Search Results (4,742)

Balance assessment is crucial for health monitoring and rehabilitation evaluation of neurological diseases like Parkinson’s disease (PD) and stroke. The Berg Balance Scale (BBS) is a widely used clinical tool for balance evaluation. However, its dependence on trained therapists for subjective, time-consuming assessments limits its scalability. Current researchers have proposed several automated assessment systems. However, they suffer from difficulty in use in clinical settings and the need for feature engineering. The rapid advancement of wearable inertial measurement units (IMUs) provides an objective tool for motion analysis that is suitable for use in clinical environments. Thus, to address the limitations of manual scoring and complexities of capturing gait features, we proposed an automated BBS assessment system using an attention-based deep learning algorithm with IMU data, integrating convolutional neural networks (CNNs) for spatial feature extraction, bidirectional long short-term memory (Bi-LSTM) networks for temporal modeling, and attention mechanisms to emphasize informative features. Validated with 20 healthy subjects (young and elderly) and 20 patients (PD and stroke), the system achieved a mean absolute error (MAE) of 1.1627 and root mean squared error (RMSE) of 1.5333. Requiring only 5 min of walking data, this approach provided an efficient, objective solution for balance assessment to assist healthcare physicians as well as patients in their own health monitoring. The key limitations included: a limited generalizability to severely impaired patients who were unable to walk independently, and the inability to predict the score of individual tasks. Full article

Background: The superficial circumflex iliac artery perforator (SCIP) flap is widely recognized for its reliability and minimal donor site morbidity in reconstructive surgery. However, its safety and efficacy in elderly patients—a growing demographic with increased comorbidities—remain less understood. This study aims to evaluate the clinical outcomes of the SCIP flap in elderly patients compared to younger patients, focusing on flap survival, complications, and recovery. Methods: In this retrospective cohort study, conducted at Guangdong Provincial People’s Hospital, from 28 August 2019 to 7 June 2024, we included 37 patients who underwent SCIP flap procedures for reconstruction. Patients were divided into two groups: younger (15–59 years) and elderly (≥60 years). Key variables analyzed included demographics, comorbidities, flap characteristics, recipient sites, arterial sources, and surgical outcomes. Univariate analysis and ROC curve analysis were used to explore the impact of age on flap survival and complications. Results: The cohort consisted of 28 younger and 9 elderly patients. Vascular disease was significantly more prevalent in the elderly group (88.9% vs. 21.4%, p = 0.001), and abnormalities in the CTA results indicate that the elderly cohort exhibited a 29-fold increased odds of vascular disease compared to younger patients (OR = 29.17, 95% CI: 4.82–176.40, p = 0.001). However, no significant differences were found between the groups in terms of flap area, recipient sites, or arterial sources. Hospital stay duration and flap survival rates were comparable across both age groups, with no cases of total flap loss reported. While systemic complications were somewhat higher in the elderly group, this difference did not reach statistical significance. The ROC analysis (AUC = 0.52) indicates that age alone is not a significant predictor of flap survival. Conclusions: The SCIP flap is a safe and effective reconstructive option for elderly patients, despite a higher incidence of vascular disease. Flap survival and postoperative recovery were favorable, indicating that the procedure is viable for older patients. These findings support the continued use of SCIP flaps in aging populations, emphasizing the need for individualized surgical approaches to optimize patient outcomes. Full article

The ubiquitous presence of per- and polyfluoroalkyl substances (PFAS) in the environment has garnered global public concern. Epidemiological studies have proved that exposure to PFAS is associated with human health risks. Although evidence demonstrated the toxic mechanisms of PFAS based on animal models and traditional cell cultures, their limitations in inter-species differences and lack of human-relevant microenvironments hinder the understanding of health risks from PFAS exposure. There is an increasing necessity to explore alternative methodologies that can effectively evaluate human health risks. Human organoids derived from stem cells accurately mimic the sophisticated and multicellular structures of native human organs, providing promising models for toxicology research. Advanced organoids combined with innovative technologies are expected to improve understanding of the breadth and depth of PFAS toxicity. Full article

The electrocardiogram (ECG) has long been considered the non-invasive gold standard in diagnosing heart diseases. However, its connection with the cardiac molecular biology remains somewhat unclear. Therefore, modeling the electrophysiological behavior of the heart provides an important theoretical complement to clinically observable data. This study employed an electrophysiological model, integrating a bidomain model with the Fitzhugh–Nagumo (FHN) model, to compute an ECG and body surface potential maps (BSPMs). Parameters from previous studies were simulated individually for the cardiac domain. A specific set of parameters was selected based on comparisons of the morphology of the 12-lead ECG. The effect of the heart position relative to the torso on the 12-lead ECG was analyzed using a simplified whole-heart model to approximate the realistic heart position within the torso. Significant waveform changes were observed in leads $VIII$ and $aVL$, as compared to other leads. This study employed a realistic heart–torso model, in contrast to earlier studies. External stimuli were incorporated into the original electrophysiological model to account for the electrical isolation between the atria and ventricles. The morphology of the simulated 12-lead ECG closely matched that of clinically observed data. Full article

Background: Primary and secondary salivary gland malignancies differ significantly in treatment and prognosis. However, conventional ultrasonography often struggles to differentiate between these malignancies due to overlapping imaging features. We aimed to develop and evaluate noninvasive diagnostic models based on traditional ultrasound features, radiomics, and deep learning—independently or in combination—for distinguishing between primary and secondary salivary gland malignancies. Methods: This retrospective study included a total of 140 patients, comprising 68 with primary and 72 with secondary salivary gland malignancies, all pathologically confirmed, from four medical centers. Ultrasound features of salivary gland tumors were analyzed, and a radiomics model was established. Transfer learning with multiple pre-trained models was used to create deep learning (DL) models from which features were extracted and combined with radiomics features to construct a radiomics-deep learning (RadiomicsDL) model. A combined model was further developed by integrating ultrasound features. Least absolute shrinkage and selection operator (LASSO) regression and various machine learning algorithms were employed for feature selection and modeling. The optimal model was determined based on the area under the receiver operating characteristic curve (AUC), and interpretability was assessed using SHapley Additive exPlanations (SHAP). Results: The RadiomicsDL model, which combines radiomics and deep learning features using the Multi-Layer Perceptron (MLP), demonstrated the best performance on the test set with an AUC of 0.807. This surpassed the performances of the ultrasound (US), radiomics, DL, and combined models, which achieved AUCs of 0.421, 0.636, 0.763, and 0.711, respectively. SHAP analysis revealed that the radiomic feature Wavelet_LHH_glcm_SumEntropy contributed most significantly to the mode. Conclusions: The RadiomicsDL model based on ultrasound images provides an efficient and non-invasive method to differentiate between primary and secondary salivary gland malignancies. Full article

Rheumatoid arthritis (RA) is a chronic autoimmune disease that can cause severe joint damage and functional impairment. Ultrasound imaging has shown promise in providing real-time assessment of synovium inflammation associated with the early stages of RA. Accurate segmentation of the synovium region and quantification of inflammation-specific imaging biomarkers are crucial for assessing and grading RA. However, automatic segmentation of the synovium in 3D ultrasound is challenging due to ambiguous boundaries, variability in synovium shape, and inhomogeneous intensity distribution. In this work, we introduce a novel network architecture, Swin Transformers with Deep Attentive Features for 3D segmentation (SwinDAF3D), which integrates Swin Transformers into a Deep Attentive Features framework. The developed architecture leverages the hierarchical structure and shifted windows of Swin Transformers to capture rich, multi-scale and attentive contextual information, improving the modeling of long-range dependencies and spatial hierarchies in 3D ultrasound images. In a six-fold cross-validation study with 3D ultrasound images of RA patients’ finger joints (n = 72), our SwinDAF3D model achieved the highest performance with a Dice Score (DSC) of 0.838 ± 0.013, an Intersection over Union (IoU) of 0.719 ± 0.019, and Surface Dice Score (SDSC) of 0.852 ± 0.020, compared to 3D UNet (DSC: 0.742 ± 0.025; IoU: 0.589 ± 0.031; SDSC: 0.661 ± 0.029), DAF3D (DSC: 0.813 ± 0.017; IoU: 0.689 ± 0.022; SDSC: 0.817 ± 0.013), Swin UNETR (DSC: 0.808 ± 0.025; IoU: 0.678 ± 0.032; SDSC: 0.822 ± 0.039), UNETR++ (DSC: 0.810 ± 0.014; IoU: 0.684 ± 0.018; SDSC: 0.829 ± 0.027) and TransUNet (DSC: 0.818 ± 0.013; IoU: 0.692 ± 0.017; SDSC: 0.815 ± 0.016) models. This ablation study demonstrates the effectiveness of combining a Swin Transformers feature pyramid with a deep attention mechanism, improving the segmentation accuracy of the synovium in 3D ultrasound. This advancement shows great promise in enabling more efficient and standardized RA screening using ultrasound imaging. Full article

Although the existence of highly prevalent pain, disability, and work time lost associated with discogenic low back pain is well known, the recognition of the culpability of universally present disc degradation and mechanical insufficiency in the first three decades of life is often overlooked. There is a corresponding “treatment gap” and no current interventions with demonstrated capabilities to address the pain and resist the usual progression of increasing structural failure of spinal tissues with increasing levels of pain and disability. This narrative review summarizes more than forty years of the literature describing the pathomechanics of progressive degradation of lumbar discs, with a focus on studies that implicate an increasing mechanical insufficiency in the etiology of early-stage chronic and recurrent discogenic low back pain. Topics highlighted in this review include the deleterious biological changes that begin soon after birth, stress intensification due to the loss of fluid phase load support, fatigue weakening and damage accumulation in non-regenerative tissue, disc tears, segmental instability, and the timeline for first incidence of chronic low back pain. The review concludes with preferred treatment characteristics and a brief summary of emerging treatment approaches. Full article

Alzheimer’s disease, an irreversible neurodegenerative disorder, manifests through the progressive deterioration of memory and cognitive functions. While magnetic resonance imaging has become an indispensable neuroimaging modality for Alzheimer’s disease diagnosis and monitoring, current diagnostic paradigms predominantly rely on single-time-point data analysis, neglecting the inherent longitudinal nature of neuroimaging applications. Therefore, in this paper, we propose a multi-task feature selection algorithm for Alzheimer’s disease classification based on longitudinal imaging and hypergraphs (THM2TFS). Our methodology establishes a multi-task learning framework where feature selection at each temporal interval is treated as an individual task within each imaging modality. To address temporal dependencies, we implement group sparse regularization with two critical components: (1) a hypergraph-induced regularization term that captures high-order structural relationships among subjects through hypergraph Laplacian modeling, and (2) a fused sparse Laplacian regularization term that encodes progressive pathological changes in brain regions across time points. The selected features are subsequently integrated via multi-kernel support vector machines for final classification. We used functional magnetic resonance imaging and structural functional magnetic resonance imaging data from Alzheimer’s Disease Neuroimaging Initiative at four different time points (baseline (T1), 6th month (T2), 12th month (T3), and 24th month (T4)) to evaluate our method. The experimental results show that the accuracy rates of 96.75%, 93.45, and 83.78 for the three groups of classification tasks (AD vs. NC, MCI vs. NC and AD vs. MCI) are obtained, respectively, which indicates that the proposed method can not only capture the relevant information between longitudinal image data well, but also the classification accuracy of Alzheimer’s disease is improved, and it helps to identify the biomarkers associated with Alzheimer’s disease. Full article

Existing studies have shown that the attentional function of epilepsy is prone to be impaired. However, the characterization of brain connectivity behind this impairment remains uncertain. This study investigates attention-related brain connectivity in 92 patients with temporal lobe epilepsy and 78 healthy controls using a 32-channel EEG monitor during an attention network test. Compared to controls, patients showed reduced temporal–occipital connectivity in the alerting and orienting networks, but increased frontal–occipital connectivity in the executive network. Additionally, this study showed that patients and healthy individuals exhibited similar network topologies in the alerting and orienting networks, but the executive networks in patients showed altered topology properties, with a larger clustering coefficient in the theta band and a longer characteristic path length in the delta and theta bands. These findings reveal distinct characteristics of attention network connectivity in patients with temporal lobe epilepsy, offering valuable insights into the underlying mechanisms of epilepsy and providing clinical guidance for long-term monitoring and intervention. Full article

Enhanced external counterpulsation (EECP) treatment has been demonstrated to be effectively vasculoprotective and anti-atherosclerotic in clinical observations and controlled trials. The diastolic blood flow augmentation induced by EECP greatly affected the local hemodynamic environment in multiple arterial segments. In this study, a porcine model of hypercholesterolaemia was developed to perform an invasive physiological measurement involving electrocardiogram, blood flow wave, and arterial pressure. Subsequently, a three-dimensional carotid bifurcation model was developed to evaluate the variations in wall shear stress (WSS) and its temporal and spatial oscillations. The results show that, compared to the pre-EECP state, EECP stimulus led to an increase of 28.7% in the common carotid artery (CCA) blood flow volume over a cardiac cycle, as well as an augmentation of 22.73% in the diastolic pressure. Meanwhile, the time-average wall shear stress (TAWSS) over the cardiac cycle increased 25.1%, while the relative residence time (RRT) declined 45.7%. These results may serve to reveal the hemodynamic mechanism of EECP treatment that contributes to its anti-atherosclerotic effects. Full article

Osteoporosis is a metabolic bone disorder characterized by the progressive loss of bone mass, which significantly increases the risk of fractures. While dual-energy X-ray absorptiometry is the standard technique for assessing bone mineral density, its use is limited in high-risk female populations. Additionally, quantitative computed tomography offers three-dimensional evaluations of bone mineral density but is costly and prone to motion artifacts. To overcome these limitations, this study proposes a hybrid model integrating U-Net and artificial neural networks, specifically focusing on abdominal X-ray images in the anteroposterior view for detailed skeletal analysis and improved accuracy in L2 vertebra mineral density measurement. The model targets female patients, who are at a higher risk for spinal disorders and osteoporosis. The U-Net model is employed for image preprocessing to reduce background noise and enhance bone tissue features, followed by analysis with the artificial neural network model to predict bone mineral density through nonlinear regression. The performance of the model, demonstrated by a high correlation coefficient of 0.77 and a low mean absolute error of 0.08 g per square centimeter, highlights its significance and effectiveness, particularly in comparison to dual-energy X-ray absorptiometry. Full article

The interspinous process device (IPD) has emerged as a viable alternative for managing lumbar degenerative pathologies. Nevertheless, limited research exists regarding mechanical failure modes including device failure and spinous process fracture. This study developed a novel IPD (IPD-NEW) and systematically evaluated its biomechanical characteristics through finite element (FE) analysis and in vitro cadaveric biomechanical testing. Six human L1–L5 lumbar specimens were subjected to mechanical testing under four experimental conditions: (1) Intact spine (control); (2) L3–L4 implanted with IPD-NEW; (3) L3–L4 implanted with Wallis device; (4) L3–L4 implanted with Coflex device. Segmental range of motion (ROM) was quantified across all test conditions. A validated L1–L5 finite element model was subsequently employed to assess biomechanical responses under both static and vertical vibration loading regimes. Comparative analysis revealed that IPD-NEW demonstrated comparable segmental ROM to the Wallis device while exhibiting lower rigidity than the Coflex implant. The novel design effectively preserved physiological spinal mobility while enhancing load distribution capacity. IPD-NEW demonstrated notable reductions in facet joint forces, device stress concentrations, and spinous process loading compared to conventional implants, particularly under vibrational loading conditions. These findings suggest that IPD-NEW may mitigate risks associated with facetogenic pain, device failure, and spinous process fracture through optimized load redistribution. Full article

The field of reconstructive surgery faces significant challenges in addressing limb loss and disfigurement, with current organ preservation methods limited by short storage times. Decellularization offers a promising solution for generating engineered alternatives for reconstructive surgery by removing cellular material while preserving the extracellular matrix (ECM) and providing scaffolds for tissue regeneration. In this study, we developed a robust protocol for decellularizing whole digits from long-term freezer storage, achieving the successful removal of cellular material with intact ECM. Digit angiography confirmed the preservation of vascular integrity, facilitating future perfusion for recellularization. Quantitative analysis revealed significantly lower DNA content in decellularized tissues, indicating effective decellularization. Furthermore, extracellular matrix analysis showed the preservation of collagen, elastin, and glycosaminoglycans (GAGs) contents. Histological examination confirmed the reduction in cellularity and maintenance of tissue architecture in decellularized digits. Mechanical strength testing of decellularized digit tendons proved consistent with that of native digits. Our findings highlight the potential of decellularized digits as versatile platforms for tissue engineering and regenerative medicine. Moving forward, further optimization of protocols and collaborative efforts are essential for translating these findings into clinical practice, offering innovative solutions for reconstructive surgery and limb transplantation. Full article

Obstructive sleep apnea (OSA) is a common disorder characterized by disrupted breathing during sleep, leading to serious health consequences such as daytime fatigue, hypertension, metabolic issues, and cardiovascular disease. Polysomnography (PSG) is the standard diagnostic method but is costly and uncomfortable for patients, which has led to interest in artificial intelligence (AI) for automated OSA detection. To develop an explainable AI model that utilizes electrocardiogram (ECG) and blood oxygen saturation (SpO2) data for real-time apnea detection, providing visual explanations to enhance interpretability and support clinical decisions. It emphasizes giving visual explanations to show how specific segments of the signal contribute to the AI’s conclusions. Furthermore, it explores the combination of individual models to improve detection accuracy. The fusion of individual models demonstrates an enhanced performance in detection accuracy. Visual explanations for AI decisions highlight the importance of certain signal features, making the model’s operations transparent to healthcare providers. The proposed AI model addresses the crucial need for transparent and interpretable AI in healthcare. By providing real-time, explainable OSA detection, this approach represents a significant advancement in the field, potentially improving patient care and aiding in the early identification and management of OSA. Full article

Gastrointestinal stromal tumors (GISTs), which usually develop with a significant malignant potential, are a serious challenge in stromal health. With Endoscopic ultrasound (EUS), GISTs can appear similar to other tumors. This study introduces a lightweight convolutional neural network model optimized for the classification of GISTs and leiomyomas using EUS images only. Models are constructed based on a dataset that comprises 13277 augmented grayscale images derived from 703 patients, ensuring a balanced representation between GIST and leiomyoma cases. The optimized model architecture includes seven convolutional units followed by fully connected layers. After being trained and evaluated with a 5-fold cross-validation, the optimized model achieves an average validation accuracy of 96.2%. The model achieved a sensitivity, specificity, positive predictive value, and negative predictive value of 97.7%, 94.7%, 94.6%, and 97.7%, respectively, and significantly outperformed endoscopists’ assessments. The study highlights the model’s robustness and consistency. Our results suggest that instead of using developed deep models with fine-tuning, lightweight models with their simpler designs may grasp the essence and drop speckle noise. A lightweight model as a hypothesis with fewer model parameters is preferable to a deeper model with 10 times the model parameters according to Occam’s razor statement. Full article