Search Results (269)

Reliable acquisition of vital signs is essential in prehospital emergency care; however, conventional contact-based sensors may delay assessment, cause patient discomfort, increase cross-contamination risk, and perform poorly during motion. To address these limitations, this study developed a body-worn smart camera system for paramedics incorporating a remote photoplethysmography (rPPG)-based signal-processing algorithm to estimate heart rate (HR), oxygen saturation (SpO₂), and blood pressure (BP) in real time from subtle facial blood volume fluctuations. The system was evaluated in a repeated-measures full-factorial experiment with three adults under varying lighting, camera positions, and stabilization conditions. Performance was assessed using mean absolute error (MAE) relative to contact-based reference devices. HR (MAE: 1.20–5.60 bpm) and SpO₂ (MAE: 0.93–3.00%) showed relatively small errors relative to the reference measurements across the tested conditions, whereas BP estimation showed larger errors (SYS: 5.00–14.20 mmHg; DIA: 3.87–11.60 mmHg), indicating the need for further algorithm refinement. The head-mounted configuration provided the best performance (HR MAE: 1.96 bpm). These preliminary findings support the technical feasibility of a wearable, contactless rPPG-based vital sign monitoring system under the tested conditions, while identifying BP estimation as the primary target for future improvement. Further validation in larger and more diverse populations is required before clinical or prehospital applicability can be established. Full article

Background/Objectives: Accurate anatomic reduction is a major determinant of outcomes after Lisfranc injury, but the optimal fixation method remains controversial. Although screws/plates are commonly used, Kirschner-wire (K-wire) fixation may provide adequate stability after precise open reduction. Methods: We retrospectively reviewed 62 patients who underwent surgery for acute unstable Lisfranc injuries at a single institution between 2002 and 2024. Fifty patients underwent open reduction and K-wire fixation, and 12 underwent screw/plate fixation. Propensity score overlap weighting was performed using age, sex, body mass index, time from injury to surgery, and injury mechanism. The primary outcome was final follow-up medial cuneiform-second metatarsal (C1-M2) gap; Post-traumatic osteoarthritic change was the secondary outcome. Results: After overlap weighting, baseline covariates were well balanced. The K-wire group had a significantly smaller final C1-M2 gap than the screw/plate group (1.919 ± 0.115 mm vs. 2.536 ± 0.279 mm, p = 0.046; weighted mean difference, 0.617 mm; 95% confidence interval, 0.013–1.220). Post-traumatic osteoarthritic changes were less frequent in the K-wire group (29.6% vs. 57.7%), although the difference was not significant (p = 0.091). Conclusions: When accurate open reduction was achieved, K-wire fixation provided radiographic outcomes comparable to and, regarding the C1-M2 gap, potentially more favorable than screw/plate fixation. Despite reduced construct rigidity, multiple K-wire fixations appeared to provide sufficient stability to maintain anatomic reduction and may reduce subtle reduction loss during screw/plate insertion. These findings suggest that K-wire fixation is a reasonable, less articular-invasive fixation option for acute unstable Lisfranc injuries. Full article

Background: Volumetric modulated arc therapy (VMAT) for stereotactic body radiotherapy (SBRT) involves highly modulated dose distributions and steep dose gradients, increasing the importance of patient-specific quality assurance (QA). Gamma index analysis is widely used for comparing measured and treatment planning system (TPS)-calculated dose distributions; however, its sensitivity to small systematic mechanical errors remains controversial, particularly across different detector systems and normalization methods. This study aimed to investigate the sensitivity of various gamma index criteria to intentional linear accelerator-based mechanical errors, including multileaf collimator (MLC) positional deviations and collimator rotation errors, using four dosimetric systems. Additionally, global and local gamma analyses were compared to evaluate their ability to detect clinically relevant geometric deviations in SBRT VMAT. Methods: Twenty-five lung SBRT VMAT plans were retrospectively selected. For each patient, six additional plans containing systematic MLC aperture widening errors (0.25, 0.5, 1, and 2 mm) and collimator rotation errors (0.5° and 2°) were generated, resulting in 175 treatment plans. Each plan was delivered to five different patient-specific QA dosimetric systems, resulting in a total of 875 QA measurements. Patient-specific QA measurements were performed using EPID-based EPIQA, ArcCHECK (SNCPATIENT/3DVH), COMPASS (Matrixx Evolution), and Octavius 4D systems. Gamma analyses were conducted using 3%/3 mm, 3%/2 mm, 2%/2 mm, 2%/1 mm, 1%/2 mm, and 1%/1 mm criteria with a 10% dose threshold. Pearson correlation analysis assessed relationships between global and local gamma results. Linear regression slopes quantified sensitivity to MLC aperture widening errors. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values were calculated to evaluate error detectability. Results: Gamma sensitivity varied considerably depending on the characteristics of the dosimetric system (including detector resolution, reconstruction algorithm, and evaluation method) as well as the selected gamma criteria. The 2%/1 mm criterion consistently demonstrated high sensitivity across all systems, providing strong discrimination of ≥0.5 mm MLC errors and near-perfect AUC values for ≥1 mm deviations. The 1%/1 mm criterion yielded the steepest regression slopes but produced unstable passing rates, including in error-free plans, particularly in lower-resolution systems. Conventional 3%/3 mm and 3%/2 mm criteria frequently failed to detect clinically relevant submillimeter MLC deviations. EPID-based EPIQA showed the highest overall sensitivity and AUC performance for small errors, whereas ArcCHECK and Octavius 4D exhibited reduced responsiveness to subtle deviations. Conclusions: Gamma index performance in SBRT VMAT QA is strongly dependent on detector characteristics and gamma configuration. Among the evaluated criteria, 2%/1 mm provided the most balanced combination of sensitivity and clinical stability. Widely used 3%/3 mm thresholds were insufficient for detecting submillimeter geometric deviations. Detector-specific and technique-specific gamma protocols should be implemented to ensure reliable identification of clinically relevant mechanical errors in high-precision radiotherapy. Full article

Eating disorders are associated with substantial morbidity and mortality yet remain underidentified in general mental health practice, delaying intervention and worsening outcomes. Counselor preparation often provides limited eating disorder content within broader psychopathology coursework, leaving trainees underprepared to recognize subtle, culturally diverse, and nonstereotypical presentations. This conceptual paper draws on scholarship in counselor education, body image, embodied self-awareness, and eating disorder training to propose a four-domain framework intended to strengthen counselor preparation for eating disorder recognition and clinical response. The framework includes foundational knowledge of eating disorder diagnosis, medical and nutritional risk, levels of care, and multidisciplinary treatment; reflective body-related self-awareness concerning clinicians’ beliefs about food, weight, health, exercise, appearance, and culture; embodied and creative practices that strengthen awareness of bodily and relational responses; and clinical translation through direct assessment, supervision, consultation, and referral. A seven-session graduate course illustrates how the framework can be implemented while protecting students from coerced personal disclosure. Within the U.S. counselor education and mental health training context, policy recommendations address curriculum infusion, weight stigma, countertransference, competency assessment, and basic detection and referral preparations. Integrating body-related reflection with diagnostic knowledge may offer a promising approach for helping clinicians recognize when eating disorder and body image concerns warrant further inquiry, reduce stereotype-based omissions, and respond more deliberately across diverse clinical settings; however, whether embodied training improves detection outcomes remains an empirical question. Full article

Classroom behavior detection plays an important role in intelligent education by providing objective visual evidence for the analysis of learning engagement, classroom interaction assessment, and teaching evaluation. However, accurate behavior detection for individual students in real classroom environments remains challenging due to subtle behavior-related cues, visually similar action categories, occlusion, and complex background interference. To address these challenges, this paper proposes a Fine-grained Gated Detail Network (FGD-Net) for the fine-grained detection of individual student behaviors in classroom scenes. The proposed network improves behavior representation from three complementary aspects. Firstly, a Fine-grained Dynamic Recalibration Convolution Block (FDRC) is designed to enhance behavior-sensitive local regions, such as hands, arms, heads, and upper-body postures. Secondly, a Multi-path Gated Context Aggregation Block (MGCA) is introduced to aggregate complementary contextual information from multiple feature paths, thereby strengthening the semantic representation of visually similar classroom behaviors. Thirdly, a Shift-guided Detail Reconstruction Upsampling Block (SDRU) is developed to alleviate spatial detail loss during multi-scale feature fusion and improve the reconstruction of small-scale behavior-related cues. Extensive experiments are conducted on the SCB5 and SCB3 classroom behavior detection datasets. The experimental results show that FGD-Net achieves better detection performance than recent detectors on both datasets. These results demonstrate the potential of FGD-Net as an efficient visual perception model for scalable classroom video analytics and intelligent education applications. Full article

Reliable identification and behavioural tracking of individual fish are increasingly required in aquaculture monitoring and ecological conservation, yet such tasks often rely on extremely limited image samples. Individual-level fish recognition remains challenging because subtle inter-individual variations in stripe patterns, spots and body markings are difficult to distinguish, while annotated datasets are scarce and costly to construct. To address these challenges, this study proposes Squeeze-and-Excitation Feature-Fusion Window Transformer (SEFFwin), a lightweight vision Transformer derived from Swin Transformer V2 for ultra-fine-grained fish recognition under extreme few-shot conditions. Through structured pruning, the SEFFwin backbone contains approximately 11.30 million parameters, excluding the task-specific classification layer. To support evaluation, we construct Koi-fish-3, a dedicated few-shot benchmark consisting of three individual koi categories, with only two training images and 100 validation images per class. Transfer learning, data augmentation and knowledge distillation are further incorporated to improve model optimisation under severely limited supervision. Experimental results show that SEFFwin achieves 92.0% top-1 accuracy on Koi-fish-3, outperforming representative lightweight baselines while maintaining high computational efficiency. Post-hoc interpretability analysis indicates that SEFFwin consistently attends to biologically meaningful stripe and spot patterns and can weakly localise class-specific regions. These findings demonstrate that SEFFwin provides an accurate and efficient solution for individual fish recognition under extreme data scarcity, offering practical value for intelligent aquaculture and ecological monitoring, while also providing insights into compact Transformer design for low-resource fine-grained recognition. Full article

When LiDAR detects underwater targets, the water severely attenuates the laser beams, making it impossible to extract valid echo information during 3D reconstruction of urban water bodies. This study proposes a Multi-Scale Spectral Adaptive Loss Generative Adversarial Network Based on Morphology-Spatiotemporal Decoupled Attention (MSAGAN) that effectively enhances far-field underwater echo signals for LiDAR. Its core components consist of three parts: Morphology-Aware Dynamic Receptive Field Attention (MADRA), Spatial-Temporal Decoupled Frequency-Enhanced Global Feature Fusion Block (STDFBlock), and Adaptive Dynamic Adjustment Loss Function Based on Frequency-Domain Decomposition and Gradient Response (FGADLoss). The model precisely identifies the narrow and curved local structures of the echo signals during the feature extraction process, improving the precise detection of subtle structural changes in the echo signals and enabling the extraction of valid echo signal features from a background of numerous invalid echo signals. The model reduces image fragmentation and center-of-mass drift during echo signal augmentation, improving the accuracy of water body environments’ 3D reconstruction. Through this model, the average point cloud density per square meter for lakes and ponds increased by 2.12 and 3.54, respectively, enabling effective reconstruction of urban water bodies information and offering a high-quality data basis for underwater object recognition and bathymetric surveying. Furthermore, this method effectively addresses the challenge of simultaneously obtaining degraded and ideal streak images that match the echo signals of underwater detection targets, and it also offers advantages in terms of training data requirements, making it particularly well-suited for real-world underwater detection scenarios where paired ideal-degraded data is scarce. Full article

The taxonomic status of Cipangopaludina chinensis and C. cathayensis remains controversial due to morphological overlap. We combined morphometrics (24 landmarks vs. 200 semilandmarks) with multi-locus phylogenetics (COI, 16S rRNA, H3, 28S rRNA) and haplotype networks on sympatric populations from Liuzhou and GenBank. Morphometrics completely separated C. chinensis_lz from C. cathayensis_lz in shell shape; key diagnostic traits include aperture size, spire height, and body whorl inflation. The high-density semilandmark method outperformed discrete landmarks in dimensionality reduction and fine-scale resolution, capturing subtle apex and lateral whorl variations. No sexual dimorphism occurred in C. cathayensis_lz, with only weak dimorphism in C. chinensis_lz. Molecular data were ambiguous: the species tree and mitochondrial gene tree recovered C. chinensis and C. cathayensis as monophyletic, but the nuclear gene tree showed mixing of C. chinensis_lz/C. cathayensis_lz with C. wisseli, C. chinensis, and C. cathayensis. Haplotype networks revealed haplotypes sharing between C. chinensis_lz and C. cathayensis_lz, yet neither population shared haplotype with GenBank sequences of the two nominal species. Morphology strongly supports C. chinensis_lz and C. cathayensis_lz as distinct species, whereas molecular evidence shows only low-level differentiation and discordant signals between mitochondrial and nuclear markers. We conclude they are likely valid species, yet mitonuclear discordance warrants further genomic investigation. Despite no evidence of microhabitat partitioning, the stable morphological divergence between these sympatric morphospecies supports separate management units to conserve phenotypic diversity and local adaptive potential. This study validates geometric morphometrics as an efficient frontline tool for biodiversity assessment in morphologically diverse yet genetically conserved freshwater snails, and reinforces the need for genome-wide data to resolve species boundaries within the Cipangopaludina complex. Full article

The research investigates the psychopathological mechanisms through which perceived leader favoritism (PLF) can affect counterproductive work behavior (CWB) through the mediating effects of employee jealousy toward their coworkers and the specialized form of envy known as malicious envy. Integrating Social Comparison Theory with Affective Events Theory, the study proposes that perceived favoritism triggers unfavorable social comparisons, which in turn evoke negative emotional states that manifest in dysfunctional workplace behaviors. The research used a quantitative study design to gather information from 436 employees working in hotels. The researchers used structural equation modeling (SEM) to analyze the research data while they also conducted reliability and validity assessments. The study shows that perceived leader favoritism leads to higher organizational counterproductive work behavior (CWB-O) and higher interpersonal counterproductive work behavior (CWB-I) among employees. The study found that PLF leads to higher employee jealousy levels which result in higher malicious envy levels that drive CWB behavior. The research found that jealousy and malicious envy function as central psychological pathways which connect favoritism to workplace deviance. This study offers a new contribution to the existing body of knowledge about leadership by extending its scope to investigate how subtle favoritism practices lead to harmful results while explaining the emotional mechanisms which cause counterproductive behavior. The research develops an integrated framework which helps people comprehend how perceived leader favoritism affects emotional responses and behavioral patterns within modern workplaces. Full article

Background: Despite normal lung imaging and preserved pulmonary and cardiac function, many patients with long COVID continue to experience persistent respiratory symptoms. This study aimed to quantify the pulmonary blood and airway volumes in patients with long COVID compared with healthy controls and to evaluate the associations of COVID-19 vaccination with these imaging parameters. Methods: Patients with long COVID presenting with persistent respiratory symptoms despite normal laboratory findings, pulmonary function tests, chest radiography, and chest computed tomography (CT) were prospectively enrolled. CT datasets were analyzed using functional respiratory imaging (FRI), incorporating the three-dimensional reconstruction and automated segmentation of the lungs, airways, and pulmonary vasculature. Quantitative imaging parameters were compared with those of historical healthy controls from the COPDGene study, matched for age, sex, body mass index, comorbidities, and pulmonary function test parameters. Results: Thirty patients with long COVID (mean 221 ± 128 days after confirmed SARS-CoV-2 infection) and 30 matched healthy controls were included. Compared with controls, patients with long COVID demonstrated significantly lower pulmonary blood volumes in small and large pulmonary vessels, together with significantly reduced intrapulmonary airway volumes. Within the long COVID cohort, full COVID-19 vaccination was associated with a significantly greater small-vessel pulmonary blood volume and lobar airway volume compared with non-vaccinated individuals. Conclusions: These findings indicate that patients with long COVID exhibit persistent reductions in pulmonary blood and airway volumes despite normal conventional imaging and pulmonary function tests, suggesting the presence of subtle microvascular and small-airway abnormalities that may contribute to ongoing respiratory symptoms. The association between full COVID-19 vaccination and higher small-vessel pulmonary blood and lobar airway volumes suggests a potential protective effect on pulmonary structure and function; however, these findings require confirmation in larger, prospective controlled studies. Full article

Despite the rapid advancement of Emotion Recognition in Conversation (ERC), prevailing systems that primarily integrate language and speech exhibit substantial performance disparities on underrepresented emotion classes (e.g., Fear, Disgust). This study investigates whether fine-grained non-verbal visual modalities (facial action units, hand gestures, and body pose) can effectively mitigate these biases. We propose a multi-stream fusion architecture combining language, speech, and engineered pose-aware visual features, trained with class-imbalance-aware objectives. Experiments on MELD demonstrate that hybrid pose augmentation improves F1 on the least frequent classes: Fear +9.19%, Disgust +6.07%, Sadness +6.46%. We achieve an overall weighted F1 of 68.79%, competitive with recent state-of-the-art systems while uniquely targeting minority-class debiasing. These results establish fine-grained body language as a critical debiasing signal, recovering accuracy on the subtle expressions that text and speech alone fail to capture. Full article

Background: In recent years, aesthetic medicine has progressively prioritized conservative treatment volumes, subtle enhancements, and skin quality improvement over volumization. This study evaluates patient-reported psychosocial outcomes, satisfaction, and regret rates following minimally invasive aesthetic procedures using validated instruments. Methods: A review was conducted in accordance with PRISMA guidelines. PubMed, Scopus, and Cochrane Library were searched for studies reporting outcomes using validated PROMs (FACE-Q, GAIS, Decision Regret Scale, BDDQ, DCQ and COPS) with a minimum follow-up of 6 months. Studies evaluating facial botulinum neurotoxins, hyaluronic acid fillers, and biostimulation treatments were included. Given the heterogeneity in study design and outcome reporting, findings were synthesized narratively with descriptive comparisons across treatment modalities. Results: Increased treatment intensity was not consistently associated with greater satisfaction, and higher dose or volume often corresponded to more dissatisfaction and regret. The evidence for this pattern was stronger for botulinum toxin and hyaluronic acid fillers; weaker for biostimulators and preliminary for post-GLP-1 facial changes. Conservative approaches were associated with favorable PROMs, and unrealistic expectations, body dysmorphic disorder, and insufficient pre-treatment counseling were the principal predictors of poor outcomes. Conclusions: Patient satisfaction was not proportional to treatment intensity, particularly when results were perceived as unnatural or overcorrected. This relationship appears associative rather than causal, as patients receiving more intense treatment may differ in expectations, history, and psychological profile. A PROM-driven, patient-tailored approach seems more likely to produce durable satisfaction and minimize regret. Full article

Detecting localized morphological anomalies in three-dimensional point clouds is difficult because geometric deviations are entangled with rigid pose variation, residual registration error, sampling noise, and normal inter-subject variability. This challenge is particularly relevant in translational neuroimaging, where abnormal shape changes may be subtle and abnormal annotations are scarce. We propose an unsupervised framework that formulates 3D anomaly detection as a two-stage factorization problem, termed AdvFlow3D-AD. First, Fast Global Registration, followed by multi-scale Iterative Closest Point refinement, establishes a common geometric reference frame and reduces rigid-body nuisance variation. Second, an adversarially regularized normalizing flow models the residual distribution of aligned normal coordinates, enabling localized anomaly scores based on distance from the learned normal latent support. Percentile calibration on normal data then defines interpretable point-level and object-level operating points without requiring abnormal samples during training. We evaluate AdvFlow3D-AD on the Real3D-AD and Anomaly ShapeNet3D datasets, achieving a point-level area under the receiver operating characteristic curve (AUROC) of 0.747 on Real3D-AD and an object-level AUROC of 0.816 on Anomaly ShapeNet3D. We further present an exploratory neurodevelopmental brain-shape case study involving pediatric perinatal-asphyxia cases. The resulting anomaly maps showed qualitative spatial correspondence with anatomically plausible hippocampal and cerebellar regions under neuroradiological review. These results suggest that separating geometric nuisance variation from residual morphology can support interpretable anomaly localization when abnormal labels are limited. Full article

Accurate automated interpretation of upper-extremity musculoskeletal radiographs remains challenging because fracture appearance varies across anatomical regions and can be subtle under class imbalance. This study proposes a two-stage deep learning framework for MURA-based X-ray analysis, aiming to improve body-part recognition and body-part-wise abnormality detection. Multiple architectures were first compared for seven-class body-part classification, after which the selected hybrid Xception-Swin model was fine-tuned for abnormality detection within each anatomical subset. The framework combines Xception-derived local structural features with Swin Transformer contextual features using attention-based fusion, and performance was evaluated using accuracy, F1-score, AUC-ROC, Cohen’s kappa, calibration, component-level ablation, post hoc explainability, and zero-shot FracAtlas validation. For body-part classification, the model achieved accuracy = 0.9643, macro F1 = 0.9574, AUC-ROC = 0.9963, and kappa = 0.9579. For abnormality detection, accuracy ranged from 0.7289 to 0.8538, F1 from 0.7191 to 0.8508, AUC from 0.7693 to 0.9080, and kappa from 0.4449 to 0.7071. Ablation on hand and humerus radiographs showed the highest macro F1 with Hybrid Attention, while FracAtlas validation yielded AUC = 0.8247 and kappa = 0.5812. The results support complementary CNN-Transformer fusion and indicate preliminary cross-dataset generalizability. Implementation resources are available at Zenodo. Full article

Background: Liver cirrhosis is frequently associated with cardiovascular abnormalities collectively referred to as cirrhotic cardiomyopathy, characterized by impaired cardiac reserve and subclinical myocardial dysfunction despite preserved conventional systolic function. Advanced myocardial deformation imaging techniques, including two-dimensional speckle-tracking echocardiography (2D-STE) and cardiac magnetic resonance feature tracking (CMR-FT), may allow earlier detection of subtle ventricular impairment. We performed a systematic review and meta-analysis to comprehensively evaluate conventional and deformation-derived indices of biventricular systolic function in cirrhotic patients. Methods: PubMed, Scopus, and EMBASE databases were systematically searched for observational studies evaluating myocardial systolic function in adult cirrhotic patients using 2D-STE and/or CMR-FT. Comparative meta-analyses between cirrhotic patients and controls were performed using standardized mean differences (SMDs) with 95% confidence intervals (CIs). Separate analyses were conducted for left ventricular ejection fraction (LVEF), left ventricular global longitudinal strain (LV-GLS), left ventricular global circumferential strain (LV-GCS), left ventricular global radial strain (LV-GRS), right ventricular ejection fraction (RVEF), and right ventricular global longitudinal strain (RV-GLS). Weighted pooled descriptive analyses of clinical, laboratory, echocardiographic, and CMR findings were additionally performed. Results: Twenty studies including 1553 cirrhotic patients and 498 controls were included, whereas 14 studies were eligible for quantitative meta-analysis. Conventional LVEF remained globally preserved and showed no significant overall difference between cirrhotic patients and controls, although CMR-based studies demonstrated mildly higher LVEF values in cirrhosis. Meta-analysis revealed no significant overall differences in LV-GLS, LV-GCS, LV-GRS, or RVEF, whereas RV-GLS was significantly reduced in cirrhotic patients. Substantial heterogeneity was observed across most deformation analyses. Meta-regression demonstrated significant associations between LV-GLS variability and age, body mass index, MELD score, diabetes prevalence, heart rate, systolic blood pressure, and software vendor. Descriptive pooled analyses demonstrated larger cardiac chamber dimensions, increased filling pressures, mildly increased pulmonary pressures, and increased extracellular volume fraction values in cirrhotic populations. Conclusions: Patients with liver cirrhosis exhibit preserved conventional systolic function despite evidence of subtle myocardial mechanical abnormalities, particularly involving right ventricular longitudinal mechanics and diastolic function. Advanced deformation imaging with 2D-STE and CMR-FT may improve early detection of subclinical cardiac involvement in cirrhotic cardiomyopathy. Full article