Browse Articles
Discover research articles across all indexed journals
An importance sampling vortex particle method for turbulence visualization simulation in maritime simulators
HSSAM-Net: hyper-scale shifted aggregation network for precise colorectal polyp segmentation in endoscopic images
Abstract Colorectal cancer remains a leading cause of cancer-related mortality worldwide, emphasizing the importance of early detection through accurate polyp identification. However, colonoscopy relies heavily on precise polyp segmentation in endoscopic images, yet this task remains challenging due to morphological variability, low contrast, and imaging artifacts. In this study, we propose HSSAM-Net, a lightweight deep learning framework that integrates a Hyper-Scale Shifted Aggregation Module to capture multi-scale contextual information while preserving fine-grained details, Progressive Reuse Attention mechanism that strengthens feature propagation across the encoder-decoder pathway, and Max-Diagonal Pooling/Unpooling (MaxDP/MaxDUP) a novel dual-branch sampling scheme to improve texture representation, feature alignment to enhance feature aggregation, context learning, and boundary refinement. The proposed model is evaluated on five benchmark datasets (Kvasir, CVC-ClinicDB, ETIS, CVC-300, EndoCV2020). Experimental results show that HSSAM-Net consistently outperforms state-of-the-art methods across benchmark datasets, HSSAM-Net consistently achieves state-of-the-art accuracy (Dice: 0.949–0.952, mIoU: 0.924–0.930), while maintaining real-time efficiency at 24.1 FPS with only 0.9 M parameters. Furthermore, an analysis of trainable parameters and inference speed confirms its suitability for real-time clinical applications. Our findings demonstrate that HSSAM-Net achieves a favorable trade-off between accuracy and efficiency, advancing the development of practical and reliable computer-aided colonoscopy systems.
Geometry-aware lightweight convolutional network for efficient molecular property prediction
Evaluating the role of a visual pitch meter in carnatic music education and pitch internalization through constructivist and RALD frameworks
Modulation of aluminum-induced genotoxicity and oxidative stress in Allium cepa L. by Ramalina pollinaria (Westr.) Ach. extract
Artificial intelligence improves detection and classification of pulmonary venous hypertension related to left ventricular diastolic dysfunction by chest radiography
A sterna migration algorithm-based efficient bionic engineering optimization algorithm
Resistome profiling and bacterial community structure of semi-urban gutter ecosystems of India
No effect of preliminarily simulated cathodal HD-tDCS on the frontopolar cortex in the exploration-exploitation task
Abstract This study investigated the causal role of the human frontopolar cortex (FPC) in managing counterfactual strategies during decision-making under uncertainty. Using a combination of cathodal high-definition transcranial direct current stimulation (HD-tDCS) and computational modeling, we examined how cathodal stimulation, preliminarily simulated with SimNIBS, affects the retrieval of alternative strategies in the task that constantly provokes exploration-exploitation dilemmas. A comparison of resting-state recordings with functional near-infrared spectroscopy (fNIRS) before and after stimulation did not reveal any physiological effect of HD-tDCS. Furthermore, there was no significant difference in participants’ exploratory behavior between the sham and cathodal groups. These results indicate that the employed HD-tDCS protocol may not sufficiently influence FPC function, despite preliminary tDCS simulations with SimNIBS, calling for further refinement of the HD-tDCS protocol used in future research to elucidate the causal role of the FPC in decision-making under uncertainty.
Electrochemical and dielectric properties of cobalt doped SnS on cotton based electrodes for potential use in supercapacitors
Porous cementless cups combined with trabecular metal augments in revision hip arthroplasty: mid-term outcomes
Abstract Reconstruction of acetabular bone defects represents one of the most technically demanding aspects of revision total hip arthroplasty. Although numerous implant options and surgical techniques have been proposed, porous acetabular components combined with trabecular metal augments have gained widespread acceptance as a contemporary reconstructive strategy. The present study aims to assess implant survivorship and to report mid-term clinical and radiographic outcomes associated with this technique. We identified 69 revision total hip arthroplasties (69 patients) performed at the Department of Joint Arthroplasty of the Priorov National Medical Research Center of Traumatology and Orthopedics between January 2016 and June 2022, using porous acetabular cups in combination with trabecular metal augments. Among these patients, 46 (66.6%) were female and 23 (33.4%) were male. The mean patient age was 59.9 years (± 12.4), with a mean follow-up duration of 4.9 years (± 1.78), ranging from a minimum of 2.6 years to a maximum of 9 years. Functional outcomes were assessed using the Harris Hip Score (HHS), Visual Analogue Scale (VAS), and Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), while implant survival was evaluated using Kaplan–Meier analysis. The overall HHS significantly improved from a preoperative mean of 32.9 (± 9.8) to a postoperative mean of 86.7 (± 4.9). VAS scores decreased from 8.1 (± 0.5) to 3.4 (± 0.5), WOMAC scores decreased from 61.3 (± 4.7) to 24.7 (± 2.4), indicating favorable clinical and functional outcomes ( p < 0.00001 for each scale). Kaplan–Meier survival analysis demonstrated a 9 years (109.7 months) cumulative implant survivorship rate of 98.55%. The results indicate that porous acetabular cups combined with trabecular metal augments represent an effective option in revision hip arthroplasty, demonstrating excellent mid-term outcomes in terms of both implant survivorship and functional improvement.
Optimization of groundwater utilization strategy based on an improved snake optimizer integrating whale algorithm and bubble-net mechanism
Development of biochar adsorbents based on walnut shell with magnetic modification for efficient crude oil removal from water
Contact exposure to ivermectin induces acute mortality and inhibits parasite development in malaria vectors
Sleep and sleep disorders: much more than how long you sleep, what truly matters is How you sleep
Tannic acid modified horizontal platelet-rich fibrin membrane with improved mechanical and biological properties for tissue regeneration
Machine learning to predict the role of CHWs in shifting birth preferences away from homebirth in India
Abstract This study utilized well-known supervised machine learning algorithms to NFHS‑5 data of West Bengal, India, to predict the place of birth (home vs facility) by integrating CHW (community health worker) contact factors and women participant’s perceptions about intimate partner violence (IPV). Although the study applied modelling techniques from conventional ML literature, the overarching contribution was identifying avenues to enhance public health policy response (e.g., efficient targeting of home visits and counselling by ANM/ASHA). The study concludes that, identifying likely homebirth cases among women with IPV-related poor perceptions applying improved prediction can enhance prioritising of CHW-contact and alter birth preference. The study improves minority-class learning using SMOTE on weighted NFHS data keeping in mind the complex survey design and SMOTE limitations. With respect to the ML model performance, Random Forest produced the highest test AUC (0.991) and accuracy (96.7%) among the 5 evaluated classifiers—LR (base), RF, MNB, k-NN, SVM and 0.950 with stable accuracy of 96% on hold-out data. The study does not bring methodological novelty in the underlying algorithms but generated actionable insights for equitable CHW allocation for efficient targeting using standard cross-sectional survey data.
Hierarchical multi-scale vision transformer model for accurate detection and classification of brain tumors in MRI-based medical imaging
Androgen receptor gene polymorphism and biological age markers in men
Abstract Inter-individual differences in aging rates may stem from the trade-offs between reproductive effort and somatic maintenance, with higher reproductive effort potentially reducing healthspan and lifespan. In men, these trade-offs are thought to be regulated by androgens, where high androgen levels incur biological costs. However, the relationship between androgen levels, health, and aging is complex, and the role of androgen receptor (AR) sensitivity in aging remains unclear. Thus, this study aimed to investigate whether genetic polymorphisms in the AR gene, related to receptor affinity and androgen sensitivity, predict biological age in men. The analyses included 131 healthy men (mean age: 35.4, age range 30–45). Biological age was assessed using physiological markers, including klotho, inflammatory markers, oxidative stress, total antioxidant capacity, and DHEA/S levels. AR sensitivity was estimated based on CAG repeat length in exon 1 of the AR gene (AR CAGn), with shorter repeats indicating higher sensitivity. The independent effect of testosterone (T) level, as well as its potential interaction with AR CAGn, was also verified. Chronological age, body adiposity, lifestyle factors, and cortisol levels were controlled for. Results showed no relationship between AR CAGn and biological age markers, directly or through interaction with T levels. Findings suggest that lifetime testosterone fluctuations, influenced by environmental and health factors, may obscure the link between AR CAGn and reproductive/somatic investment, ultimately affecting the aging rate.