Proc Natl Acad Sci U S A. 2025 May 6;122(18):e2411446122. doi: 10.1073/pnas.2411446122. Epub 2025 Apr 28.

ABSTRACT

Transposable elements (TEs) make up the bulk of eukaryotic genomes and examples abound of TE-derived sequences repurposed for organismal function. The process by which TEs become coopted remains obscure because most cases involve ancient, transpositionally inactive elements. Reports of active TEs serving beneficial functions are scarce and often contentious due to difficulties in manipulating repetitive sequences. Here, we show that recently active TEs in zebrafish encode products critical for embryonic development. Knockdown and rescue experiments demonstrate that the endogenous retrovirus family BHIKHARI-1 (Bik-1) encodes a Gag protein essential for mesoderm development. Mechanistically, Bik-1 Gag associates with the cell membrane, and its ectopic expression in chicken embryos alters cell migration. Similarly, depletion of BHIKHARI-2 Gag, a relative of Bik-1, causes defects in neural crest development in zebrafish. We propose an "addiction" model to explain how active TEs can be integrated into conserved developmental processes.

PMID:40294259 | DOI:10.1073/pnas.2411446122

Cancer Res Commun. 2025 Apr 1;5(4):706-718. doi: 10.1158/2767-9764.CRC-25-0030.

ABSTRACT

This study presents a novel approach that integrates LLMs with real-time biomedical literature to uncover drug-gene relationships, transforming how cancer researchers identify therapeutic targets, repurpose drugs, and interpret complex molecular interactions. GeneRxGPT, our user-friendly tool, enables researchers to leverage this approach without requiring computational expertise.

PMID:40293950 | DOI:10.1158/2767-9764.CRC-25-0030

Mol Neurobiol. 2025 Apr 28. doi: 10.1007/s12035-025-04957-8. Online ahead of print.

ABSTRACT

L-3,4-Dihydroxyphenylalanine (L-DOPA) is effective at alleviating motor impairments in Parkinson's disease (PD) patients but has mixed effects on nonmotor symptoms and causes adverse effects after prolonged treatment. Here, we analyzed the spatial profile of L-DOPA-induced gene expression in the forebrain of mice with an inducible progressive loss of dopaminergic neurons (the TIF-IADATCreERT2 strain), with a focus on the similarities and differences in areas relevant to different PD symptoms. The animals received a 14-day L-DOPA treatment, and 1 h after the final drug injection, a spatial transcriptome analysis was performed on coronal forebrain sections. A total of 121 genes were identified as being regulated by L-DOPA. We found that the treatment had widespread effects extending beyond the primary areas involved in dopamine-dependent movement control. An unsupervised clustering analysis of the transcripts recapitulated the forebrain anatomy and indicated both ubiquitous and region-specific effects on transcription. The changes were most pronounced in layers 2/3 and 5 of the dorsal cortex and the dorsal striatum, where a robust increase in the abundance of activity-regulated transcripts, including Fos, Egr1, and Junb, was observed. Conversely, transcripts with a decreased abundance, e.g., Plekhm2 or Pgs1, were identified primarily in the piriform cortex, the adjacent endopiriform nucleus, and the claustrum. Taken together, our spatial analysis of L-DOPA-induced alterations in gene expression reveals the anatomical complexity of treatment effects, identifying novel genes affected by the drug, as well as molecular activation in brain areas relevant to the nonmotor symptoms of PD.

PMID:40293707 | DOI:10.1007/s12035-025-04957-8

Front Pharmacol. 2025 Apr 1;16:1519383. doi: 10.3389/fphar.2025.1519383. eCollection 2025.

ABSTRACT

BACKGROUND: Aspirin is a cornerstone medication for acute ischemic stroke (AIS), but its efficacy varies significantly among individuals. This study aimed to develop a pharmacogenetic polygenic response score (PgxRS) to predict the incidence of adverse outcomes in aspirin-treated AIS patients.

METHODS: We conducted a retrospective study involving 828 AIS patients who received aspirin therapy. Fifteen candidate single nucleotide variants (SNPs) in genes related to aspirin's mechanism of action, transport, metabolism, and platelet function were genotyped. The association between SNPs and the risk of unfavorable prognosis (defined as modified Rankin Scale score >1 at 90 days) was assessed using logistic regression analysis. Multivariable models incorporating SNPs and clinical factors were developed to predict adverse outcomes.

RESULTS: The rs1045642GG genotype in the ABCB1 gene was significantly associated with a lower risk of unfavorable prognosis, while the rs1371097T allele in the P2Y1 gene was linked to a higher risk. A prediction model incorporating these two SNPs along with clinical variables demonstrated moderate diagnostic accuracy for predicting unfavorable prognosis (AUC = 0.78, 95% CI: 0.74-0.81).

CONCLUSION: Our findings suggest that rs1045642 and rs1371097 genotypes contribute to variability in aspirin response among AIS patients. The developed PgxRS, incorporating these SNPs and clinical factors, can potentially aid in risk stratification and guide personalized antiplatelet therapy decisions. However, further validation in larger, diverse cohorts is warranted.

PMID:40290439 | PMC:PMC12023276 | DOI:10.3389/fphar.2025.1519383

Front Pharmacol. 2025 Apr 11;16:1548991. doi: 10.3389/fphar.2025.1548991. eCollection 2025.

ABSTRACT

The sequencing of the human genome in 2003 marked a transformative shift from a one-size-fits-all approach to personalized medicine, emphasizing patient-specific molecular and physiological characteristics. Advances in sequencing technologies, from Sanger methods to Next-Generation Sequencing (NGS), have generated vast genomic datasets, enabling the development of tailored therapeutic strategies. Pharmacogenomics (PGx) has played a pivotal role in elucidating how the genetic make-up influences inter-individual variability in drug efficacy and toxicity discovering predictive and prognostic biomarkers. However, challenges persist in interpreting polymorphic variants and translating findings into clinical practice. Multi-omics data integration and bioinformatics tools are essential for addressing these complexities, uncovering novel molecular insights, and advancing precision medicine. In this review, starting from our experience in PGx studies performed by DMET microarray platform, we propose a guideline combining machine learning, statistical, and network-based approaches to simplify and better understand complex DMET PGx data analysis which can be adapted for broader PGx applications, fostering accessibility to high-performance bioinformatics, also for non-specialists. Moreover, we describe an example of how bioinformatic tools can be used for a comprehensive integrative analysis which could allow the translation of genetic insights into personalized therapeutic strategies.

PMID:40290426 | PMC:PMC12022492 | DOI:10.3389/fphar.2025.1548991

JAMA. 2025 Apr 28. doi: 10.1001/jama.2025.2680. Online ahead of print.

ABSTRACT

IMPORTANCE: Non-cystic fibrosis (CF) bronchiectasis is a chronic lung condition caused by permanent bronchial dilatation and inflammation and is characterized by daily cough, sputum, and recurrent exacerbations. Approximately 500 000 people in the US have non-CF bronchiectasis.

OBSERVATIONS: Non-CF bronchiectasis may be associated with prior pneumonia, infection with nontuberculous mycobacteria or tuberculosis, genetic conditions (eg, α1-antitrypsin deficiency, primary ciliary dyskinesia), autoimmune diseases (eg, rheumatoid arthritis, inflammatory bowel disease), allergic bronchopulmonary aspergillosis, and immunodeficiency syndromes (eg, common variable immunodeficiency). Up to 38% of cases are idiopathic. According to US data, conditions associated with non-CF bronchiectasis include gastroesophageal reflux disease (47%), asthma (29%), and chronic obstructive pulmonary disease (20%). The prevalence of non-CF bronchiectasis increases substantially with age (7 per 100 000 in individuals 18-34 years vs 812 per 100 000 in those ≥75 years) and is more common in women than men (180 vs 95 per 100 000). Diagnosis is confirmed with noncontrast chest computed tomography showing dilated airways and often airway thickening and mucus plugging. Initial diagnostic evaluation involves blood testing (complete blood cell count with differential); immunoglobulin quantification testing (IgG, IgA, IgE, and IgM); sputum cultures for bacteria, mycobacteria, and fungi; and prebronchodilator and postbronchodilator spirometry. Treatment includes airway clearance techniques; nebulization of saline to loosen tenacious secretions; and regular exercise, participation in pulmonary rehabilitation, or both. Inhaled bronchodilators (β-agonists and antimuscarinic agents) and inhaled corticosteroids are indicated for patients with bronchiectasis who have asthma or chronic obstructive pulmonary disease. Exacerbations of bronchiectasis, which typically present with increased cough and sputum and worsened fatigue, are associated with progressive decline in lung function and decreased quality of life. Exacerbations should be treated with oral or intravenous antibiotics. Individuals with 3 or more exacerbations of bronchiectasis annually may benefit from long-term inhaled antibiotics (eg, colistin, gentamicin) or daily oral macrolides (eg, azithromycin). Lung transplant may be considered for patients with severely impaired pulmonary function, frequent exacerbations, or both. Among patients with non-CF bronchiectasis, mortality is higher for those with frequent and severe exacerbations, infection with Pseudomonas aeruginosa, and comorbidities, such as chronic obstructive pulmonary disease.

CONCLUSIONS AND RELEVANCE: Non-CF bronchiectasis is a chronic lung condition that typically causes chronic cough and daily sputum production. Exacerbations are associated with progressive decline in lung function and decreased quality of life. Management involves treatment of conditions associated with bronchiectasis, airway clearance techniques, oral or intravenous antibiotics for acute exacerbations, and consideration of long-term inhaled antibiotics or oral macrolides for patients with 3 or more exacerbations annually.

PMID:40293759 | DOI:10.1001/jama.2025.2680

Lancet Reg Health Eur. 2025 Apr 19;53:101303. doi: 10.1016/j.lanepe.2025.101303. eCollection 2025 Jun.

ABSTRACT

BACKGROUND: According to estimates, globally more than 200,000 pregnant women develop tuberculosis (TB) annually. Despite this, data on perinatal TB remain scarce. This study aimed to describe perinatal TB, comprising congenital (cTB) and postnatal (pTB) TB, in a European setting.

METHODS: Retrospective cohort study via the Paediatric Tuberculosis Network European Trials Group (ptbnet) capturing and comparing cases of cTB and pTB diagnosed at 104 participating European healthcare institutions between 1995 and 2019.

FINDINGS: Forty-six cases reported by 20 centres were included in the final analysis (cTB, n = 27; pTB, n = 19). Median age at symptom onset was one week in cTB (IQR: 0-1 weeks), and 12 weeks in pTB patients (IQR: 5-18 weeks). Prematurity was more common in cTB than pTB patients [57.9% (11/19); 95% CI: 36.3-76.9% vs. 21.1% (4/19); 95% CI: 8.5-43.3%; p = 0.049], and the average birth weight was significantly lower [1680 g; IQR: 932-2805 g vs. 2890 g; IQR: 2461-3400 g; p = 0.0043]. Microbiological confirmation was achieved in most patients [85.2% (23/27); 95% CI: 67.5-94.1% vs. 78.9% (15/19); 95% CI: 56.7-91.5%; p = 0.70]. The sensitivity of interferon-gamma release assays was poor in both groups [25.0% (3/12) 95% CI: 8.9-53.2% vs. 35.7% (5/14) 95% CI: 16.3-61.2%; p = 0.68]; in contrast, the sensitivity of the tuberculin skin tests (at 5 mm cut-off) was significantly higher in pTB patients [16.7% (2/12) 95% CI: 4.7-44.8% vs. 66.7% (10/15); 95% CI: 41.7-84.8%; p = 0.0185]. Approximately half of the patients required intensive care support [51.9% (14/27) 95% CI: 34.0-69.3% vs. 47.4% (9/19); 95% CI: 27.3-68.3%; p > 0.99]. Four (4/46; 8.7%) patients died, and four (4/46; 8.7%) had severe long-term sequelae.

INTERPRETATION: There was substantial mortality and morbidity in this patient cohort, despite the high-resource setting. cTB was associated with premature birth and low birth weight. In contrast to microbiological tests, immunological tests perform poorly in perinatal TB, and should therefore not be used as rule-out tests.

FUNDING: No study-specific funding.

PMID:40291400 | PMC:PMC12032942 | DOI:10.1016/j.lanepe.2025.101303

APL Bioeng. 2025 Apr 25;9(2):026110. doi: 10.1063/5.0220367. eCollection 2025 Jun.

ABSTRACT

Dysregulated neutrophil recruitment drives many pulmonary diseases, but most preclinical screening methods are unsuited to evaluate pulmonary neutrophilia, limiting progress toward therapeutics. Namely, high-throughput therapeutic assays typically exclude critical neutrophilic pathophysiology, including blood-to-lung recruitment, dysfunctional activation, and resulting impacts on the air-blood barrier. To meet the conflicting demands of physiological complexity and high throughput, we developed an assay of 96-well leukocyte recruitment in an air-blood barrier array (L-ABBA-96) that enables in vivo-like neutrophil recruitment compatible with downstream phenotyping by automated flow cytometry. We modeled acute respiratory distress syndrome (ARDS) with neutrophil recruitment to 20 ng/mL epithelial-side interleukin 8 and found a dose-dependent reduction in recruitment with physiologic doses of baricitinib, a JAK1/2 inhibitor recently Food and Drug Administration-approved for severe Coronavirus Disease 2019 ARDS. Additionally, neutrophil recruitment to patient-derived cystic fibrosis sputum supernatant induced disease-mimetic recruitment and activation of healthy donor neutrophils and upregulated endothelial e-selectin. Compared to 24-well assays, the L-ABBA-96 reduces required patient sample volumes by 25 times per well and quadruples throughput per plate. Compared to microfluidic assays, the L-ABBA-96 recruits two orders of magnitude more neutrophils per well, enabling downstream flow cytometry and other standard biochemical assays. This novel pairing of high-throughput in vitro modeling of organ-level lung function with parallel high-throughput leukocyte phenotyping substantially advances opportunities for pathophysiological studies, personalized medicine, and drug testing applications.

PMID:40290728 | PMC:PMC12033047 | DOI:10.1063/5.0220367

Biofilm. 2025 Apr 11;9:100279. doi: 10.1016/j.bioflm.2025.100279. eCollection 2025 Jun.

ABSTRACT

Co-infections by Staphylococcus aureus and Pseudomonas aeruginosa are frequent in the airways of patients with cystic fibrosis. These co-infections show higher antibiotic tolerance in vitro compared to mono-infections. In vitro models have been developed to study the interspecies interactions between P. aeruginosa and S. aureus. However, these model systems fail to incorporate clinical isolates with diverse phenotypes, do not reflect the nutritional environment of the CF airway mucus, and/or do not model the biofilm mode of growth observed in the CF airways. Here, we established a dual-species biofilm model grown in artificial sputum medium, where S. aureus was inoculated before P. aeruginosa to facilitate the maintenance of both species over time. It was successfully applied to ten pairs of clinical isolates exhibiting different phenotypes. Co-isolates from individual patients led to robust, stable co-cultures, supporting the theory of cross-adaptation in vivo. Investigation into the cross-adaptation of the VBB496 co-isolate pair revealed that both the P. aeruginosa and S. aureus isolates had reduced antagonism, in part due to reduced production of P. aeruginosa secondary metabolites as well as higher tolerance to those metabolites by S. aureus. Together, these results indicate that the two-species biofilm model system provides a useful tool for exploring interspecies interactions of P. aeruginosa and S. aureus in the context of CF airway infections.

PMID:40290724 | PMC:PMC12033965 | DOI:10.1016/j.bioflm.2025.100279

Pak J Med Sci. 2025 Apr;41(4):1052-1057. doi: 10.12669/pjms.41.4.10877.

ABSTRACT

BACKGROUND & OBJECTIVES: Bronchiectasis is the permanent enlargement of the bronchi following damage to the respiratory tract (bronchi) in the lungs. Bronchiectasis not associated with cystic fibrosis is gaining an increasing place among chronic respiratory diseases worldwide. The purpose of this study was to identify the levels of MMP-9, known to cause bronchial damage in chronic pulmonary illness, and SIRT-1, an anti-aging and anti-infective regulatory protein, in patients with bronchiectasis and to evaluate the importance of these biomarkers in diagnosis.

METHODS: This cross-sectional study was conducted in the Chest Diseases Clinic of Sivas Cumhuriyet University Medical Faculty Hospital between November 2020 and September 2022. We recruited 30 patients with bronchiectasis whose diagnosis was verified by high-resolution chest CT scan and 30 healthy controls. SIRT-1 and MMP-9 levels in the serum of the study group were determined by the ELISA method.

RESULTS: SIRT-1 and MMP-9 concentrations were found to be statistically significant. In comparison to the control group, it was observed that the bronchiectasis group had a lower serum SIRT-1 levels (p<0.001). The bronchiectasis group had higher serum MMP-9 values than the control group (p<0.001). Age-related differences in SIRT-1 and MMP-9 concentrations were not observed. No correlation was found between MMP-9 and SIRT-1. The results of Receiver Operating Characteristic (ROC) analysis indicated that MMP-9 has relatively high sensitivities.

CONCLUSIONS: We concluded that, higher inflammation elevates MMP-9 levels while decreasing SIRT-1 levels. MMP-9 and SIRT-1 may be potential biomarkers in the diagnosis of bronchiectasis.

PMID:40290232 | PMC:PMC12022576 | DOI:10.12669/pjms.41.4.10877

Abdom Radiol (NY). 2025 Apr 28. doi: 10.1007/s00261-025-04951-7. Online ahead of print.

ABSTRACT

Accurate, reproducible body composition analysis from abdominal computed tomography (CT) images is critical for both clinical research and patient care. We present a fully automated, artificial intelligence (AI)-based pipeline that streamlines the entire process-from data normalization and anatomical landmarking to automated tissue segmentation and quantitative biomarker extraction. Our methodology ensures standardized inputs and robust segmentation models to compute volumetric, density, and cross-sectional area metrics for a range of organs and tissues. Additionally, we capture selected DICOM header fields to enable downstream analysis of scan parameters and facilitate correction for acquisition-related variability. By emphasizing portability and compatibility across different scanner types, image protocols, and computational environments, we ensure broad applicability of our framework. This toolkit is the basis for the Opportunistic Screening Consortium in Abdominal Radiology (OSCAR) and has been shown to be robust and versatile, critical for large multi-center studies.

PMID:40293521 | DOI:10.1007/s00261-025-04951-7

Abdom Radiol (NY). 2025 Apr 28. doi: 10.1007/s00261-025-04963-3. Online ahead of print.

ABSTRACT

Renal cell carcinoma (RCC) as a significant health concern, with incidence rates rising annually due to increased use of cross-sectional imaging, leading to a higher detection of incidental renal lesions. Differentiation between benign and malignant renal lesions is essential for effective treatment planning and prognosis. Renal tumors present numerous histological subtypes with different prognoses, making precise subtype differentiation crucial. Artificial intelligence (AI), especially machine learning (ML) and deep learning (DL), shows promise in radiological analysis, providing advanced tools for renal lesion detection, segmentation, and classification to improve diagnosis and personalize treatment. Recent advancements in AI have demonstrated effectiveness in identifying renal lesions and predicting surveillance outcomes, yet limitations remain, including data variability, interpretability, and publication bias. In this review we explored the current role of AI in assessing kidney lesions, highlighting its potential in preoperative diagnosis and addressing existing challenges for clinical implementation.

PMID:40293518 | DOI:10.1007/s00261-025-04963-3

Int Orthop. 2025 Apr 28. doi: 10.1007/s00264-025-06531-2. Online ahead of print.

ABSTRACT

AIM: We aimed to compare the diagnostic performance of physicians in the detection of arthroscopically confirmed meniscus and anterior cruciate ligament (ACL) tears on knee magnetic resonance imaging (MRI), with and without assistance from a deep learning (DL) model.

METHODS: We obtained preoperative MR images from 88 knees of patients who underwent arthroscopic meniscal repair, with or without ACL reconstruction. Ninety-eight MR images of knees without signs of meniscus or ACL tears were obtained from a publicly available database after matching on age and ACL status (normal or torn), resulting in a global dataset of 186 MRI examinations. The Keros® (Incepto, Paris) DL algorithm, previously trained for the detection and characterization of meniscus and ACL tears, was used for MRI assessment. Magnetic resonance images were individually, and blindly annotated by three physicians and the DL algorithm. After three weeks, the three human raters repeated image assessment with model assistance, performed in a different order.

RESULTS: The Keros® algorithm achieved an area under the curve (AUC) of 0.96 (95% CI 0.93, 0.99), 0.91 (95% CI 0.85, 0.96), and 0.99 (95% CI 0.98, 0.997) in the detection of medial meniscus, lateral meniscus and ACL tears, respectively. With model assistance, physicians achieved higher sensitivity (91% vs. 83%, p = 0.04) and similar specificity (91% vs. 87%, p = 0.09) in the detection of medial meniscus tears. Regarding lateral meniscus tears, sensitivity and specificity were similar with/without model assistance. Regarding ACL tears, physicians achieved higher specificity when assisted by the algorithm (70% vs. 51%, p = 0.01) but similar sensitivity with/without model assistance (93% vs. 96%, p = 0.13).

CONCLUSIONS: The current model consistently helped physicians in the detection of medial meniscus and ACL tears, notably when they were combined.

LEVEL OF EVIDENCE: Diagnostic study, Level III.

PMID:40293511 | DOI:10.1007/s00264-025-06531-2

Sleep. 2025 Apr 28:zsaf113. doi: 10.1093/sleep/zsaf113. Online ahead of print.

ABSTRACT

Wearable devices with sleep tracking functionalities can prompt behavioral changes to promote sleep, but proactively preventing poor sleep when it is likely to occur remains a challenge due to a lack of prediction models that can forecast sleep parameters prior to sleep onset. We developed models that forecast low sleep efficiency 4 and 8 hours prior to sleep onset using gradient boosting (CatBoost) and deep learning (Convolutional Neural Network Long Short-Term Memory, CNN-LSTM) algorithms trained exclusively on accelerometer data from 80,811 adults in the UK Biobank. Associations of various sleep and activity parameters with sleep efficiency were further examined. During repeated cross-validation, both CatBoost and CNN-LSTM exhibited excellent predictive performance (median AUCs > 0.90, median AUPRCs > 0.79). U-shaped relationships were observed between total activity within 4 and 8 hours of sleep onset and low sleep efficiency. Functional data analyses revealed higher activity 6 to 8 hours prior to sleep onset had negligible associations with sleep efficiency. Higher activity 4 to 6 hours prior had moderate beneficial associations, while higher activity within 4 hours had detrimental associations. Additional analyses showed that increased variability in sleep duration, efficiency, onset timing, and offset timing over the preceding four days was associated with lower sleep efficiency. Our study represents a first step towards wearable-based machine learning systems that proactively prevent poor sleep by demonstrating that sleep efficiency can be accurately forecasted prior to bedtime and by identifying pre-bed activity targets for subsequent intervention.

PMID:40293116 | DOI:10.1093/sleep/zsaf113

Sensors (Basel). 2025 Mar 19;25(6):1924. doi: 10.3390/s25061924.

ABSTRACT

With the development of UAV technology, the composition of UAVs has become increasingly complex, interconnected, and tightly coupled. Fault features are characterized by weakness, nonlinearity, coupling, and uncertainty. A promising approach is the use of deep learning methods, which can effectively extract useful diagnostic information from weak, coupled, nonlinear data from inputs with background noise. However, due to the diversity of flight environments and missions, the distribution of the obtained sample data varies. The types of fault data and corresponding labels under different conditions are unknown, and it is time-consuming and expensive to label sample data. These challenges reduce the performance of traditional deep learning models in anomaly detection. To overcome these challenges, a novel weighted-transfer domain-adaptation network (WTDAN) method is introduced to realize the online anomaly detection and fault diagnosis of UAV electromagnetic-sensitive flight data. The method is based on unsupervised transfer learning, which can transfer the knowledge learnt from existing datasets to solve problems in the target domain. The method contains three novel multiscale modules: a feature extractor, used to extract multidimensional features from the input; a domain discriminator, used to improve the imbalance of the data distribution between the source domain and the target domain; and a label classifier, used to classify data categories for the target domain. Multilayer domain adaptation is used to reduce the distance between the source domain datasets and the target domain datasets distributions. The WTDAN assigns different weights to the source domain samples in order to weight the different contributions of source samples to solve the problem during the training process. The dataset adopts not only open datasets from the website but also test datasets from experiments to evaluate the transferability of the proposed WTDAN model. The experimental results show that, under the condition of fewer anomalous target data samples, the proposed method had a classification accuracy of up to 90%, which is higher than that of the other compared methods, and performed with superior transferability on the cross-domain datasets. The capability of fault diagnosis can provide a novel method for online anomaly detection and the prognostics and health management (PHM) of UAVs, which, in turn, would improve the reliability, repairability, and safety of UAV systems.

PMID:40293102 | DOI:10.3390/s25061924

Sensors (Basel). 2025 Mar 20;25(6):1942. doi: 10.3390/s25061942.

ABSTRACT

Fringe projection profilometry (FPP) is a widely employed technique owing to its rapid speed and high accuracy. However, when FPP is utilized to measure shiny surfaces, the fringes tend to be saturated or too dark, which significantly compromises the accuracy of the 3D measurement. To overcome this challenge, this paper proposes an efficient method for the 3D measurement of shiny surfaces based on FPP. Firstly, polarizers are employed to alleviate fringe saturation by leveraging the polarization property of specular reflection. Although polarizers reduce fringe intensity, a deep learning method is utilized to enhance the quality of fringes, especially in low-contrast regions, thereby improving measurement accuracy. Furthermore, to accelerate measurement efficiency, a dual-frequency complementary decoding method is introduced, requiring only two auxiliary fringes for accurate fringe order determination, thereby achieving high-efficiency and high-dynamic-range 3D measurement. The effectiveness and feasibility of the proposed method are validated through a series of experimental results.

PMID:40293081 | DOI:10.3390/s25061942

Sensors (Basel). 2025 Mar 20;25(6):1926. doi: 10.3390/s25061926.

ABSTRACT

This paper presents a new methodology for localizing impact events on plate-like structures using a proposed two-dimensional convolutional neural network (CNN) and received impact signals. A network of four piezoelectric wafer active sensors (PWAS) was installed on the tested plate to acquire impact signals. These signals consisted of reflection waves that provided valuable information about impact events. In this methodology, each of the received signals was divided into several equal segments. Then, a wavelet transform (WT)-based time-frequency analysis was used for processing each segment signal. The generated WT diagrams of these segments' signals were cropped and resized using MATLAB code to be used as input image datasets to train, validate, and test the proposed CNN model. Two scenarios were adopted from PAWS transducers. First, two sensors were positioned in two corners of the plate, while, in the second scenario, four sensors were used to monitor and collect the signals. Eight datasets were collected and reshaped from these two scenarios. These datasets presented the signals of two, three, four, and five impacts. The model's performance was evaluated using four metrics: confusion matrix, accuracy, precision, and F1 score. The proposed model demonstrated exceptional performance by accurately localizing all of the impact points of the first scenario and 99% of the second scenario. The main limitation of the proposed model is how to differentiate the data samples that have similar features. From our point of view, the similarity challenge arose from two factors: the segmentation interval and the impact distance. First, applying the segmenting procedure to the PWAS signals led to an increase in the number of data samples. The procedure segmented each PWAS signal to 30 samples with equal intervals, regardless of the features of the signal. Segmenting and transforming different PWAS signals into image-based data points led to data samples that had similar features. Second, some of the impacts had a close distance to the PWAS sensors, which resulted in similar segmented signals. Therefore, the second scenario was more challenging for the proposed model.

PMID:40293079 | DOI:10.3390/s25061926

Sensors (Basel). 2025 Mar 19;25(6):1902. doi: 10.3390/s25061902.

ABSTRACT

Advanced communication systems, particularly in the context of autonomous driving and integrated sensing and communication (ISAC), require high precision and refresh rates for environmental perception, alongside reliable data transmission. This paper presents a novel approach to enhance the ISAC performance in existing 4G and 5G systems by utilizing a two-dimensional offset in the Delay-Doppler (DD) domain, effectively leveraging the sounding reference signal (SRS) resources. This method aims to improve spectrum efficiency and sensing accuracy in vehicular networks. However, a key challenge arises from interference between multiple users after the wireless propagation of signals. To address this, we propose a deep learning-based interference mitigation solution using an UNet architecture, which operates on the Range-Doppler maps. The UNet model, with its encoder-decoder structure, efficiently filters out unwanted signals, therefore enhancing the system performance. Simulation results show that the proposed method significantly improves the accuracy of environmental sensing and resource utilization while mitigating interference, even in dense network scenarios. Our findings suggest that this DD-domain-based approach offers a promising solution to optimizing ISAC capabilities in current and future communication systems.

PMID:40293069 | DOI:10.3390/s25061902

Sensors (Basel). 2025 Mar 19;25(6):1909. doi: 10.3390/s25061909.

ABSTRACT

Echocardiography is a widely used cardiac imaging modality in clinical practice. Physicians utilize echocardiography images to measure left ventricular volumes at end-diastole (ED) and end-systole (ES) frames, which are pivotal for calculating the ejection fraction and thus quantitatively assessing cardiac function. However, most existing approaches focus on features from ES frames and ED frames, neglecting the inter-frame correlations in unlabeled frames. Our model is based on an encoder-decoder architecture and consists of two modules: the Temporal Feature Fusion Module (TFFA) and the Vision Retentive Network (Vision RetNet) encoder. The TFFA leverages self-attention to learn inter-frame correlations across multiple consecutive frames and aggregates the features of the temporal-channel dimension through channel aggregation to highlight ambiguity regions. The Vision RetNet encoder introduces explicit spatial priors by constructing a spatial decay matrix using the Manhattan distance. We conducted experiments on the EchoNet-Dynamic dataset and the CAMUS dataset, where our proposed model demonstrates competitive performance. The experimental results indicate that spatial prior information and inter-frame correlations in echocardiography images can enhance the accuracy of semantic segmentation, and inter-frame correlations become even more effective when spatial priors are provided.

PMID:40293054 | DOI:10.3390/s25061909

Sensors (Basel). 2025 Mar 19;25(6):1916. doi: 10.3390/s25061916.

ABSTRACT

BACKGROUND: IgA nephropathy (IgAN) is a leading cause of renal failure, characterized by significant clinical and pathological heterogeneity. Accurate subtype classification remains challenging due to overlapping clinical manifestations and the multidimensional nature of data. Traditional methods often fail to fully capture IgAN's complexity, limiting their clinical applicability. This study introduces MAL-Net, a deep learning framework for multi-label classification of IgAN subtypes, leveraging multidimensional clinical data and incorporating sensor-based inputs such as laboratory indices and symptom tracking.

METHODS: MAL-Net integrates Long Short-Term Memory (LSTM) networks with Multi-Head Attention (MHA) mechanisms to effectively capture sequential and contextual dependencies in clinical data. A memory network module extracts features from clinical sensors and records, while the MHA module emphasizes critical features and mitigates class imbalance. The model was trained and validated on clinical data from 500 IgAN patients, incorporating demographic, laboratory, and symptomatic variables. Performance was evaluated against six baseline models, including traditional machine learning and deep learning approaches.

RESULTS: MAL-Net outperformed all baseline models, achieving 91% accuracy and an AUC of 0.97. The integration of MHA significantly enhanced classification performance, particularly for underrepresented subtypes. The F1-score for the Ni-du subtype improved by 0.8, demonstrating the model's ability to address class imbalance and improve precision.

CONCLUSIONS: MAL-Net provides a robust solution for multi-label IgAN subtype classification, tackling challenges such as data heterogeneity, class imbalance, and feature interdependencies. By integrating clinical sensor data, MAL-Net enhances IgAN subtype prediction, supporting early diagnosis, personalized treatment, and improved prognosis evaluation.

PMID:40293045 | DOI:10.3390/s25061916