Front Comput Neurosci. 2025 Feb 10;19:1561635. doi: 10.3389/fncom.2025.1561635. eCollection 2025.

NO ABSTRACT

PMID:39995891 | PMC:PMC11847876 | DOI:10.3389/fncom.2025.1561635

Front Neurol. 2025 Feb 10;16:1434334. doi: 10.3389/fneur.2025.1434334. eCollection 2025.

ABSTRACT

INTRODUCTION: Although medical imaging plays a crucial role in stroke management, machine learning (ML) has been increasingly used in this field, particularly in lesion segmentation. Despite advances in acquisition technologies and segmentation architectures, one of the main challenges of subacute stroke lesion segmentation in computed tomography (CT) imaging is image contrast.

METHODS: To address this issue, we propose a method to assess the contrast quality of an image dataset with a ML trained model for segmentation. This method identifies the critical contrast level below which the medical-imaging model fails to learn meaningful content from images. Contrast measurement relies on the Fisher's ratio, estimating how well the stroke lesion is contrasted from the background. The critical contrast is found-thanks to the following three methods: Performance, graphical, and clustering analysis. Defining this threshold improves dataset design and accelerates training by excluding low-contrast images.

RESULTS: Application of this method to brain lesion segmentation in CT imaging highlights a Fisher's ratio threshold value of 0.05, and training validation of a new model without these images confirms this with similar results with only 60% of the training data, resulting in an almost 30% reduction in initial training time. Moreover, the model trained without the low-contrast images performed equally well with all images when tested on another database.

DISCUSSION: This study opens discussion with clinicians concerning the limitations, areas for improvement, and strategies for enhancing datasets and training models. While the methodology was only applied to stroke lesion segmentation in CT images, it has the potential to be adapted to other tasks.

PMID:39995787 | PMC:PMC11849432 | DOI:10.3389/fneur.2025.1434334

Quant Imaging Med Surg. 2025 Feb 1;15(2):1265-1274. doi: 10.21037/qims-24-772. Epub 2025 Jan 21.

ABSTRACT

BACKGROUND: Anterior compartment prolapse is a common pelvic organ prolapse (POP), which occurs frequently among middle-aged and elderly women and can cause urinary incontinence, perineal pain and swelling, and seriously affect their physical and mental health. At present, pelvic floor ultrasound is the primary examination method, but it is not carried out by many primary medical institutions due to the significant shortcomings of training in the early stage and the variable image quality. There has been great progress in the application of deep learning (DL) in image-based diagnosis in various clinical contexts. The main purpose of this study was to improve the speed and reliability of pelvic floor ultrasound diagnosis of POP by training neural networks to interpret ultrasound images, thereby facilitating the diagnosis and treatment of POP in primary care.

METHODS: This retrospective study analyzed medical records of women with anterior compartment organ prolapse (n=1,605, mean age 45.1±12.2 years) or without (n=200, mean age 38.1±13.4 years), who were examined at West China Second University Hospital between March 2019 and September 2021. Static ultrasound images of the anterior chamber of the pelvic floor (5,281 abnormal, 535 normal) were captured at rest and at maximal Valsalva motion, and four convolutional neural network (CNN) models, AlexNet, VGG-16, ResNet-18, and ResNet-50, were trained on 80% of the images, then internally validated on the other 20%. Each model was trained in two ways: through a random initialization parameter training method and through a transfer learning method based on ImageNet pre-training. The diagnostic performance of each network was evaluated according to accuracy, precision, recall and F1-score, and the receiver operating characteristic (ROC) curve of each network in the training set and validation set was drawn and the area under the curve (AUC) was obtained.

RESULTS: All four models, regardless of training method, achieved recognition accuracy of >91%, whereas transfer learning led to more stable and effective feature extraction. Specifically, ResNet-18 and ResNet-50 performed better than AlexNet and VGG-16. However, the four networks learned by transfer all showed fairly high AUCs, with the ResNet-18 network performing the best: it read images in 13.4 msec and provided recognition an accuracy of 93.53% along with an AUC of 0.852.

CONCLUSIONS: Combining DL with pelvic floor ultrasonography can substantially accelerate diagnosis of anterior compartment organ prolapse in women while improving accuracy.

PMID:39995742 | PMC:PMC11847209 | DOI:10.21037/qims-24-772

Quant Imaging Med Surg. 2025 Feb 1;15(2):1455-1467. doi: 10.21037/qims-24-1577. Epub 2025 Jan 20.

ABSTRACT

BACKGROUND: Deep learning (DL) technologies are playing increasingly important roles in computer-aided diagnosis in medicine. In this study, we sought to address issues related to the diagnosis of Alzheimer's disease (AD) based on multi-modal features, and introduced a multi-modal three-dimensional Inception-v4 model that employs transfer learning for AD diagnosis based on magnetic resonance imaging (MRI) and clinical score data.

METHODS: The multi-modal three-dimensional (3D) Inception-v4 model was first pre-trained using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Subsequently, independent validation data were used to fine-tune the model with pre-trained weight parameters. The model was quantitatively evaluated using the mean values obtained from five-fold cross-validation. Further, control experiments were conducted to verify the performance of the model patients with AD, and in the study of disease progression.

RESULTS: In the AD diagnosis task, when a single image marker was used, the average accuracy (ACC) and area under the curve (AUC) were 62.21% and 71.87%, respectively. When transfer learning was not employed, the average ACC and AUC were 75.74% and 83.13%, respectively. Conversely, the combined approach proposed in this study achieved an average ACC of 87.84%, and an average AUC of 90.80% [with an average precision (PRE) of 87.21%, an average recall (REC) of 82.52%, and an average F1 of 83.58%].

CONCLUSIONS: In comparison with existing methods, the performance of the proposed method was superior in terms of diagnostic accuracy. Specifically, the method showed an enhanced ability to accurately distinguish among various stages of AD. Our findings show that multi-modal feature fusion and transfer learning can be valuable resources in the treatment of patients with AD, and in the study of disease progression.

PMID:39995734 | PMC:PMC11847174 | DOI:10.21037/qims-24-1577

J Labelled Comp Radiopharm. 2025 Jan-Feb;68(1-2):e4133. doi: 10.1002/jlcr.4133.

ABSTRACT

(R)-2-(4-(5-Chloropyrimidin-2-yl)piperidin-1-yl)-4-((1-(hydroxymethyl)cyclobutyl)amino)-6,7-dihydrothieno[3,2-d]pyrimidine 5-oxide (BI 1015550, 1) is a potent and selective inhibitor of phosphodiesterase type 4 (PDE4) being developed for the treatment of idiopathic pulmonary fibrosis (IPF) and progressive pulmonary fibrosis (PPF). We report the synthesis of this drug candidate labelled with carbon 14 and deuterium. The carbon 14 synthesis was completed in three radioactive steps in 27% overall yield, with a specific activity of 52 mCi/mmol (1.92 GBq/mmol), radiochemical purity, and enantiomeric excess higher than 99%. The deuterium labelled compound was prepared in seven steps in 67% overall yield and with isotopic enrichment, chemical purity, and enantiomeric excess higher than 99%.

PMID:39995220 | DOI:10.1002/jlcr.4133

J Exp Bot. 2025 Feb 25;76(4):899-903. doi: 10.1093/jxb/erae411.

NO ABSTRACT

PMID:39996292 | DOI:10.1093/jxb/erae411

JHEP Rep. 2024 Nov 12;7(3):101267. doi: 10.1016/j.jhepr.2024.101267. eCollection 2025 Mar.

ABSTRACT

BACKGROUND & AIMS: Primary sclerosing cholangitis (PSC) is a chronic heterogenous cholangiopathy with unknown etiology where chronic inflammation of the bile ducts leads to multifocal biliary strictures and biliary fibrosis with consecutive cirrhosis development. We here aimed to identify a PSC-specific gene signature associated with biliary fibrosis development.

METHODS: We performed RNA-sequencing of 47 liver biopsies from people with PSC (n = 16), primary biliary cholangitis (PBC, n = 15), and metabolic dysfunction-associated steatotic liver disease (MASLD, n = 16) with different fibrosis stages to identify a PSC-specific gene signature associated with biliary fibrosis progression. For validation, we compared an external transcriptome data set of liver biopsies from people with PSC (n = 73) with different fibrosis stages (baseline samples from NCT01672853).

RESULTS: Differential gene expression analysis of the liver transcriptome from patients with PSC with advanced vs. early fibrosis revealed 431 genes associated with fibrosis development. Of those, 367 were identified as PSC-associated when compared with PBC or MASLD. Validation against an external data set of 73 liver biopsies from patients with PSC with different fibrosis stages led to a condensed set of 150 (out of 367) differentially expressed genes. Cell type specificity assignment of those genes by using published single-cell RNA-Seq data revealed genetic disease drivers expressed by cholangiocytes (e.g. CXCL1, SPP1), fibroblasts, innate, and adaptive immune cells while deconvolution along fibrosis progression of the PSC, PBC, and MASLD samples highlighted an early involvement of macrophage- and neutrophil-associated genes in PSC fibrosis.

CONCLUSIONS: We reveal a PSC-attributed gene signature associated with biliary fibrosis development that may enable the identification of potential new biomarkers and therapeutic targets in PSC-related fibrogenesis.

IMPACT AND IMPLICATIONS: Primary sclerosing cholangitis (PSC) is an inflammatory liver disease that is characterized by multifocal inflammation of bile ducts and subsequent biliary fibrosis. Herein, we identify a PSC-specific gene set of biliary fibrosis progression attributing to a uniquely complex milieu of different cell types, including innate and adaptive immune cells while neutrophils and macrophages showed an earlier involvement in fibrosis initiation in PSC in contrast to PBC and metabolic dysfunction-associated steatotic liver disease. Thus, our unbiased approach lays an important groundwork for further mechanistic studies for research into PSC-specific fibrosis.

PMID:39996122 | PMC:PMC11848773 | DOI:10.1016/j.jhepr.2024.101267

iScience. 2025 Jan 27;28(2):111808. doi: 10.1016/j.isci.2025.111808. eCollection 2025 Feb 21.

ABSTRACT

Intracrinology-wherein hormones are synthesized in the organ where they exert their effect without release into circulation-has been described. However, molecular mechanisms of hormone deactivation within intracrine tissue are still largely unknown. The meibomian glands in the eyelids produce oil (meibum) to the ocular surface to prevent dehydration (dry eye). Androgens are generated inside this gland and are crucial for its tissue-homeostasis. However, there is no data showing the presence of androgens in meibum, implying local conversion/deactivation into unknown metabolites. Here, we performed radioactive tracer studies in combination with pharmacological enzyme inhibition, followed by targeted liquid chromatography-tandem mass spectrometry (LC-MS/MS) analysis, and found three androgen metabolites-androstanedione, androsterone, and epiandrosterone-in mouse and human meibomian glands. Accounting for the enzymatic conversion, we show tissue-endogenous 3α/3β-ketosteroid reductase expression. We therefore reinforce the idea that androgens are metabolically inactivated within the glands. These metabolite markers may help to assess meibomian local androgen activity using meibum.

PMID:39995859 | PMC:PMC11848505 | DOI:10.1016/j.isci.2025.111808

Int J Cardiol Heart Vasc. 2025 Feb 5;57:101621. doi: 10.1016/j.ijcha.2025.101621. eCollection 2025 Apr.

ABSTRACT

BACKGROUND: Atrial fibrillation Better Care (ABC) pathway is recommended by guidelines on atrial fibrillation (AF) and exerts a protective role against adverse outcomes of AF patients. But the possible differences in its effectiveness across the diverse range of patients in China have not been systematically evaluated. We aim to comprehensively evaluate multiple clinical characteristics of patients, and probe clusters of ABC criteria efficacy in patients with AF.

METHODS: We used data from an observational cohort that included 2,016 patients with AF. We utilized 45 baseline variables for cluster analysis. We evaluated the management patterns and adverse outcomes of identified phenotypes. We assessed the effectiveness of adherence to the ABC criteria at reducing adverse outcomes of phenotypes.

RESULTS: Cluster analysis identified AF patients into three distinct groups. The clusters include Cluster 1: old patients with the highest prevalence rates of atherosclerotic and/or other comorbidities (n = 964), Cluster 2: valve-comorbidities AF in young females (n = 407), and Cluster 3: low comorbidity patients with paroxysmal AF (n = 644). The clusters showed significant differences in MACNE, all-cause death, stroke, and cardiovascular death. All clusters showed that full adherence to the ABC pathway was associated with a significant reduction in the risk of MACNE (all P < 0.05). For three clusters, adherence to the different 'A'/'B'/'C' criterion alone showed differential clinic impact.

CONCLUSION: Our study suggested specific optimization strategies of risk stratification and integrated management for different groups of AF patients considering multiple clinical, genetic and socioeconomic factors.

PMID:39995811 | PMC:PMC11848476 | DOI:10.1016/j.ijcha.2025.101621

Rep Biochem Mol Biol. 2024 Jul;13(2):281-300. doi: 10.61186/rbmb.13.2.281.

ABSTRACT

BACKGROUND: Gastric cancer (GC) is a prevalent malignancy with high recurrence. Advances in systems biology have identified molecular pathways and biomarkers. This study focuses on discovering gene and miRNA biomarkers for diagnosing and predicting survival in GC patients.

METHODS: Three sets of genes (GSE19826, GSE81948, and GSE112369) and two sets of miRNA expression (GSE26595, GSE78775) were obtained from the Gene Expression Omnibus (GEO), and subsequently, differentially expressed genes (DEGs) and miRNAs (DEMs) were identified. Functional pathway enrichment, DEG-miR-TF-protein-protein interaction network, DEM-mRNA network, ROC curve, and survival analyses were performed. Finally, qRT-PCR was applied to validate our results.

RESULTS: From the high-throughput profiling studies of GC, we investigated 10 candidate mRNA and 7 candidate miRNAs as potential biomarkers. Expression analysis of these hubs revealed that 5 miRNAs (including miR-141-3p, miR-204-5p, miR-338-3p, miR-609, and miR-369-5p) were significantly upregulated compared to the controls. The genes with the highest degree included 6 upregulated and 4 downregulated genes in tumor samples compared to controls. The expression of miR-141-3p, miR-204-5p, SESTD1, and ANTXR1 were verified in vitro from these hub DEMs and DEGs. The findings indicated a decrease in the expression of miR-141-3p and miR-204-5p and increased expression of SESTD1 and ANTXR1 in GC cell lines compared to the GES-1 cell line.

CONCLUSIONS: The current investigation successfully recognized a set of prospective miRNAs and genes that may serve as potential biomarkers for GC's early diagnosis and prognosis.

PMID:39995653 | PMC:PMC11847593 | DOI:10.61186/rbmb.13.2.281

J Vis Exp. 2025 Feb 7;(216). doi: 10.3791/67892.

ABSTRACT

Systematic screening of gain- or loss-of-function genetic perturbations can be used to characterize the genetic dependencies and mechanisms of regulation for essentially any cellular process of interest. These experiments typically involve profiling from a pool of single gene perturbations and how each genetic perturbation affects the relative cell fitness. When applied in the context of drug efficacy studies, often called chemo-genetic profiling, these methods should be effective at identifying drug mechanisms of action. Unfortunately, fitness-based chemo-genetic profiling studies are ineffective at identifying all components of a drug response. For instance, these studies generally fail to identify which genes regulate drug-induced cell death. Several issues contribute to obscuring death regulation in fitness-based screens, including the confounding effects of proliferation rate variation, variation in the drug-induced coordination between growth and death, and, in some cases, the inability to separate DNA from live and dead cells. MEDUSA is an analytical method for identifying death-regulatory genes in conventional chemo-genetic profiling data. It works by using computational simulations to estimate the growth and death rates that created an observed fitness profile rather than scoring fitness itself. Effective use of the method depends on optimal tittering of experimental conditions, including the drug dose, starting population size, and length of the assay. This manuscript will describe how to set up a chemo-genetic profiling study for MEDUSA-based analysis, and we will demonstrate how to use the method to quantify death rates in chemo-genetic profiling data.

PMID:39995184 | DOI:10.3791/67892

Pharmacol Res Perspect. 2025 Apr;13(2):e70080. doi: 10.1002/prp2.70080.

ABSTRACT

Concern over the side effects of anti-obesity medications, particularly if severe, has grown as their use has increased. Thus, the objective was to use trends in the reporting of suspected adverse events associated with anti-obesity medications that have been approved for sale in the European Union to attempt to uncover discrepancies in the safety of these medications. The study was designed as secondary research, based on data about the number of adverse drug reactions (both serious and non-serious) reported to the EudraVigilance database. Trends of the annual reporting rates for the six anti-obesity drugs were analyzed by the Joinpoint Trend Analysis Software that divides the trendline into an optimum number of segments connected by "joinpoints" and tests the significance of the trend within each segment. The trends of serious adverse drug events showed clear differences among the anti-obesity drugs: while all drugs had significant increasing trends during a few initial years after their appearance on the market, only the annual number of reports for semaglutide continued to grow ever since (annual change + 67.1%, p = 0.000). On the contrary, a continuous increase in the reporting rate of non-serious adverse drug events was observed only for liraglutide (annual change + 33.8%, p = 0.000) while for the other anti-obesity drugs, including semaglutide, the trends after the initial period were either negative or did not increase significantly. In conclusion, among the anti-obesity drugs currently approved, only semaglutide shows a continuously increasing trend in the annual reporting of serious adverse events, suggesting a need for further investigation of safety signals.

PMID:39995024 | DOI:10.1002/prp2.70080

Virus Res. 2025 Apr;354:199549. doi: 10.1016/j.virusres.2025.199549. Epub 2025 Feb 22.

ABSTRACT

The adeno-associated virus 9 (AAV9) vector was particularly notable for its broad tissue tropism, making it a preferred vector for gene therapy. Goals: The study aimed to investigate the patterns of pre-existing immunity against AAV9 in the Chinese population. In this study, we conducted a serological research from November 2022 to June 2024. The study included 341 participants in total with age ranged from 0 to 90 years old: 270 healthy individuals, 30 pediatric patients and 41 adults with rare diseases. Total AAV9-binding antibodies (TAbs) and neutralizing antibodies (NAbs) were measured. The seroprevalence of anti-AAV9 NAbs showed no significant differences between healthy individuals and rare disease patients across both pediatric and adult groups. Newborns exhibited a high NAb-positive rate (64.3 %), while children aged 6 months to 3 years had the lowest prevalence (7.7 %). This rate progressively increased through childhood and adolescence. Overall, 58.7 % of the Chinese population aged 0-90 years tested positive for anti-AAV9 NAbs, with adults showing a significantly higher prevalence than children (75.0 % vs. 34.3 %). Additionally, 58.1 % of the population exhibited low levels of anti-AAV9 NAb titers (IC50 ≤ 100). No significant sex-specific differences were observed, and antibody titers (NAbs or TAbs) showed no strong correlation with age. A strong correlation was identified between TAb and NAb positivity rates and titers. The optimal AAV9-based GT period was between 6 months and 3 years in that patients possessed lowest pre-existing immunity. Since TAbs had a strong association with NAbs, TAbs was considered as an alternative indicator to screen rare diseases.

PMID:39993606 | DOI:10.1016/j.virusres.2025.199549

Sci Rep. 2025 Feb 24;15(1):6656. doi: 10.1038/s41598-025-90809-3.

ABSTRACT

GPS spoofing presents a significant threat to small Unmanned Aerial Vehicles (UAVs) by manipulating navigation systems, potentially causing safety risks, privacy violations, and mission disruptions. Effective countermeasures include secure GPS signal authentication, anti-spoofing technologies, and continuous monitoring to detect and respond to such threats. Safeguarding small UAVs from GPS spoofing is crucial for their reliable operation in applications such as surveillance, agriculture, and environmental monitoring. In this paper, we propose a compact, tiny deep learning architecture named CTDNN-Spoof for detecting and multi-label classifying GPS spoofing attacks in small UAVs. The architecture utilizes a sequential neural network with 64 neurons in the input layer (ReLU activation), 32 neurons in the hidden layer (ReLU activation), and 4 neurons in the output layer (linear activation), optimized with the Adam optimizer. We use Mean Squared Error (MSE) loss for regression and accuracy for evaluation. First, early stopping with a patience of 10 epochs is implemented to improve training efficiency and restore the best weights. Furthermore, the model is also trained for 50 epochs, and its performance is assessed using a separate validation set. Additionally, we use two other models to compare with the CTDNN-Spoof in terms of complexity, loss, and accuracy. The proposed CTDNN-Spoof demonstrates varying accuracies across different labels, with the proposed architecture achieving the highest performance and promising time complexity. These results highlight the model's effectiveness in mitigating GPS spoofing threats in UAVs. This innovative approach provides a scalable, real-time solution to enhance UAV security, surpassing traditional methods in precision and adaptability.

PMID:39994281 | DOI:10.1038/s41598-025-90809-3

Sci Rep. 2025 Feb 24;15(1):6562. doi: 10.1038/s41598-025-89451-w.

ABSTRACT

Image denoising is a critical problem in low-level computer vision, where the aim is to reconstruct a clean, noise-free image from a noisy input, such as a mammogram image. In recent years, deep learning, particularly convolutional neural networks (CNNs), has shown great success in various image processing tasks, including denoising, image compression, and enhancement. While CNN-based approaches dominate, Transformer models have recently gained popularity for computer vision tasks. However, there have been fewer applications of Transformer-based models to low-level vision problems like image denoising. In this study, a novel denoising network architecture called DeepTFormer is proposed, which leverages Transformer models for the task. The DeepTFormer architecture consists of three main components: a preprocessing module, a local-global feature extraction module, and a reconstruction module. The local-global feature extraction module is the core of DeepTFormer, comprising several groups of ITransformer layers. Each group includes a series of Transformer layers, convolutional layers, and residual connections. These groups are tightly coupled with residual connections, which allow the model to capture both local and global information from the noisy images effectively. The design of these groups ensures that the model can utilize both local features for fine details and global features for larger context, leading to more accurate denoising. To validate the performance of the DeepTFormer model, extensive experiments were conducted using both synthetic and real noise data. Objective and subjective evaluations demonstrated that DeepTFormer outperforms leading denoising methods. The model achieved impressive results, surpassing state-of-the-art techniques in terms of key metrics like PSNR, FSIM, EPI, and SSIM, with values of 0.41, 0.93, 0.96, and 0.94, respectively. These results demonstrate that DeepTFormer is a highly effective solution for image denoising, combining the power of Transformer architecture with convolutional layers to enhance both local and global feature extraction.

PMID:39994276 | DOI:10.1038/s41598-025-89451-w

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