Sci Rep. 2025 Feb 24;15(1):6610. doi: 10.1038/s41598-025-89971-5.

ABSTRACT

Oral carcinoma (OC) is a toxic illness among the most general malignant cancers globally, and it has developed a gradually significant public health concern in emerging and low-to-middle-income states. Late diagnosis, high incidence, and inadequate treatment strategies remain substantial challenges. Analysis at an initial phase is significant for good treatment, prediction, and existence. Despite the current growth in the perception of molecular devices, late analysis and methods near precision medicine for OC patients remain a challenge. A machine learning (ML) model was employed to improve early detection in medicine, aiming to reduce cancer-specific mortality and disease progression. Recent advancements in this approach have significantly enhanced the extraction and diagnosis of critical information from medical images. This paper presents a Deep Structured Learning with Vision Intelligence for Oral Carcinoma Lesion Segmentation and Classification (DSLVI-OCLSC) model for medical imaging. Using medical imaging, the DSLVI-OCLSC model aims to enhance OC's classification and recognition outcomes. To accomplish this, the DSLVI-OCLSC model utilizes wiener filtering (WF) as a pre-processing technique to eliminate the noise. In addition, the ShuffleNetV2 method is used for the group of higher-level deep features from an input image. The convolutional bidirectional long short-term memory network with a multi-head attention mechanism (MA-CNN-BiLSTM) approach is utilized for oral carcinoma recognition and identification. Moreover, the Unet3 + is employed to segment abnormal regions from the classified images. Finally, the sine cosine algorithm (SCA) approach is utilized to hyperparameter-tune the DL model. A wide range of simulations is implemented to ensure the enhanced performance of the DSLVI-OCLSC method under the OC images dataset. The experimental analysis of the DSLVI-OCLSC method portrayed a superior accuracy value of 98.47% over recent approaches.

PMID:39994267 | DOI:10.1038/s41598-025-89971-5

Light Sci Appl. 2025 Feb 25;14(1):93. doi: 10.1038/s41377-024-01729-2.

ABSTRACT

Pursuing higher data rate with limited spectral resources is a longstanding topic that has triggered the fast growth of modern wireless communication techniques. However, the massive deployment of active nodes to compensate for propagation loss necessitates high hardware expenditure, energy consumption, and maintenance cost, as well as complicated network interference issues. Intelligent metasurfaces, composed of a number of subwavelength passive or active meta-atoms, have recently found to be a new paradigm to actively reshape wireless communication environment in a green way, distinct from conventional works that passively adapt to the surrounding. In this review, we offer a unified perspective on how intelligent metasurfaces can facilitate wireless communication in three manners: signal relay, signal transmitter, and signal processor. We start by the basic modeling of wireless channel and the evolution of metasurfaces from passive, active to intelligent metasurfaces. Integrated with various deep learning algorithms, intelligent metasurfaces adapt to cater for the ever-changing environments without human intervention. Then, we overview specific experimental advancements using intelligent metasurfaces. We conclude by identifying key issues in the practical implementations of intelligent metasurfaces, and surveying new directions, such as gain metasurfaces and knowledge migration.

PMID:39994200 | DOI:10.1038/s41377-024-01729-2

Clin Transl Oncol. 2025 Feb 24. doi: 10.1007/s12094-025-03870-9. Online ahead of print.

ABSTRACT

PURPOSE: This study evaluates a three-dimensional (3D) deep learning (DL) model based on fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) for predicting the preoperative status of spread through air spaces (STAS) in patients with clinical stage I lung adenocarcinoma (LUAD).

METHODS: A retrospective analysis of 162 patients with stage I LUAD was conducted, splitting data into training and test sets (4:1). Six 3D DL models were developed, and the top-performing PET and CT models (ResNet50) were fused for optimal prediction. The model's clinical utility was assessed through a two-stage reader study.

RESULTS: The fused PET/CT model achieved an area under the curve (AUC) of 0.956 (95% CI 0.9230-0.9881) in the training set and 0.889 (95% CI 0.7624-1.0000) in the test set. Compared to three physicians, the model demonstrated superior sensitivity and specificity. After the artificial intelligence (AI) assistance's participation, the diagnostic accuracy of the physicians improved during their subsequent reading session.

CONCLUSION: Our DL model demonstrates potential as a resource to aid physicians in predicting STAS status and preoperative treatment planning for stage I LUAD, though prospective validation is required.

PMID:39994163 | DOI:10.1007/s12094-025-03870-9

Sci Rep. 2025 Feb 24;15(1):6678. doi: 10.1038/s41598-025-91187-6.

ABSTRACT

In this retrospective observational study, we aimed to investigate the potential of natural language processing (NLP) for drug repositioning by analyzing the preventive effects of cardioprotective drugs against anthracycline-induced cardiotoxicity (AIC) using electronic medical records. We evaluated the effects of angiotensin II receptor blockers/angiotensin-converting enzyme inhibitors (ARB/ACEIs), beta-blockers (BBs), statins, and calcium channel blockers (CCBs) on AIC using signals extracted from clinical texts via NLP. The study included 2935 patients prescribed anthracyclines at a single hospital, with concomitant prescriptions of ARB/ACEIs, BBs, statins, and CCBs. Upon propensity score matching, groups with and without these medications were compared, and expressions suggestive of cardiotoxicity, extracted via NLP, were considered as the outcome. The hazard ratios for ARB/ACEIs, BBs, statins, and CCBs were 0.58 [95% CI: 0.38-0.88], 0.71 [95% CI: 0.35-1.44], 0.60 [95% CI 0.38-0.95], and 0.63 [95% CI: 0.45-0.88], respectively. ARB/ACEIs, statins, and CCBs significantly suppressed AIC, whereas BBs did not demonstrate statistical significance, possibly due to limited statistical power. NLP-extracted signals from clinical texts reflected the known effects of these medications, demonstrating the feasibility of NLP-based drug repositioning. Further investigation is needed to determine if similar results can be replicated using electronic medical records from other institutions.

PMID:39994365 | DOI:10.1038/s41598-025-91187-6

Ageing Res Rev. 2025 Feb 22:102698. doi: 10.1016/j.arr.2025.102698. Online ahead of print.

ABSTRACT

Alzheimer's disease (AD) is an insidious, irreversible, complex neurodegenerative disorder characterized by progressive cognitive decline and memory loss; affecting millions worldwide. Despite decades of research, no effective disease-modifying treatment exists. However, drug repurposing is a progressive step in identifying new therapeutic uses of existing drugs. It has emerged as a promising strategy in the quest to combat AD. Various classes of repurposed drugs, such as antidiabetic, antihypertensive, antimicrobial, and anti-inflammatory, have shown potential neuroprotective effects in preclinical and clinical studies. These drugs act by combating free radicals generation, neuroinflammation, amyloid-beta aggregation, and tau hyper-phosphorylation. Furthermore, repurposing offers several advantages, including reduced time and cost compared to de novo drug development. It holds immense promise as a complementary approach to traditional drug discovery. Future research efforts should focus on elucidating the underlying mechanisms of repurposed drugs in AD, optimizing drug combinations, and conducting large-scale clinical trials to validate their efficacy and safety profiles. This review overviews recent advancements and findings in preclinical and clinical fields of different repurposed drugs for AD treatment.

PMID:39993451 | DOI:10.1016/j.arr.2025.102698

Pharmacogenomics J. 2025 Feb 25;25(2):4. doi: 10.1038/s41397-025-00363-4.

ABSTRACT

Liver transplantation is the only curative option for patients with advanced stages of liver disease, with tacrolimus used as the immunosuppressive drug of choice. Genetic variability can interfere with drug response, potentially leading to overexposure or underexposure. This study aims to investigate the association of CYP3A4 (rs2740574, rs2242480, rs35599367), CYP3A5 (rs776746, rs10264272), POR (rs1057868) and ABCB1 (rs1128503, rs2229109, rs9282564) gene polymorphisms with infection, acute rejection, and renal failure. The logistic regression model found an influence of CYP3A5 (rs776746) and POR28 (rs1057868) on the development of acute rejection after liver transplantation (p = 0.028). It also found an association between carriers of the variant allele of the POR*28 gene and infection.

PMID:39994182 | DOI:10.1038/s41397-025-00363-4

Cancer Genomics Proteomics. 2025 Mar-Apr;22(2):285-305. doi: 10.21873/cgp.20502.

ABSTRACT

BACKGROUND/AIM: Oncogenic processes are delineated by metabolic dysregulation. Drug likeness is pharmacokinetically tested through the CYP450 enzymatic system, whose genetic aberrations under epigenetic stress could shift male organisms into prostate cancer pathways. Our objective was to predict the susceptibility to prostate neoplasia, focused on benign prostatic hyperplasia (BPH) and prostate cancer (PCa), based on the pharmacoepigenetic and the metabolic profile of Caucasians.

MATERIALS AND METHODS: Two independent cohorts of 47,389 individuals in total were assessed to find risk associations of CYP450 genes with prostatic neoplasia. The metabolic profile of the first cohort was statistically evaluated and frequencies of absorption-distribution-metabolism-excretion-toxicity (ADMET) properties were calculated. Prediction of miRNA pharmacoepigenetic targeting was performed.

RESULTS: We found that prostate cancer and benign prostatic hyperplasia patients of the first cohort shared common cardiometabolic trends. Drug classes C08CA, C09AA, C09CA, C10AA, C10AX of the cardiovascular, and G04CA, G04CB of the genitourinary systems, were associated with increased prostate cancer risk, while C03CA and N06AB of the cardiovascular and nervous systems were associated with low-risk for PCa. CYP3A4*1B was the most related pharmacogenetic polymorphism associated with prostate cancer susceptibility. miRNA-200c-3p and miRNA-27b-3p seem to be associated with CYP3A4 targeting and prostate cancer predisposition. Metabolomic analysis indicated that 11β-OHT, 2β-OHT, 15β-OHT, 2α-OHT and 6β-OHT had a high risk, and 16α-OHT, and 16β-OHT had an intermediate disease-risk.

CONCLUSION: These findings constitute a novel integrated signature for prostate cancer susceptibility. Further studies are required to assess their predictive value more fully.

PMID:39993800 | DOI:10.21873/cgp.20502

Sci Rep. 2025 Feb 24;15(1):6551. doi: 10.1038/s41598-025-91073-1.

ABSTRACT

A novel lytic bacteriophage, PSA-KC1, was isolated from wastewater. In this study, the whole genome of the bacteriophage PSA-KC1 was analyzed, and its lytic properties were assessed. PSA-KC1 has a linear double-stranded DNA genome with a total length of 43,237 base pairs and a GC content of 53.6%. In total, 65 genes were predicted, 46 of which were assigned functions as structural proteins involved in genome replication, packaging or phage lysis. PSA-KC1 belongs to the genus Septimatrevirus under the Caudoviricetes class. The aim of this study was to investigate the efficacy of the lytic bacteriophage PSA-KC1 and compare it with that of the Pyophage phage cocktail on 25 multi drug resistant (MDR) Pseudomonas aeruginosa strains isolated from sputum samples of cystic fibrosis patients. Seventeen of these strains were susceptible (68%) to the PSA-KC1 lytic phage we isolated, whereas eight clinical strains were resistant. However, 22 (88%) of the P. aeruginosa strains were susceptible to the Pyophage cocktail, and three (12%) were resistant to the Phage cocktail. At the end of our study, a new lytic phage active against multidrug-resistant P. aeruginosa strains from CF patients was isolated, and its genome was characterized. Since the PSA-KC1 phage does not contain virulence factors, toxins or integrase genes, it can be expected to be a therapeutic candidate with the potential to be used safely in phage therapy.

PMID:39994360 | DOI:10.1038/s41598-025-91073-1

BMC Bioinformatics. 2025 Feb 25;26(1):62. doi: 10.1186/s12859-025-06061-z.

ABSTRACT

BACKGROUND: Advancements in high-throughput sequencing and deep learning have boosted single-cell RNA studies. However, current methods for annotating single-cell data face challenges due to high data sparsity and tedious manual annotation on large-scale data.

RESULTS: Thus, we proposed a novel annotation model integrating FFT (Fast Fourier Transform) and an enhanced Transformer, named scFTAT. Initially, it reduces data sparsity using LDA (Linear Discriminant Analysis). Subsequently, automatic cell annotation is achieved through a proposed module integrating FFT and an enhanced Transformer. Moreover, the model is fine-tuned to improve training performance by effectively incorporating such techniques as kernel approximation, position encoding enhancement, and attention enhancement modules. Compared to existing popular annotation tools, scFTAT maintains high accuracy and robustness on six typical datasets. Specifically, the model achieves an accuracy of 0.93 on the human kidney data, with an F1 score of 0.84, precision of 0.96, recall rate of 0.80, and Matthews correlation coefficient of 0.89. The highest accuracy of the compared methods is 0.92, with an F1 score of 0.71, precision of 0.75, recall rate of 0.73, and Matthews correlation coefficient of 0.85. The compiled codes and supplements are available at: https://github.com/gladex/scFTAT .

CONCLUSION: In summary, the proposed scFTAT effectively integrates FFT and enhanced Transformer for automatic feature learning, addressing the challenges of high sparsity and tedious manual annotation in single-cell profiling data. Experiments on six typical scRNA-seq datasets from human and mouse tissues evaluate the model using five metrics as accuracy, F1 score, precision, recall, and Matthews correlation coefficient. Performance comparisons with existing methods further demonstrate the efficiency and robustness of our proposed method.

PMID:39994539 | DOI:10.1186/s12859-025-06061-z

Commun Biol. 2025 Feb 24;8(1):298. doi: 10.1038/s42003-025-07711-x.

ABSTRACT

The complex spatiotemporal dynamics of neurons encompass a wealth of information relevant to perception and decision-making, making the decoding of neural activity a central focus in neuroscience research. Traditional machine learning or deep learning-based neural information modeling approaches have achieved significant results in decoding. Nevertheless, such methodologies require the vectorization of data, a process that disrupts the intrinsic relationships inherent in high-dimensional spaces, consequently impeding their capability to effectively process information in high-order tensor domains. In this paper, we introduce a novel decoding approach, namely the Least Squares Sport Tensor Machine (LS-STM), which is based on tensor space and represents a tensorized improvement over traditional vector learning frameworks. In extensive evaluations using human and mouse data, our results demonstrate that LS-STM exhibits superior performance in neural signal decoding tasks compared to traditional vectorization-based decoding methods. Furthermore, LS-STM demonstrates better performance in decoding neural signals with limited samples and the tensor weights of the LS-STM decoder enable the retrospective identification of key neurons during the neural encoding process. This study introduces a novel tensor computing approach and perspective for decoding high-dimensional neural information in the field.

PMID:39994447 | DOI:10.1038/s42003-025-07711-x

Sci Rep. 2025 Feb 24;15(1):6553. doi: 10.1038/s41598-025-91352-x.

ABSTRACT

Cracks that occur in concrete surfaces are numerous and diverse, and different cracks will affect road safety in different degrees. Accurately identifying pavement cracks is crucial for assessing road conditions and formulating maintenance strategies. This study improves the original U-shaped convolutional network (U-Net) model through the introduction of two innovations, thereby modifying its structure, reducing the number of parameters, enhancing its ability to distinguish between background and cracks, and improving its speed and accuracy in crack detection tasks. Additionally, datasets with different exposure levels and noise conditions are used to train the network, broadening its predictive ability. A custom dataset of 960 road crack images was added to the public dataset to train and evaluate the model. The test results demonstrate that the proposed U-Net-FML model achieves high accuracy and detection speed in complex environments, with MIoU, F1 score, precision, and recall values of 76.4%, 74.2%, 84.2%, and 66.4%, respectively, significantly surpassing those of the other models. Among the seven comparison models, U-Net-FML has the strongest overall performance, highlighting its engineering value for precise detection and efficient analysis of cracks.

PMID:39994438 | DOI:10.1038/s41598-025-91352-x

NPJ Digit Med. 2025 Feb 24;8(1):122. doi: 10.1038/s41746-025-01436-1.

ABSTRACT

We aim to assess the real-world accuracy (primary outcome), feasibility and acceptability (secondary outcomes) of an automated retinal photography and artificial intelligence (AI)-based cardiovascular disease (CVD) risk assessment system (rpCVD) in Australian primary care settings. Participants aged 45-70 years who had recently undergone all or part of a CVD risk assessment were recruited from two general practice clinics in Victoria, Australia. After consenting, participants underwent retinal imaging using an automated fundus camera, and an rpCVD risk score was generated by a deep learning algorithm. This score was compared against the World Health Organisation (WHO) CVD risk score, which incorporates age, sex, and other clinical risk factors. The predictive accuracy of the rpCVD and WHO CVD risk scores for 10-year incident CVD events was evaluated using data from the UK Biobank, with the accuracy of each system assessed through the area under the receiver operating characteristic curve (AUC). Participant satisfaction was assessed through a survey, and the imaging success rate was determined by the percentage of individuals with images of sufficient quality to produce an rpCVD risk score. Of the 361 participants, 339 received an rpCVD risk score, resulting in a 93.9% imaging success rate. The rpCVD risk scores showed a moderate correlation with the WHO CVD risk scores (Pearson correlation coefficient [PCC] = 0.526, 95% CI: 0.444-0.599). Despite this, the rpCVD system, which relies solely on retinal images, demonstrated a similar level of accuracy in predicting 10-year incident CVD (AUC = 0.672, 95% CI: 0.658-0.686) compared to the WHO CVD risk score (AUC = 0.693, 95% CI: 0.680-0.707). High satisfaction rates were reported, with 92.5% of participants and 87.5% of general practitioners (GPs) expressing satisfaction with the system. The automated rpCVD system, using only retinal photographs, demonstrated predictive accuracy comparable to the WHO CVD risk score, which incorporates multiple clinical factors including age, the most heavily weighted factor for CVD prediction. This underscores the potential of the rpCVD approach as a faster, easier, and non-invasive alternative for CVD risk assessment in primary care settings, avoiding the need for more complex clinical procedures.

PMID:39994433 | DOI:10.1038/s41746-025-01436-1

Nat Mater. 2025 Feb 24. doi: 10.1038/s41563-024-02115-4. Online ahead of print.

ABSTRACT

Medical interventions often require timed series of doses, thus necessitating accurate medical record-keeping. In many global settings, these records are unreliable or unavailable at the point of care, leading to less effective treatments or disease prevention. Here we present an invisible-to-the-naked-eye on-patient medical record-keeping technology that accurately stores medical information in the patient skin as part of microneedles that are used for intradermal therapeutics. We optimize the microneedle design for both a reliable delivery of messenger RNA (mRNA) therapeutics and the near-infrared fluorescent microparticles that encode the on-patient medical record-keeping. Deep learning-based image processing enables encoding and decoding of the information with excellent temporal and spatial robustness. Long-term studies in a swine model demonstrate the safety, efficacy and reliability of this approach for the co-delivery of on-patient medical record-keeping and the mRNA vaccine encoding severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This technology could help healthcare workers make informed decisions in circumstances where reliable record-keeping is unavailable, thus contributing to global healthcare equity.

PMID:39994390 | DOI:10.1038/s41563-024-02115-4

Sci Rep. 2025 Feb 24;15(1):6650. doi: 10.1038/s41598-025-90607-x.

ABSTRACT

Lung disease is an infection that causes chronic inflammation of the human lung cells, which is one of the major causes of death around the world. Thoracic X-ray medical image is a well-known cheap screening approach used for lung disease detection. Deep learning networks, which are used to identify disease features in X-rays medical images, diagnosing a variety of lung diseases, are playing an increasingly important role in assisting clinical diagnosis. This paper proposes an explainable transformer with a hybrid network structure (LungMaxViT) combining CNN initial stage block with SE block to improve feature recognition for predicting Chest X-ray images for multiple lung disease classification. We contrast four classical pre-training models (ResNet50, MobileNetV2, ViT and MaxViT) through transfer learning based on two public datasets. The LungMaxVit, based on maxvit pre-trained with ImageNet 1K datasets, is a hybrid transformer with fine-tuning hyperparameters on the both X-ray datasets. The LungMaxVit outperforms all the four mentioned models, achieving a classification accuracy of 96.8%, AUC scores of 98.3%, and F1 scores of 96.7% on the COVID-19 dataset, while AUC scores of 93.2% and F1 scores of 70.7% on the Chest X-ray 14 dataset. The LungMaxVit distinguishes by its superior performance in terms of Accuracy, AUC and F1-score compared with other hybrids Networks. Several enhancement techniques, such as CLAHE, flipping and denoising, are employed to improve the classification performance of our study. The Grad-CAM visual technique is leveraged to represent the heat map of disease detection, explaining the consistency among clinical doctors and neural network models in the treatment of lung disease from Chest X-ray. The LungMaxVit shows the robust results and generalization in detecting multiple lung lesions and COVID-19 on Chest X-ray images.

PMID:39994381 | DOI:10.1038/s41598-025-90607-x

Sci Rep. 2025 Feb 24;15(1):6643. doi: 10.1038/s41598-025-90823-5.

ABSTRACT

Faults represent significant geological structures. Conventional fault identification methods pri-marily rely on the linear features of faults, achieved through the interpretation of remote sensing imagery (RSI). To more accurately enhance the morphological features of faults and achieve their rapid, precise, and intelligent identification, this paper employs a multi-source information fusion method. By analyzing and processing RSI, digital elevation model, and geological map data, the spectral, topographic, geomorphic, and structural features of faults are extracted. By training samples and applying fusion algorithms, the spectral, topographic, geomorphic, and structural features are integrated to enhance the morphological features information of faults. Ultimately, intelligent fault identification is realized through deep learning-based image recognition technology. First, 16 influencing factors are selected from the perspectives of spectral, topographic, geomorphic, and structural features. Second, the importance of each influencing factor is predicted using 4 machine learning methods. Finally, fault identification is carried out on the fault identification map, which is fused with multi-source feature information, using the Convolutional Neural Network Model. The study applies the method to the southern part of Jinzhai County, Lu'an City. The results indicate that among the machine learning methods, the classification and regression Trees model achieved an accuracy of 0.993, true positive rate of 0.988, F1-score of 0.994. Topographic position index(TPI), Valley line (VL), Surface cutting depth (SCD), and RSI all show high importance across the four machine learning models, indicating their crucial role in fault identification. For the Convolutional Neural Network model-based method, the Validation Accuracy(Val_Accuracy) was 0.990, F1-score was 0.736, and Validation Loss(Val_Loss) was 0.025, suggesting that this method can accurately identify faults in the study area.

PMID:39994344 | DOI:10.1038/s41598-025-90823-5

Sci Rep. 2025 Feb 24;15(1):6637. doi: 10.1038/s41598-025-90117-w.

ABSTRACT

In recent years, the number of people suffering from depression has gradually increased, and early detection is of great significance for the well-being of the public. However, the current methods for detecting depression are relatively limited, typically relying on the self-rating depression scale (SDS) and interviews. These methods are influenced by subjective or environmental factors. To improve the objectivity and efficiency of diagnosis, deep learning techniques have been applied to the field of automatic depression detection (ADD), providing a more accurate and objective approach. During interviews, transcribed interview data is one of the most commonly used modalities in ADD. However, previous studies have only utilized response texts or selected question-answer pairs, resulting in information redundancy and loss. This paper is the first to apply the multiple instance learning (MIL) framework to the field of textual interview data, aiming to overcome issues of inadequate text representation and ineffective information extraction in long texts. In the MIL framework, each instance undergoes an independent feature extraction process, ensuring that the local features of each instance are fully captured. This not only enhances the overall text representation capability but also alleviates the issue of sample imbalance in the dataset. Additionally, this paper improves upon previous aggregation strategies by introducing two hyper-parameters to accommodate the uncertainties in the field of text sentiment. An ensemble model of MT5 and RoBERTa (referred to as multi-MTRB) was constructed to extract features from each instance and output confidence scores indicating the presence of depressive information in the instances. Due to the unique design of the MIL framework, the proposed method is highly interpretable and is able to identify specific sentences that identify people from depressed patients, while introducing LIME techniques to provide more in-depth interpretation of negative instance sentences. This provides a promising approach for depression detection in the context of text interview data patterns. We evaluated the proposed method on DAIC-WOZ and E-DAIC datasets with excellent results. The F1 score is 0.88 on the DAIC-WOZ dataset and 0.86 on the E-DAIC dataset.

PMID:39994325 | DOI:10.1038/s41598-025-90117-w

Sci Rep. 2025 Feb 24;15(1):6659. doi: 10.1038/s41598-025-91148-z.

ABSTRACT

With the rapid development of the internet, phishing attacks have become more diverse, making phishing website detection a key focus in cybersecurity. While machine learning and deep learning have led to various phishing URL detection methods, many remain incomplete, limiting accuracy. This paper proposes CSPPC-BiLSTM, a malicious URL detection model based on BiLSTM (Bidirectional Long Short-Term Memory, BiLSTM). The model processes URL character sequences through an embedding layer and captures contextual information via BiLSTM. By integrating CBAM (Convolutional Block Attention Module, CBAM), it applies channel and spatial attention to highlight key features and transforms URL sequence features into a spatial matrix. The SPP (Spatial Pyramid Pooling, SPP) module enables multi-scale pooling. Finally, a fully connected layer fuses features, and dropout regularization enhances robustness. Compared to CharBiLSTM, CSPPC-BiLSTM significantly improves detection accuracy. Evaluated on two datasets, Grambedding (balanced) and Mendeley AK Singh 2020 phish (imbalanced)-and compared with six baselines, it demonstrates strong generalization and accuracy. Ablation experiments confirm the critical role of CBAM and SPP in boosting performance.

PMID:39994324 | DOI:10.1038/s41598-025-91148-z

Sci Rep. 2025 Feb 24;15(1):6580. doi: 10.1038/s41598-025-90972-7.

ABSTRACT

Diffusion magnetic resonance imaging (diffusion MRI) is widely employed to probe the diffusive motion of water molecules within the tissue. Numerous diseases and processes affecting the central nervous system can be detected and monitored via diffusion MRI thanks to its sensitivity to microstructural alterations in tissue. The latter has prompted interest in quantitative mapping of the microstructural parameters, such as the fiber orientation distribution function (fODF), which is instrumental for noninvasively mapping the underlying axonal fiber tracts in white matter through a procedure known as tractography. However, such applications demand repeated acquisitions of MRI volumes with varied experimental parameters demanding long acquisition times and/or limited spatial resolution. In this work, we present a deep-learning-based approach for increasing the spatial resolution of diffusion MRI data in the form of fODFs obtained through constrained spherical deconvolution. The proposed approach is evaluated on high quality data from the Human Connectome Project, and is shown to generate upsampled results with a greater correspondence to ground truth high-resolution data than can be achieved with ordinary spline interpolation methods. Furthermore, we employ a measure based on the earth mover's distance to assess the accuracy of the upsampled fODFs. At low signal-to-noise ratios, our super-resolution method provides more accurate estimates of the fODF compared to data collected with 8 times smaller voxel volume.

PMID:39994322 | DOI:10.1038/s41598-025-90972-7

Nat Biotechnol. 2025 Feb 24. doi: 10.1038/s41587-025-02569-0. Online ahead of print.

ABSTRACT

Human lungs contain unique cell populations in distal respiratory airways or terminal and respiratory bronchioles (RA/TRBs) that accumulate in persons with lung injury and idiopathic pulmonary fibrosis (IPF), a lethal lung disease. As these populations are absent in rodents, deeper understanding requires a human in vitro model. Here we convert human pluripotent stem cells (hPS cells) into expandable spheres, called induced respiratory airway progenitors (iRAPs), consisting of ~98% RA/TRB-associated cell types. One hPS cell can give rise to 1010 iRAP cells. We differentiate iRAPs through a stage consistent with transitional type 2 alveolar epithelial (AT2) cells into a population corresponding to mature AT1 cells with 95% purity. iRAPs with deletion of Heřmanský-Pudlák Syndrome 1 (HPS1), which causes pulmonary fibrosis in humans, replicate the aberrant differentiation and recruitment of profibrotic fibroblasts observed in IPF, indicating that intrinsic dysfunction of RA/TRB-associated alveolar progenitors contributes to HPS1-related IPF. iRAPs may provide a system suitable for IPF drug discovery and validation.

PMID:39994483 | DOI:10.1038/s41587-025-02569-0

Sci Rep. 2025 Feb 24;15(1):6670. doi: 10.1038/s41598-025-91060-6.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is characterised by progressive worsening of lung function. In some cases, IPF is accompanied by air-trapping and emphysema. This study aimed to evaluate air trapping quantified with RV/TLC in patients with IPF. This retrospective study included 122 patients diagnosed with IPF in South Korea between January 2011 and December 2020. Air trapping was defined as RV/TLC ≥ 0.40. Increased RV/TLC was found in 34.4% of all patients. The RV/TLC negatively correlated with lung function (forced expiratory volume in 1 s and functional vital capacity [FVC]) and showed consistent results after 1 year of follow-up. After propensity score matching, FVC and diffusion capacity between the groups showed no statistical difference. No difference in lung function decline was found between the increased and not increased RV/TLC groups. Regarding univariable analysis, the patients in the increased RV/TLC group had a lower risk of all-cause mortality (hazard ratio 1.753, P = 0.034). Using multivariable analysis, age, pirfenidone treatment, and FVC were significant factors for survival but not increased RV/TLC. Increased RV/TLC was related to emphysema and demonstrated a negative relationship with lung function. Although increased RV/TLC might relate to poor clinical outcome, it was not independent prognostic factor for IPF.

PMID:39994366 | DOI:10.1038/s41598-025-91060-6