies to achieve functional multi-finger control with multi-channel FES.
Accurate analysis of lesions in colonoscopic images is essential for computer-aided diagnosis. However, most existing methods are designed for single-lesion segmentation and assume a predefined lesion category, limiting their applicability in real-world scenarios where multiple lesion types exhibit similar visual characteristics. To address this issue, we propose a unified framework for the joint classification and segmentation of dual-type lesions in colonoscopic images, enabling simultaneous identification and localization of submucosal lesions and polyps/adenomas. The proposed method integrates joint supervision, context-aware feature enhancement, and ambiguity-aware optimization to improve consistency between semantic recognition and spatial delineation. In particular, a soft-label supervision strategy is introduced to alleviate semantic ambiguity, while an imbalance-aware loss design enhances segmentation accuracy and reduces false negative predictions. Extensive experiments on both private and public datasets demonstrate that the proposed method achieves superior performance compared with representative CNN- and transformer-based approaches. Notably, the method shows clear advantages in segmentation accuracy, localization precision, and robustness under challenging conditions. Ablation studies further confirm the effectiveness of each component in the proposed framework. These results indicate that the proposed approach provides an effective solution for dual-type lesion analysis and has the potential to assist clinical decision-making in gastrointestinal endoscopy.
Conductive intracardiac communication (CIC) is one of the most innovative and promising communication technologies in multi-point cardiac pacing schemes that utilize the heart as the transmission channel in recent years. Current research predominantly focuses on static channel characteristics. Although some studies have explored dynamic responses, they are largely confined to basic amplitude-frequency and amplitude-time behaviors, lacking in-depth analysis of underlying dynamic mechanisms such as path loss, shadowing, multipath, and Doppler effects. Designing CIC systems solely on the basis of static properties can result in inaccurate channel estimation, distorted channel state information (CSI), and elevated bit error rate (BER). To solve the problems of dynamic channel measurement and modeling, this paper for the first time proposes a dynamic channel modeling method for CIC based on sinusoidal response and impulse response. Firstly, we develop a physical simulation and miniaturized measurement setup to measure the dynamic cardiac channel, and analyze the amplitude-frequency characteristics and amplitude-time characteristics. The influence of factors such as instrument differences, heart rate, flow rate, and motion artifacts is also discussed. Secondly, we systematically analyze the path loss, shadowing effect, multipath effect, and Doppler effect of the CIC channel. Combined with the dynamic channel characteristics and parameters, we propose a composite fading dynamic channel model and analyze the BER performance of baseband signal transmission and On-Off Keying (OOK) modulation systems. We conclude that (1) the CIC channel exhibits capacitive characteristics. Fixed electrodes can effectively suppress motion artifacts. (2) The dynamic channel gain of CIC varies periodically with the heartbeat, and the fluctuation range of the signal is less than 1-2 dB. (3) The dynamic CIC channel presents extremely weak shadow fading, no significant multipath, and no measurable Doppler characteristics, belonging to an extremely slow-fading channel. This work provides effective dynamic channel measurement approaches and a parameter basis for the transceiver design of CIC and a reliable model for the simulation of CIC systems.
Traditional 3D bioprinting of corneal constructs relies on planar slicing, which often results in a significant stairstep effect and the loss of anatomical curvature. Curvilinear layering has emerged as a promising alternative to address these limitations. The presented methodology, based on non-planar layer integration, ensures a smoother surface finish. The model's surface is identified via vertex normals and reconstructed using the Poisson method. Finally, surface parametrization is applied to generate spatially curved trajectories. To validate the algorithm, corneal constructs were printed using a planar and the proposed non-planar approach. Quantitative evaluation of micro-Computed Tomography data revealed that the non-planar approach achieved significantly higher morphological fidelity, successfully replicating the intended parabolic profile of the human cornea. Furthermore, the non-planar constructs demonstrated adequate functional performance, characterized by high optical transparency. Thereby, the feasibility of printing non-planar layers using the proposed novel approach is successfully demonstrated. Furthermore, the comparative analysis confirms the method's potential for corneal biofabrication when compared to traditional planar methods.
The present study investigated the effect of a 3D-printed nanocomposite scaffold on bone healing in vivo. The scaffolds used were made from the bioresorbable thermoplastic polycaprolactone polymer, blended with Multi-Walled Carbon Nanotubes functionalized with chitosan, and manufactured with a rectilinear infill pattern and interconnected pores of 500 μm in size. The study included three groups of 10 Wistar rats, in which a 2 mm bone defect was created in the middle of the right femur. In the scaffold/peptide group, the gap was filled with the scaffold loaded with a peptide corresponding to human pleiotrophin amino acids 48-56 (PTN48-56), and the fracture was stabilized with a 12 mm K-wire as an intramedullary nail. In the scaffold group, the scaffold did not contain the peptide, and in the control group, the bone defect was stabilized without the use of a scaffold. Radiological examination revealed that bone healing was achieved on average in 6.6 weeks in the scaffold/peptide group, 7.2 weeks in the scaffold group, and 8.1 weeks in the control group. Histopathological examination performed 2 weeks postoperatively showed that angiogenesis in the scaffold/peptide group was 1.5 times higher than in the scaffold group and 2.5 times higher than in the control group. In conclusion, our osteo-inductive 3D-printed scaffold covered with PTN48-56 is a promising option for accelerating bone defect healing.
