Computers in biology and medicine最新文献

{"title":"The critical role of COL1A1 revealed by integrated bioinformatics analysis of differentially-expressed genes in colorectal cancer and inflammatory bowel disease","authors":"Martyna Pawlak ,&nbsp;Żaneta Kałuzińska-Kołat ,&nbsp;Zbigniew W. Pasieka ,&nbsp;Damian Kołat ,&nbsp;Elżbieta Płuciennik","doi":"10.1016/j.compbiomed.2025.110116","DOIUrl":"10.1016/j.compbiomed.2025.110116","url":null,"abstract":"<div><h3>Purpose</h3><div>There is an urgent need to identify biomarkers of tumorigenesis for colitis-associated cancer (CAC) as early cancer detection remains crucial for patients with inflammatory bowel disease (IBD). This <em>in silico</em> study examines the relationship between IBD and CAC, with particular regard to differentially-expressed genes (DEGs).</div></div><div><h3>Methods</h3><div>Integrated bioinformatics tools and public databases were employed. Data from GEO (GSE102133, GSE48958, GSE9348, GSE83687, GSE138202) were processed using GEOexplorer. DEGs were then functionally annotated with DAVID, SRplot, and integrated analysis via Metascape. Validation used Oncopression and Human Protein Atlas. Survival analysis employed GEPIA2. miRNA interactions were studied via miRTargetLink 2.0. Immune infiltration was analyzed with TIMER 2.0. <em>COL1A1</em> expression and mutations were examined using cBioPortal, Kaplan-Meier plotter, and DNA methylation was analyzed using MethSurv. Correlation of <em>COL1A1</em> gene promoter methylation with tissue type and clinical data was performed using the UALCAN database. The ROC analysis of <em>COL1A1</em> was conducted in the R environment.</div></div><div><h3>Results</h3><div>Our analysis identified three potential hub genes (<em>ICAM1</em>, <em>LAMC1</em>, and <em>COL1A1</em>), which are overexpressed in IBD and cancer tissues compared to normal tissue, and hence may play a role in CAC. Furthermore, patients with lower <em>COL1A1</em> expression had longer disease-free survival (p = 0.01) than those with higher expression. Therefore, this gene was chosen for further analysis and identified as the most crucial.</div></div><div><h3>Conclusion</h3><div><em>COL1A1</em> reveals significant immunohistochemistry, mutations, and methylation data. Further studies involving machine learning and clinical data are required to validate the results.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 110116"},"PeriodicalIF":7.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deployment of a digital twin using the coupled momentum method for fluid–structure interaction: A case study for aortic aneurysm","authors":"Giacomo Creazzo ,&nbsp;Guido Nannini ,&nbsp;Simone Saitta ,&nbsp;Davide Astori ,&nbsp;Mario Gaudino ,&nbsp;Leonard N. Girardi ,&nbsp;Jonathan W. Weinsaft ,&nbsp;Alberto Redaelli","doi":"10.1016/j.compbiomed.2025.110084","DOIUrl":"10.1016/j.compbiomed.2025.110084","url":null,"abstract":"<div><h3>Introduction:</h3><div>Dacron graft replacement is the standard therapy for ascending aorta aneurysm, involving the insertion of a prosthesis with lower compliance than native tissue, which can alter downstream hemodynamics and lead to adverse remodeling. Digital human twins (DHT), based on in-silico models, have the potential to predict biomarkers of adverse outcome and aid in designing optimal treatments tailored to the individual patient.</div></div><div><h3>Objective:</h3><div>We propose a pipeline for deploying a digital human twin of the thoracic aorta to explore alternative solutions to traditional Dacron grafting, utilizing more compliant prostheses for reconstructing the ascending aorta.</div></div><div><h3>Methods:</h3><div>We propose a DHT based on fluid–structure interaction (FSI) analysis of the thoracic aorta. We create 3 models of the patient, representing: (i) the pre-operative baseline, (ii) the post-operative with Dacron graft, and (iii) a virtual post-operative using a compliant fibrous prosthesis. 3D geometry of the thoracic aorta for a patient with a congenital aneurysm, before and after the surgery, were reconstructed from magnetic resonance imaging (MRI). As inlet boundary condition (BC), we assigned a time-varying 3D velocity profile extrapolated from 4D flow MRI. For the outlet BCs, we coupled 0D Windkessel models, tuned to match the flow rate measured in the descending aorta from 4D flow. The aortic wall and the prosthetic graft were modeled as hyperelastic materials using the Holzapfel–Gasser constitutive model and tuned to patients distensibility. FSI analysis was run for two cardiac cycles.</div></div><div><h3>Results:</h3><div>Results were validated against 4D flow data. Quantitative comparison of outflows between FSI and 4D flow yielded relative squared errors of 5.28% and 0.33% for models (i) and (ii), respectively. Wall shear stress (WSS) and strain increased in both post-surgical scenarios (ii) and (iii) compared to (i), with a lower increase observed in the virtual scenario (iii) (<span><math><mrow><mi>p</mi><mo>&lt;</mo><mn>0</mn><mo>.</mo><mn>001</mn></mrow></math></span>). However, the difference between scenarios (iii) and (ii) remained moderate on average (e.g., 0.6 Pa for WSS).</div></div><div><h3>Conclusion:</h3><div>FSI analysis enables the deployment of reliable thoracic aorta DHTs to predict the impact of prostheses with different distensibility. Results indicate moderate yet promising benefits of more compliant fibrous devices on distal hemodynamics.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 110084"},"PeriodicalIF":7.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Two-dimensional vessel wall diffusion anisotropy of human carotids – A novel measure of vascular ageing?","authors":"Stefan L. Leber ,&nbsp;Felix Gunzer ,&nbsp;Eva Maria Hassler ,&nbsp;Peter Opriessnig ,&nbsp;Thomas Metzner ,&nbsp;Günther Silbernagel ,&nbsp;Hannes Deutschmann ,&nbsp;Gernot Reishofer","doi":"10.1016/j.compbiomed.2025.110079","DOIUrl":"10.1016/j.compbiomed.2025.110079","url":null,"abstract":"<div><h3>Background</h3><div>Magnetic resonance (MR) diffusion tensor imaging (DTI) is a new, non-invasive method to investigate arterial vessel walls. High resolution diffusion weighted imaging (DWI) in combination with a two-dimensional (2D) diffusion gradient sampling scheme has recently been demonstrated as feasible for evaluating diffusivity in the vessel wall of human carotids. We aimed to identify associations of altered diffusivity in human carotids with presence or absence of cardiovascular disease, body mass index (BMI), sex and age in a clinical setting.</div></div><div><h3>Methods</h3><div>In this single center case-control study we used DWI in combination with a 2D gradient in a 3 T MRI scanner to evaluate diffusivity parameters in carotid vessel walls of clinical patients with known cardiovascular disease (n = 17) and healthy controls (n = 21). We used a read-out segmented EPI (rs-EPI) sequence for DWI.</div></div><div><h3>Results</h3><div>A group comparison showed significantly decreased fractional anisotropy (FA) in patients older than 60 years (p &lt; 0.001) and in patients with a BMI higher than 25 (p = 0.019). Patients with cardiovascular disease had higher values for mean diffusivity (p = 0.005) than patients without cardiovascular disease. A multiple linear regression analysis showed age and sex to be associated with FA.</div></div><div><h3>Conclusion</h3><div>Two-dimensional vessel wall DTI of human carotids is feasible for clinical research. Besides patient age, we identified Sex, BMI, or the presence of cardiovascular disease as relevant factors for carotid vessel wall diffusivity. Decreased FA values might indicate early-stage atherosclerosis and vascular ageing.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 110079"},"PeriodicalIF":7.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benchmarking pathology foundation models: Adaptation strategies and scenarios","authors":"Jaeung Lee,&nbsp;Jeewoo Lim,&nbsp;Keunho Byeon,&nbsp;Jin Tae Kwak","doi":"10.1016/j.compbiomed.2025.110031","DOIUrl":"10.1016/j.compbiomed.2025.110031","url":null,"abstract":"<div><div>In computational pathology, several foundation models have recently developed, demonstrating enhanced learning capability for analyzing pathology images. However, adapting these models to various downstream tasks remains challenging, particularly when faced with datasets from different sources and acquisition conditions, as well as limited data availability. In this study, we benchmark four pathology-specific foundation models across 20 datasets and two scenarios – consistency assessment and flexibility assessment – addressing diverse adaptation scenarios and downstream tasks. In the consistency assessment scenario, involving five fine-tuning methods, we found that the parameter-efficient fine-tuning approach was both efficient and effective for adapting pathology-specific foundation models to diverse datasets within the same classification tasks. For slide-level survival prediction, the performance of foundation models depended on the choice of feature aggregation mechanisms and the characteristics of data. In the flexibility assessment scenario under data-limited environments, utilizing five few-shot learning methods, we observed that the foundation models benefited more from the few-shot learning methods that involve modification during the testing phase only. These findings provide insights that could guide the deployment of pathology-specific foundation models in real clinical settings, potentially improving the accuracy and reliability of pathology image analysis. The code for this study is available at <span><span>https://github.com/QuIIL/BenchmarkingPathologyFoundationModels</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 110031"},"PeriodicalIF":7.0,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating lightweight convolutional neural network with entropy-informed channel attention and adaptive spatial attention for OCT-based retinal disease classification","authors":"Md Rayhan Ahmed,&nbsp;Mohamed S. Shehata,&nbsp;Patricia Lasserre","doi":"10.1016/j.compbiomed.2025.110071","DOIUrl":"10.1016/j.compbiomed.2025.110071","url":null,"abstract":"<div><div>This article proposes an effective and lightweight contextual convolutional neural network architecture called LOCT-Net for classifying retinal diseases. The LOCT-Net adopts nested residual blocks to capture the local patterns from the optical coherence tomography brightness scans and facilitate gradient flow throughout the network. The multi-scale feature enhancement module incorporates dilation-integrated depthwise strip convolutions to extract fine-grained contextual patterns with an expanded receptive field and a gating mechanism. The extracted features are then refined by a novel feature refinement network consisting of the entropy-informed channel attention module, followed by the adaptive spatial attention module. The entropy-informed channel attention module uses the frequency distribution of pixel values to compute attention weights for spatial analysis. The adaptive spatial attention module focuses on relevant clinical regions and further refines the feature maps in a multi-kernel setting. Additionally, post-explainable artificial intelligence methods are used to provide explanations of LOCT-Net’s decision-making and predictions. The LOCT-Net model has been evaluated on six benchmark datasets, demonstrating an efficient balance between performance and computational cost. With just 2.32 M trainable parameters, the proposed model addresses key challenges in retinal disease classification tasks using OCT B-scans and surpasses previous state-of-the-art methods, achieving an F1 score of 92.98%, 92.34%, 100%, 99.58%, 94.50%, and 97.14% in the OCTID, OCTDL, DUKE, SD-OCT Noor, NEH, and UCSD datasets, respectively.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 110071"},"PeriodicalIF":7.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing cell instance segmentation in scanning electron microscopy images via a deep contour closing operator","authors":"Florian Robert ,&nbsp;Alexia Calovoulos ,&nbsp;Laurent Facq ,&nbsp;Fanny Decoeur ,&nbsp;Etienne Gontier ,&nbsp;Christophe F. Grosset ,&nbsp;Baudouin Denis de Senneville","doi":"10.1016/j.compbiomed.2025.109972","DOIUrl":"10.1016/j.compbiomed.2025.109972","url":null,"abstract":"<div><div>Accurately segmenting and individualizing cells in scanning electron microscopy (SEM) images is a highly promising technique for elucidating tissue architecture in oncology. While current artificial intelligence (AI)-based methods are effective, errors persist, necessitating time-consuming manual corrections, particularly in areas where the quality of cell contours in the image is poor and requires gap filling.</div><div>This study presents a novel AI-driven approach for refining cell boundary delineation to improve instance-based cell segmentation in SEM images, also reducing the necessity for residual manual correction. A convolutional neural network (CNN) Closing Operator (COp-Net) is introduced to address gaps in cell contours, effectively filling in regions with deficient or absent information.</div><div>The network takes as input cell contour probability maps with potentially inadequate or missing information and outputs corrected cell contour delineations. The lack of training data was addressed by generating low integrity probability maps using a tailored partial differential equation (PDE). To ensure reproducibility, COp-Net weights and the source code for solving the PDE are publicly available at <span><span>https://github.com/Florian-40/CellSegm</span><svg><path></path></svg></span>.</div><div>We showcase the efficacy of our approach in augmenting cell boundary precision using both private SEM images from patient-derived xenograft (PDX) hepatoblastoma tissues and publicly accessible images datasets. The proposed cell contour closing operator exhibits a notable improvement in tested datasets, achieving respectively close to 50% (private data) and 10% (public data) increase in the accurately-delineated cell proportion compared to state-of-the-art methods. Additionally, the need for manual corrections was significantly reduced, therefore facilitating the overall digitalization process.</div><div>Our results demonstrate a notable enhancement in the accuracy of cell instance segmentation, particularly in highly challenging regions where image quality compromises the integrity of cell boundaries, necessitating gap filling. Therefore, our work should ultimately facilitate the study of tumour tissue bioarchitecture in onconanotomy field.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 109972"},"PeriodicalIF":7.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ocular surface microbiome: Influences of physiological, environmental, and lifestyle factors","authors":"Vincenzo Rizzuto ,&nbsp;Marzia Settino ,&nbsp;Giacomo Stroffolini ,&nbsp;Giuseppe Covello ,&nbsp;Juris Vanags ,&nbsp;Marta Naccarato ,&nbsp;Roberto Montanari ,&nbsp;Carlos Rocha de Lossada ,&nbsp;Cosimo Mazzotta ,&nbsp;Agostino Forestiero ,&nbsp;Carlo Adornetto ,&nbsp;Miguel Rechichi ,&nbsp;Francesco Ricca ,&nbsp;Gianluigi Greco ,&nbsp;Guna Laganovska ,&nbsp;Davide Borroni","doi":"10.1016/j.compbiomed.2025.110046","DOIUrl":"10.1016/j.compbiomed.2025.110046","url":null,"abstract":"<div><h3>Purpose:</h3><div>The ocular surface (OS) microbiome is influenced by various factors and impacts on ocular health. Understanding its composition and dynamics is crucial for developing targeted interventions for ocular diseases. This study aims to identify host variables, including physiological, environmental, and lifestyle (PEL) factors, that influence the ocular microbiome composition and establish valid associations between the ocular microbiome and health outcomes.</div></div><div><h3>Methods:</h3><div>The 16S rRNA gene sequencing was performed on OS samples collected from 135 healthy individuals using eSwab. DNA was extracted, libraries prepared, and PCR products purified and analyzed. PEL confounding factors were identified, and a cross-validation strategy using various bioinformatics methods including Machine learning was used to identify features that classify microbial profiles.</div></div><div><h3>Results:</h3><div>Nationality, allergy, sport practice, and eyeglasses usage are significant PEL confounding factors influencing the eye microbiome. Alpha-diversity analysis revealed significant differences between Spanish and Italian subjects (<span><math><mi>p</mi></math></span>-value <span><math><mo>&lt;</mo></math></span> 0.001), with a median Shannon index of 1.05 for Spanish subjects and 0.59 for Italian subjects. Additionally, 8 microbial genera were significantly associated with eyeglass usage. Beta-diversity analysis indicated significant differences in microbial community composition based on nationality, age, sport, and eyeglasses usage. Differential abundance analysis identified several microbial genera associated with these PEL factors. The Support Vector Machine (SVM) model for Nationality achieved an accuracy of 100%, with an AUC-ROC score of 1.0, indicating excellent performance in classifying microbial profiles.</div></div><div><h3>Conclusion:</h3><div>This study underscores the importance of considering PEL factors when studying the ocular microbiome. Our findings highlight the complex interplay between environmental, lifestyle, and demographic factors in shaping the OS microbiome. Future research should further explore these interactions to develop personalized approaches for managing ocular health.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 110046"},"PeriodicalIF":7.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DALL-M: Context-aware clinical data augmentation with large language models","authors":"Chihcheng Hsieh ,&nbsp;Catarina Moreira ,&nbsp;Isabel Blanco Nobre ,&nbsp;Sandra Costa Sousa ,&nbsp;Chun Ouyang ,&nbsp;Margot Brereton ,&nbsp;Joaquim Jorge ,&nbsp;Jacinto C. Nascimento","doi":"10.1016/j.compbiomed.2025.110022","DOIUrl":"10.1016/j.compbiomed.2025.110022","url":null,"abstract":"<div><div>X-ray images are vital in medical diagnostics, but their effectiveness is limited without clinical context. Radiologists often find chest X-rays insufficient for diagnosing underlying diseases, necessitating the integration of structured clinical features with radiology reports.</div><div>To address this, we introduce DALL-M, a novel framework that enhances clinical datasets by generating contextual synthetic data. DALL-M augments structured patient data, including vital signs (e.g., heart rate, oxygen saturation), radiology findings (e.g., lesion presence), and demographic factors. It integrates this tabular data with contextual knowledge extracted from radiology reports and domain-specific resources (e.g., Radiopaedia, Wikipedia), ensuring clinical consistency and reliability.</div><div>DALL-M follows a three-phase process: (i) clinical context storage, (ii) expert query generation, and (iii) context-aware feature augmentation. Using large language models (LLMs), it generates both contextual synthetic values for existing clinical features and entirely new, clinically relevant features.</div><div>Applied to 799 cases from the MIMIC-IV dataset, DALL-M expanded the original 9 clinical features to 91. Empirical validation with machine learning models – including Decision Trees, Random Forests, XGBoost, and TabNET – demonstrated a 16.5% improvement in F1 score and a 25% increase in Precision and Recall.</div><div>DALL-M bridges an important gap in clinical data augmentation by preserving data integrity while enhancing predictive modeling in healthcare. Our results show that integrating LLM-generated synthetic features significantly improves model performance, making DALL-M a scalable and practical approach for AI-driven medical diagnostics.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 110022"},"PeriodicalIF":7.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal learning-based speech enhancement and separation, recent innovations, new horizons, challenges and real-world applications","authors":"Rizwan Ullah ,&nbsp;Shaohui Zhang ,&nbsp;Muhammad Asif ,&nbsp;Fazale Wahab","doi":"10.1016/j.compbiomed.2025.110082","DOIUrl":"10.1016/j.compbiomed.2025.110082","url":null,"abstract":"<div><div>With the increasing global prevalence of disabling hearing loss, speech enhancement technologies have become crucial for overcoming communication barriers and improving the quality of life for those affected. Multimodal learning has emerged as a powerful approach for speech enhancement and separation, integrating information from various sensory modalities such as audio signals, visual cues, and textual data. Despite substantial progress, challenges remain in synchronizing modalities, ensuring model robustness, and achieving scalability for real-time applications. This paper provides a comprehensive review of the latest advances in the most promising strategy, multimodal learning for speech enhancement and separation. We underscore the limitations of various methods in noisy and dynamic real-world environments and demonstrate how multimodal systems leverage complementary information from lip movements, text transcripts, and even brain signals to enhance performance. Critical deep learning architectures are covered, such as Transformers, Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), and generative models like Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Diffusion Models. Various fusion strategies, including early and late fusion and attention mechanisms, are explored to address challenges in aligning and integrating multimodal inputs effectively. Furthermore, the paper explores important real-world applications in areas like automatic driver monitoring in autonomous vehicles, emotion recognition for mental health monitoring, augmented reality in interactive retail, smart surveillance for public safety, remote healthcare and telemedicine, and hearing assistive devices. Additionally, critical advanced procedures, comparisons, future challenges, and prospects are discussed to guide future research in multimodal learning for speech enhancement and separation, offering a roadmap for new horizons in this transformative field.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 110082"},"PeriodicalIF":7.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evolutionary trajectories of Nipah virus: Evaluating the antiviral efficacy of Kabasura Kudineer Chooranam","authors":"Mohanraj Gopikrishnan ,&nbsp;Santhosh Mudipalli Elavarasu ,&nbsp;Karthick Vasudevan ,&nbsp;M.S. Shree Devi ,&nbsp;Sasikumar K ,&nbsp;Shree Laya Varsha A ,&nbsp;George Priya Doss C","doi":"10.1016/j.compbiomed.2025.109973","DOIUrl":"10.1016/j.compbiomed.2025.109973","url":null,"abstract":"<div><div>Nipah virus (NiV) is a highly contagious zoonotic pathogen causing severe encephalitis and respiratory illnesses in humans. With a high fatality rate and no FDA-approved treatments, NiV poses a significant public health threat. This study conducts a comprehensive Bayesian phylogenetic analysis of all publicly available NiV genomes since the first human case. Additionally, a protein-protein interaction (PPI) network analysis focusing on <em>Pteropus</em> species was performed to identify potential therapeutic targets. High-throughput virtual screening assessed the inhibitory potential of Kabasura Kudineer Chooranam phytocompounds against these targets. Molecular dynamic simulations (MDS) were conducted to evaluate the stability and dynamic characteristics of NiV proteins bound to specific inhibitors. Bayesian phylogenetic analysis of 280 NiV genomes revealed two distinct clades among Indian isolates, highlighting significant regional diversity. Notably, the latest strain, OM135495, along with other NiV variants in Kerala, underscores the virus's rapid genetic evolution since 2015. The PPI network identified NiV-F, NiV-G, and NiV-N as key therapeutic targets. Among the tested phyto compounds, Vasicinone and Piperine exhibited strong binding affinities (−4.51 to −5.96 kcal/mol) and enhanced stability during MDS, suggesting their potential as antiviral agents. These findings indicate that phyto compounds may serve as viable alternatives for NiV treatment, paving the way for novel drug development. However, further validation through laboratory and animal studies is essential. This study enhances our understanding of NiV evolution, informs public health strategies, and contributes to preparedness for future outbreaks.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"190 ","pages":"Article 109973"},"PeriodicalIF":7.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}