Search Results (1,151)

Accurate staging of bladder cancer is critical for guiding clinical management, particularly the distinction between non–muscle-invasive (T1) and muscle-invasive (T2–T4) disease. Although MRI offers superior soft-tissue contrast, image interpretation remains operator-dependent and subject to inter-observer variability. This study proposes an automated deep learning framework for MRI-based bladder cancer staging to support standardized radiological interpretation. A sequential AI-based pipeline was developed, integrating hybrid tumor segmentation using YOLOv11 for lesion detection and DeepLabV3 for boundary refinement, followed by three deep learning classifiers (VGG19, ResNet50, and Vision Transformer) for MRI-based stage prediction. A total of 416 T2-weighted MRI images with radiology-derived stage labels (T1–T4) were included, with data augmentation applied during training. Model performance was evaluated using accuracy, precision, recall, F1-score, and multi-class AUC. Performance uncertainty was characterized using patient-level bootstrap confidence intervals under a fixed training and evaluation pipeline. All evaluated models demonstrated high and broadly comparable discriminative performance for MRI-based bladder cancer staging within the present dataset, with high point estimates of accuracy and AUC, particularly for differentiating non–muscle-invasive from muscle-invasive disease. Calibration analysis characterized the probabilistic behavior of predicted stage probabilities under the current experimental setting. The proposed framework demonstrates the feasibility of automated MRI-based bladder cancer staging derived from radiological reference labels and supports the potential of deep learning for standardizing and reproducing MRI-based staging procedures. Rather than serving as an independent clinical decision-support system, the framework is intended as a methodological and workflow-oriented tool for automated staging consistency. Further validation using multi-center datasets, patient-level data splitting prior to augmentation, pathology-confirmed reference standards, and explainable AI techniques is required to establish generalizability and clinical relevance. Full article

In composite membranes, non-woven substrates are often included to offer higher mechanical strength. The use of non-wovens is currently limited in electrochemical applications, apart from lab-made electrospun non-woven membranes. In this manuscript, three commercial non-wovens are compared to test their potential use in acid-based electrochemical applications, for instance redox flow batteries, and are also compared to a woven fabric substrate. The three non-wovens are found to have variable suitability in terms of the stability of solvents used in further membrane processing. However, all are deemed limiting due to their relatively high area resistance (0.37–1.47 ohm.cm²). In comparison, free-standing and selective commercial ion exchange membranes have area resistances around 0.08–0.27 ohm.cm². More open substrate backings such as a woven structure are recommended instead to allow for lower resistance of the resulting composites. Full article

Clinoptilolite is a zeolite with a microporous structure that enables ion exchange, molecular sieving, and adsorption, conferring detoxifying, antioxidant, and anti-inflammatory properties. These properties have applications in food, medicine, catalysis, and environmental remediation. This study evaluated the safety of the lab-made Clinoptilolite as a potential food ingredient through a 90-day repeated-dose toxicity study in male and female Sprague Dawley rats. The test substance was administered via oral gavage at doses of 0, 5, 10, and 15 mg/kg bw/day, followed by a 28-day recovery period. In addition, genotoxicity was assessed using the Ames test, in vitro chromosomal aberration assay, and an in vivo micronucleus test. All studies were conducted in accordance with OECD and FDA guidelines. Results showed no adverse systemic, genotoxic, or irreversible effects at any dose, with minor clinical variations being incidental and reversible. Genotoxicity tests confirmed no mutagenic or clastogenic potential. Overall, the lab-made Clinoptilolite evaluated in this investigation was well tolerated, non-toxic, and showed no evidence of treatment-related toxicity at the doses tested. These findings provide supportive evidence for its consideration toward a Generally Recognized as Safe (GRAS) determination. Full article

The non-destructive and chemical-free determination of anthocyanin content in single maize kernels is of great importance for plant-breeding programs. Previous studies have mainly relied on Near-Infrared Reflectance (NIR) spectroscopy and color-based approaches, often using conventional or randomly selected modeling techniques. In this study, an Automated Machine Learning (AutoML) framework was employed to predict anthocyanin content using spectral and digital image data obtained from individual maize kernels measured in two orientations (embryo-up and embryo-down). Forty colored maize genotypes representing diverse phenotypic characteristics were analyzed. Digital images were acquired in RGB, HSV, and LAB color spaces, together with NIR spectral data, from a total of 200 kernels. Reference anthocyanin content was determined using a colorimetric method. Ten datasets were constructed by combining different color space and spectral features and were grouped according to kernel orientation. AutoML was used to evaluate nine machine learning algorithms, while Partial Least Squares Regression (PLSR) served as a classical benchmark method, resulting in the development of 1918 predictive models. Kernel orientation had a notable effect on model performance and outlier detection. The best predictions were obtained from the RGB dataset for embryo-up kernels and from the combined RGB+HSV+LAB+NIR dataset for embryo-down kernels. Overall, AutoML outperformed conventional modeling by automatically identifying optimal algorithms for specific data structures, demonstrating its potential as an efficient screening tool for anthocyanin content at the single-kernel level. Full article

The non-thermal plasma-driven cascade process for CO₂-to-methanol conversion shows significant potential in the field of green methanol synthesis. This process innovatively couples a plasma activation module with a catalytic synthesis module via a multi-stage pressurization device, establishing an efficient two-step pathway that converts CO₂ into methanol via a CO intermediate. Such an arrangement establishes an energy conversion system characterized by both low carbon emissions and high efficiency. This work involved an initial technical evaluation employing a custom-built, lab-scale apparatus. The optimum parameters determined through this assessment were a plasma input voltage of 40 V combined with a subsequent reaction temperature of 240 °C. Operation at these specified parameters yielded a CO₂ conversion of 48%, with the methanol selectivity and production rate reaching 40% and 502 g_MeOH${·\mathrm{kg}}_{\mathrm{cat}}^{-1}$·h⁻¹, respectively. Furthermore, industrial-scale process design and scale-up were performed, accompanied by process simulation using Aspen Plus and a subsequent techno-economic evaluation. The results indicate that, compared to the conventional direct CO₂ hydrogenation process, the proposed cascade route can reduce the capital investment by approximately 17%. Full article

Concrete arch dams represent a predominant dam type in water conservancy and hydropower projects in China. The control of concrete placement progress during construction directly impacts project quality and construction efficiency. Traditional manual monitoring methods, characterized by delayed response and strong subjectivity, struggle to meet the demands of modern intelligent construction management. This study introduces machine vision technology to monitor the concrete placement process and establishes an intelligent analysis system for construction scenes based on deep learning. By comparing the performance of U-Net and DeepLabV3+ semantic segmentation models in complex construction environments, the U-Net model, achieving an IoU of 89%, was selected to identify vibrated and non-vibrated concrete areas, thereby optimizing the concrete image segmentation algorithm. A comprehensive real-time analysis method for placement progress was developed, enabling automatic ternary classification and progress calculation for key construction stages, including concrete unloading, spreading, and vibration. In a continuous placement case study of Monolith No. 3 at a project site, the model’s segmentation results showed only an 8.2% error compared with manual annotations, confirming the method’s real-time capability and reliability. The research outcomes provide robust data support for intelligent construction management and hold significant practical value for enhancing the quality and efficiency of hydraulic engineering construction. Full article

The external color of smoked sausages is a critical indicator of quality and uniformity in processing. Commercial colorimeters are unsuitable for high-throughput sorting due to the challenges posed by the sausage’s curved cylindrical surface and the need for an inline application. This study introduces a novel non-contact sensing module (LEDs at 45°, fiber optic collection at 0°) to acquire spectral data (400–700 nm) and derive CIE LAB. First, a handheld prototype validated the accuracy of the sensing module against a benchtop spectrophotometer. It successfully categorized five color grades (‘Over light’, ‘Light’, ‘Standard’, ‘Dark’, and ‘Over dark’) with a clear distribution on the a*-L* diagram. This established acceptable color boundary conditions (44.2 < L* ≤ 61.3, 14.1 < a* < 23.9). Second, three sensing modules were integrated around a conveyor belt at 120° intervals, forming the core of an automated inline sorting system. Blind field tests (n = 150) achieved high sorting accuracies of 95.3–97.3% with an efficient inspection time of less than 2 s per sausage. This work realizes the standardization, digitalization, and automation of food color inspection, demonstrating strong potential for smart manufacturing in the processed meat industry. Full article

Background/Objectives: Non-muscle invasive bladder cancer (NMIBC) management is increasingly complex due to conflicting guideline-based risk classifications, ongoing Bacillus Calmette–Guérin (BCG) shortages, and emerging alternative therapies. Computational Histology Artificial Intelligence (CHAI) tests are clinically available, providing insights from tumor specimens including predicting BCG responsiveness and individualized recurrence and progression risks, which may support precision medicine. This technology features biomarkers purpose-built for clinically unmet needs and has practical advantages including a fast turnaround time and no need for consumption of tissue or other specimens. We assessed the impact of such tests on physicians’ decision-making in routine, real-world NMIBC management. Methods: Physicians at six centers ordered CHAI tests (Vesta Bladder) at their discretion during routine NMIBC care. Tumor specimens were processed by a CLIA/CAP-accredited laboratory (Valar Labs, Houston, TX, USA) where H&E-stained slides were analyzed with the CHAI assay to extract histomorphic features of the tumor and microenvironment, which were algorithmically assessed to generate biomarker test results. For each case from 24 June 2024 to 18 July 2025, ordering physicians were surveyed to assess pre- and post-test management plans and post-test result usefulness. Results: Among 105 high-grade NMIBC cases with complete survey results available, primary management changed in 67% (70/105). Changes included modality shifts (n = 7; three to radical cystectomy with high prognostic risk scores; four avoiding cystectomy with low scores) and intravesical agent change (n = 63). Surveillance was intensified in 7%, predominantly among those with ≥90th percentile risk scores. The therapeutic agent changed in 80% (40/50) of predictive biomarker-present (indicative of poor response to BCG) tumors vs. 48% (23/48) of biomarker-absent tumors. Conclusions: In two thirds of cases, CHAI biomarker results influenced clinical decision-making during routine care. BCG predictive biomarker results frequently guided intravesical agent selection. These results have implications for optimizing clinical outcomes, especially in the setting of ongoing BCG shortages. Prognostic risk stratification results guided treatment escalation vs. de-escalation, including surveillance intensification and surgical vs. bladder-sparing decisions. CHAI biomarkers are currently utilized in routine clinical care and informing precision NMIBC management. Full article

Obesity is among the top contributing factors for non-communicable chronic disease development and has attained menacing global proportions, affecting approximately one of eight adults. Phytochemicals that support energy metabolism and prevent obesity development have been the subject of intense research endeavors over the past several decades. Cycloastragenol is a natural triterpenoid compound and aglycon of astragaloside IV, known for activating telomerase and mitigating cellular aging. Here, we aim to characterize the effect of cycloastragenol on lipid metabolism in a glucose-induced obesity model in Caenorhabditis elegans. We assessed the changes in the body length, width, and area in C. elegans maintained under elevated glucose through automated WormLab system. Lipid accumulation in the presence of either cycloastragenol (100 μM) or orlistat (12 μM), used as a positive anti-obesity control drug, was quantified through Nile Red fluorescent staining. Furthermore, we evaluated the changes in key energy metabolism molecular players in GFP-reporter transgenic strains. Our results revealed that cycloastragenol treatment decreased mean body area and reduced lipid accumulation in the C. elegans glucose-induced model. The mechanistic data indicated that cycloastragenol suppresses the nuclear hormone receptor family member NHR-49 and the delta(9)-fatty-acid desaturase 7 (FAT-7) enzyme, and activates the 5′-AMP-activated protein kinase catalytic subunit alpha-2 (AAK-2) and the protein skinhead 1 (SKN-1) signaling. Collectively, our findings highlight that cycloastragenol reprograms lipid metabolism by down-regulating the insulin-like receptor (daf-2)/phosphatidylinositol 3-kinase (age-1)/NHR-49 signaling while simultaneously enhancing the activity of the AAK-2/NAD-dependent protein deacetylase (SIR-2.1) pathway. The anti-obesogenic potential of cycloastragenol rationalizes further validation in the context of metabolic diseases and obesity management. Full article

Nowadays, the population is subject to a lot of stress, being one of society’s most encountered problems affecting people all over the world. Being under a lot of stress for prolonged periods of time impacts the physical and mental health of individuals with effects on society as an economic burden. Cortisol is one of the main indicators of stress. Long-term exposure to this stress hormone can lead to severe medical conditions such as heart disease, lung issues, obesity, anxiety, or depression. In this context, the current review aims to provide a comprehensive overview of the most recent advances made in the development of versatile and efficient cortisol devices and biosensors capable of monitoring the cortisol levels in biofluids. Lately, both non-plasmonic (polymer-based sensors, optical sensors, electrochemical sensors) and plasmonic sensors (mono- and multiple-metallic nanoparticles-based sensors) have shown great results in cortisol detection. The work focuses on the advantages, remaining restrictions, and limitations in the field of cortisol biosensors from solution-based immunosensors to wearable and Lab-on-Skin monitoring devices, providing a better understanding of the fulfilled requirements and persisting challenges in the accurate detection and monitoring of the cortisol stress hormone. Full article

This study reports the isolation, identification, and functional characterization of lactic acid bacteria (LAB) obtained from the endogenous fermentation of Theobroma bicolor (pataxte), an understudied Mesoamerican species with unexplored biotechnological potential. Five lactic acid bacteria strains were isolated and selected for comprehensive in vitro evaluation of their probiotic attributes. The assays included antimicrobial activity (disk diffusion and minimum inhibitory concentration), tolerance to simulated gastrointestinal conditions, and comparison of survival between non-encapsulated and bigel-encapsulated cells during digestion. All five isolates demonstrated notable antimicrobial activity against Escherichia coli ATCC 25922, Salmonella Enteritidis ATCC 13076, and Staphylococcus aureus ATCC 25923. Strain S1.B exhibited exceptional resistance to acidic pH (2.0) and bile salts, reaching 3.61 ± 0.00 log (CFU/mL) after gastrointestinal simulation. The strain was identified as Lactiplantibacillus pentosus via 16S rRNA gene sequencing, marking the first documented isolation of this species from pataxte fermentation. Bigel encapsulation markedly enhanced its survival, increasing viability to 5.08 ± 0.10 log (CFU/mL). These findings identify Lactiplantibacillus pentosus 124-2 as a potential probiotic candidate originating from pataxte fermentation and highlight bigel systems as powerful vehicles for bacterial protection. Collectively, this work expands the microbial biodiversity known in Theobroma fermentations and underscores their promise for future functional food applications. Full article

Artificial intelligence (AI) and machine learning (ML) are transforming medical diagnostics, but human nail, an easily accessible and rich biological substrate, is still not fully exploited in the digital health field. Nail pathologies are easily diagnosed, non-invasive disease biomarkers, including systemic diseases such as anemia, diabetes, psoriasis, melanoma, and fungal diseases. This review presents the first big synthesis of image analysis for nail lesions incorporating AI/ML for diagnostic purposes. Where dermatological reviews to date have been more wide-ranging in scope, our review will focus specifically on diagnosis and screening related to nails. The various technological modalities involved (smartphone imaging, dermoscopy, Optical Coherence Tomography) will be presented, together with the different processing techniques for images (color corrections, segmentation, cropping of regions of interest), and models that range from classical methods to deep learning, with annotated descriptions of each. There will also be additional descriptions of AI applications related to some diseases, together with analytical discussions regarding real-world impediments to clinical application, including scarcity of data, variations in skin type, annotation errors, and other laws of clinical adoption. Some emerging solutions will also be emphasized: explainable AI (XAI), federated learning, and platform diagnostics allied with smartphones. Bridging the gap between clinical dermatology, artificial intelligence and mobile health, this review consolidates our existing knowledge and charts a path through yet others to scalable, equitable, and trustworthy nail based medically diagnostic techniques. Our findings advocate for interdisciplinary innovation to bring AI-enabled nail analysis from lab prototypes to routine healthcare and global screening initiatives. Full article

Scene depth information is a key component of any robotic mobile application. Range sensors, such as LiDAR, sonar, or radar, capture depth data of a scene. However, the data captured by these sensors frequently presents missing regions or information with a low confidence level. These missing regions in the depth data could be large areas without information, making it difficult to make decisions, for instance, for an autonomous vehicle. Recovering depth data has become a primary activity for computer vision applications. This work proposes and evaluates an interpolation model to infer dense depth maps from a Lab color space reference picture and an incomplete-depth image embedded in a completion pipeline. The complete proposal pipeline comprises convolutional layers and a convex combination of the infinity Laplacian and non-local means model. The proposed model infers dense depth maps by considering depth data and utilizing clues from a color picture of the scene, along with a metric for computing differences between two pixels. The work contributes (i) the convex combination of the two models to interpolate the data, and (ii) the proposal of a class of function suitable for balancing between different models. The obtained results show that the model outperforms similar models in the KITTI dataset and outperforms our previous implementation in the NYU_v2 dataset, dropping the MSE by 34.86%, 3.35%, and 34.42% for 4×, 8×, 16× upsampling tasks, respectively. Full article

Cycling-based rehabilitation is a non-invasive intervention for individuals with lower limb asymmetries. However, current cycling devices lack comprehensive biomechanical feedback and cannot assess asymmetry. Our lab has developed a novel cycle ergometer equipped with three-dimensional force pedals, a seat post and handlebar force sensors, which allow for a comprehensive analysis of asymmetry across a fatiguing task. This study assessed the reproducibility of the cycling kinetics and asymmetry index derived from this device during incremental and constant load cycling tasks to volitional failure. Eighteen participants completed incremental and constant-load tests, each across two identical sessions. Pedal forces and power were analyzed for each leg individually, and handlebar forces and seat post mediolateral sway were recorded during cycling. Normalized symmetry index (NSI), a metric quantifying the degree of asymmetry between limbs, was calculated for each variable. The reproducibility of the device was assessed using repeated measures analysis of variance and intraclass correlation coefficients (ICC). No significant session or interaction effects were found for pedal, handlebar, and seat post measures (all p > 0.05). Time effects were observed for pedal force and power in the incremental test (all p < 0.001). NSI values were reproducible with high ICC values (≥0.70) for force and power. The results suggest that this ergometer offers reproducible cycling kinetics and asymmetry measures across a fatiguing task. The findings support the application of this ergometer in research and rehabilitation settings. Full article

Electrospinning has advanced from a lab technique to an industrial method, enabling modern filters that are high-performing, sustainable, recyclable, and non-toxic. This study produced recycled PA6 nanofibers using green solvents and incorporated non-toxic CuO nanoparticles via industrial free-surface electrospinning. Polymer solutions with concentrations of 12.5, 15.0 and 17.5 (w/v)% were electrospun directly onto recyclable polypropylene spunbond/meltblown nonwoven substrates to produce nanofibers with average fiber sizes of 80–250 nm. Electrospinning parameter optimization revealed that the 12.5 wt.% PA6 solution and the 2–3 mm·s⁻¹ winding speed had the optimal performance, attaining 98.06% filtering efficiency and a 142 Pa pressure drop. The addition of 5 wt.% CuO nanoparticles increased the membrane density and reduced the pressure drop to 162 Pa, thereby improving the filtration efficiency to 98.23%. Bacterial and viral filtration studies have demonstrated pathogen retention above 99%. Moreover, antibacterial and antiviral testing has demonstrated that membranes trap and inactivate microorganisms, resulting in a 2.0 log (≈approximately 99%) reduction in viral titer. This study shows that recycled PA6 can be converted into high-performance membranes using green, industrial electrospinning, introducing innovations such as non-toxic CuO functionalization and ultra-fine fibers on recyclable substrates, yielding sustainable filters with strong antimicrobial and filtration performance, which are suitable for personal protective equipment and medical filtration. Full article