检索结果-内蒙古大学图书馆

A Transformer-Based multi-Scale Deep Learning Model for Lung Cancer Surgery Optimization

IEEE ACCESS 2025年 13卷 70044-70054页

作者： Zhu, Pengfei Wang, Tingmin Yang, Fan Wang, Meng Zhang, Yunjie Shandong Univ Tradit Chinese Med Affiliated Hosp Thorac Surg Jinan 250011 Shandong Peoples R China Shandong Univ Tradit Chinese Med Affiliated Hosp Dept Anesthesiol Jinan 250011 Shandong Peoples R China Shandong Univ Tradit Chinese Med Affiliated Hosp Gen Surg Jinan 250011 Shandong Peoples R China

Lung cancer surgery presents significant challenges due to its complexity and the need for precise risk stratification to improve patient outcomes. This study presents a Transformer-based multi-scale deep learning framework that integrates imaging, clinical, and genomic data to optimize decision-making surrounding surgery. By using the self-attention mechanism in Transformers and multi-scale feature extraction, the model expertly explores different data modalities. Therefore, it enables a precise prediction of surgical risks, such as delayed extubation and mortality;besides, it further performs risk stratification, having the model improve resource utilization by identifying high- and low-risk patients, ensuring that intervention is matched accordingly and resources are not wasted on unnecessary measures. Thorough evaluations, including ablation experiments, case analyses, and error analyses, prove the model's robustness and practical applicability in a clinical setting. This study demonstrates the game-changing potential of advanced deep learning techniques in the field of precision medicine and provides a concrete framework for personalized treatment in lung cancer surgery, laying the foundation for broader healthcare applications.

关键词： Surgery Lung cancer data models Transformers Genomics Bioinformatics Tumors Deep learning Feature extraction Predictive models Transformer-based model multi-scale deep learning lung cancer surgery risk assessment multi-modal data integration personalized medicine

来源：评论

学校读者我要写书评

暂无评论

integration of multi-modal datasets to estimate human aging

引用

MACHINE LEARNING 2024年第10期113卷 7293-7317页

作者： Ribeiro, Rogerio Moraes, Athos Moreno, Marta Ferreira, Pedro G. Univ Porto Fac Sci Dept Comp Sci Rua Campo Alegre P-4169007 Porto Portugal Inst Syst & Comp Engn Technol & Sci Lab Artificial Intelligence & Decis Support Rua Dr Roberto Frias P-4200465 Porto Portugal

Aging involves complex biological processes leading to the decline of living organisms. As population lifespan increases worldwide, the importance of identifying factors underlying healthy aging has become critical. integration of multi-modal datasets is a powerful approach for the analysis of complex biological systems, with the potential to uncover novel aging biomarkers. In this study, we leveraged publicly available epigenomic, transcriptomic and telomere length data along with histological images from the Genotype-Tissue Expression project to build tissue-specific regression models for age prediction. Using data from two tissues, lung and ovary, we aimed to compare model performance across data modalities, as well as to assess the improvement resulting from integrating multiple data types. Our results demostrate that methylation outperformed the other data modalities, with a mean absolute error of 3.36 and 4.36 in the test sets for lung and ovary, respectively. These models achieved lower error rates when compared with established state-of-the-art tissue-agnostic methylation models, emphasizing the importance of a tissue-specific approach. Additionally, this work has shown how the application of Hierarchical Image Pyramid Transformers for feature extraction significantly enhances age modeling using histological images. Finally, we evaluated the benefits of integrating multiple data modalities into a single model. Combining methylation data with other data modalities only marginally improved performance likely due to the limited number of available samples. Combining gene expression with histological features yielded more accurate age predictions compared with the individual performance of these data types. Given these results, this study shows how machine learning applications can be extended to/in multi-modal aging research. Code used is available at https://***/zroger49/multi_modal_age_prediction.

关键词： Machine learning Aging prediction multi-omics multi-modal data integration Imbalance regression

来源：评论

学校读者我要写书评

暂无评论

Exploring urban environmental semantics for air quality prediction using explainable multi-view spatiotemporal graph neural networks

引用

APPLIED GEOGRAPHY 2025年 178卷

作者： Long, Qi Ma, Jun Univ Hong Kong Dept Urban Planning & Design Hong Kong Peoples R China

Accurate air quality forecasting is essential for urban management and public health, yet it remains challenging due to the complexity of spatiotemporal air pollution dynamics and the interplay of static and dynamic urban factors. Traditional models often neglect the influence of static urban drivers, such as built environment features, which are critical to understanding pollution patterns. Addressing this limitation, we propose a multi-view, multi-modal Spatio-Temporal Graph Neural Network (STGNN) framework that integrates dynamic pollution data with static urban environmental semantics to improve predictive performance and interpretability. By embedding static features, such as Points of Interest (POIs), into the graph structure and leveraging a selfattention mechanism, our model captures complex spatial dependencies and temporal dynamics. Furthermore, an integrated Explainer module enhances transparency by revealing the spatial and feature-level influences driving air quality predictions. Experimental results demonstrate that our approach not only achieves superior predictive accuracy compared to benchmark models but also provides actionable insights into the relationships between urban features and air quality. This study highlights the importance of integrating multi-modal data and interpretability in advancing air quality prediction, offering valuable implications for urban planning and pollution mitigation strategies.

关键词： Air pollution dynamics Urban environmental semantics multi-modal data integration Explainable machine learning Spatio-temporal graph neural networks multi-view learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised machine learning-based stratification and immune deconvolution of liver hepatocellular carcinoma

引用

BMC CANCER 2025年第1期25卷 1-16页

作者： Reierson, Mae Montserrat Acharjee, Animesh Univ Birmingham Coll Med & Hlth Sch Med Sci Canc & Genom Sci Birmingham B15 2TT England Univ Hosp Birmingham NHS Fdn Trust Inst Translat Med Birmingham B15 2TT England MRC Hlth Data Res UK HDR Midlands Site England Univ Birmingham Ctr Hlth Data Res Birmingham B15 2TT England

BackgroundHepatocellular carcinoma (HCC) is the most prevalent type of liver cancer and a leading cause of cancer-related deaths globally. The tumour microenvironment (TME) influences treatment response and prognosis, yet its heterogeneity remains *** unsupervised machine learning methods- agglomerative hierarchical clustering, multi-Omics Factor Analysis with K-means++, and an autoencoder with K-means++ - stratified patients using microarray data from HCC samples. Immune deconvolution algorithms estimated the proportions of infiltrating immune cells across identified *** genes were found to influence HCC subtyping in both primary and validation datasets, with three genes-TOP2A, DCN, and MT1E-showing significant associations with survival and recurrence. DCN, a known tumour suppressor, was significant across datasets and associated with improved survival, potentially by modulating the TME and promoting an anti-tumour immune *** discovery of the 13 conserved genes is an important step toward understanding HCC heterogeneity and the TME, potentially leading to the identification of more reliable biomarkers and therapeutic targets. We have stratified and validated the liver cancer populations. The findings suggest further research is needed to explore additional factors influencing the TME beyond gene expression, such as tumour microbiome and stromal cell interactions.

关键词： Unsupervised machine learning Liver hepatocellular carcinoma Immune deconvolution Tumor stratification Tumor microenvironment multi-modal data integration

来源：评论

学校读者我要写书评

暂无评论

Enhancing Computational Processing Performance for Generative AI Large Models with Autonomous Decision-Making in Metaverse Applications 2

Enhancing Computational Processing Performance for Generativ...

引用

2024 International Conference on Metaverse Computing, Networking, and Application

作者： Ding, Pengyong Liu, Jiarong Sun, Min Li, Li Liu, Hong China Mobile Informat Technol CO Ltd Shenzhen Peoples R China

ISBN: (纸本)9798331516000;9798331515997

We explore how to enhance the computational processing performance for generative AI large models with autonomous decision-making in metaverse applications. We first introduce the relationship between AI large models and the Metaverse. We elaborate on the application scenarios of generative AI large models in Metaverse, including real-time weather simulation, embodied intelligence of agents, dynamic environment interaction, and user emotion recognition. We then propose the method of multi-Dimensional Optimization Generation Framework (MDOGF) to improve computational processing performance. The experiment results show great improvement in computational processing performance.

关键词： Generative AI Large Models Metaverse Autonomous Decision-Making Reinforcement Learning multi-Agent Systems Model Compression Model Acceleration multi-modal data integration Digital Twin Technology AGI (Artificial General Intelligence)

来源：评论

学校读者我要写书评

暂无评论

Single Cell multi-modal Analysis Using scDMVAE with an Emphasis on SCoPE2 Technology

Single Cell Multi-Modal Analysis Using scDMVAE with an Empha...

引用

作者： Zheng, Yi University of California Santa Barbara

学位级别：Ph.D., Doctor of Philosophy

Effective multi-modal integration of single cell datasets is critical for uncovering the biological properties of cells from different molecular perspectives. However, this poses significant challenges, including how to preserve shared information and account for differences between differently distributed datasets, how to integrate datasets linked by different anchors (cells or features) and how to improve the quality of datasets for integration. In this dissertation, we introduce two novel models that address these challenges. First, we present scDMVAE, a neural network model that can capture both shared and data-specific aspects of datasets in a latent space. scDMVAE can handle both cell-linked and feature-linked datasets through its embedding learning and attention-based matching components, respectively. We demonstrate the effectiveness of scDMVAE on a cell-linked CITE-seq dataset to reveal different cell type relations between mRNA and protein, and on feature-linked SCoPE2 proteomics and scRNA-Seq mRNA human testis datasets to transfer labels from mRNA to protein. Additionally, we present PCRID, a principal curve based model that aligns the retention time of peptides to improve confidence estimates of peptide-spectrum-matches (PSMs) in SCoPE2 technology. PCRID outperforms existing models like DART-ID by handling non-linearities in retention time more effectively, increasing the identification rate of peptides by 154.53 % at a PEP threshold of 0.01 while controlling false discoveries. Together, these models represent significant advances in single cell data analysis and have broad applications across related fields.

关键词： multi-modal data integration Variational autoencoder Single-cell data integration Proteomics data CITE-seq dataset

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Breast Cancer Subtypes with Convolutional Neural Networks 1

Early Detection of Breast Cancer Subtypes with Convolutional...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Kadam, Bhagyashree Swapnil Dewangan, Leelkanth Parida, Prasanta Kumar Chaterjee, Tanushree Nahak, Kirti Sadashiv, Ebhad Swagat Sinhgad Institute of Technology and Science Narhe Pune It Department India Swangi Dept of Computer Science & Engineering Wardha India Kiit University Dept of Computer Science & Engineering Odisha Bhubaneswar751024 India Raipur Institute of Technology Department of Biotechnology Raipur India Kalinga University Dept of Computer Science & Engineering Chhattisgarh Raipur India Trinity Academy of Engineering Department of Engineering Science Kondhwa Pune India

ISBN: (纸本)9798350330915

Breast cancer continues to be a major worldwide health issue, demanding accurate subtype categorization for personalized treatment approaches. In order to accurately identify subtypes, this work introduces a unique hybrid classifier that uses multi-modal data integration as well as cutting-edge machine learning algorithms. The model uses a Convolutional Neural Network (CNN) for image-based feature extraction alongside machine learning techniques for genomic and clinical features, combining mammographic, histopathological, genomic, and clinical data. The interpretative framework, which depends on an interpretivist philosophy, makes it less difficult to comprehend subtype discrimination on a more in-depth level. With an overall accuracy of 92.5% across HER2-positive, estrogen receptor-positive, and triple-negative subtypes, the results clearly demonstrate the hybrid classifier's better performance. The model's sensitivity and specificity ratings regularly outperformed those of existing techniques, demonstrating its aptitude for picking up on fine subtype distinctions. Particularly, the classifier demonstrated a low incidence of false positives, which is critical for reducing pointless interventions. Key genetic markers, physical traits, and hormone receptor status have been recognized as important discriminators employing feature importance analysis. These discoveries broaden the understanding of the biological foundations of each subtype. The study offers a useful tool for accurate breast cancer detection and treatment planning in clinical practice. The hybrid classifier's integrative methodology makes use of several data sources in order to provide a thorough understanding of breast cancer subtypes. This work lays the groundwork for future oncology and multi-modal data analysis studies, with potential implications in personalized therapy and other cancer types. There is still much more to discover about ethical issues, model generalization, and therapeutic use in th

关键词： Breast Cancer Subtype Classification Convolutional Neural Networks (CNNs) Interpretivism Philosophy multi-modal data integration Personalized Treatment Strategies

来源：评论

学校读者我要写书评

暂无评论

Integrating OpenStreetMap tags for efficient LiDAR point cloud classification using graph neural networks

引用

INTERNATIONAL JOURNAL OF DIGITAL EARTH 2024年第1期17卷

作者： Chen, Yanming Li, Guoli Liu, Xiaoqiang Shen, Yueqian Li, Jia Tian, Qin Hohai Univ Sch Earth Sci & Engn Nanjing Peoples R China Minist Nat Resources Shenzhen Data Management Ctr Planning & Nat Resour Key Lab Urban Land Resources Monitoring & Simulat Shenzhen Peoples R China Hohai Univ Jiangsu Prov Engn Res Ctr Water Resources & Enviro Nanjing Peoples R China Chinese Acad Sci Inst Bot State Key Lab Vegetat & Environm Change Beijing Peoples R China MNR Key Lab Spatial Temporal Big Data Anal & Applicat Shanghai Peoples R China

The urban environment exhibits significant vertical variations, Light Detection and Ranging (LiDAR) point cloud classification can provide insights for the 3D morphology of the urban environment. Introducing the adjacency relationships between urban objects can enhance the accuracy of LiDAR point cloud classification. Graph Neural Network (GNN) is a popular architecture to infer the labels of urban objects by utilizing adjacency relationships. However, existing methods ignored the power of the known labels of urban objects, such as crowd-sourced tagged labels from OpenStreetMap (OSM) data, in the inferring process. Therefore, this study proposes a strategy introduces OSM data into GNN for LiDAR point cloud classification. First, we perform an over-segmentation of the LiDAR point cloud to obtain superpoints, which act as basic elements for constructing superpoint adjacency graphs. Second, PointNet is applied to embed superpoint features and edge features are generated using these superpoint features. Finally, OSM data is associated with some part of superpoints and incorporated into the GNN to update the embedded features of superpoints. The results demonstrate that the GNN with OSM data significantly improves the classification accuracy of original GNN. The improvement highlights taking advantage of crowd-sourced geoinformation in LiDAR point cloud classification for understanding 3D urban landscape.

关键词： LiDAR point cloud classification OpenStreetMap data Graph neural networks multi-modal data integration Prior knowledge

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning framework for accurate melanoma diagnosis integrating imaging and genomic data for improved patient outcomes

引用

SKIN RESEARCH AND TECHNOLOGY 2024年第6期30卷 e13770页

作者： Kiran, Ajmeera Narayanasamy, Navaprakash Ramesh, Janjhyam Venkata Naga Ahmad, Mohd Wazih MLR Inst Technol Dept Comp Sci & Engn Hyderabad Telangana India Saveetha Inst Med & Tech Sci SIMATS Saveetha Sch Engn Chennai India Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram Andhra Pradesh India Adama Sci & Technol Univ ASTU Chair Intelligent Syst SIG Adama Ethiopia

BackgroundMelanoma is one of the most malignant forms of skin cancer, with a high mortality rate in the advanced stages. Therefore, early and accurate detection of melanoma plays an important role in improving patients' prognosis. Biopsy is the traditional method for melanoma diagnosis, but this method lacks reliability. Therefore, it is important to apply new methods to diagnose melanoma *** study presents a new approach to classify melanoma using deep neural networks (DNNs) with combined multiple modal imaging and genomic data, which could potentially provide more reliable diagnosis than current medical methods for *** built a dataset of dermoscopic images, histopathological slides and genomic profiles. We developed a custom framework composed of two widely established types of neural networks for analysing image data Convolutional Neural Networks (CNNs) and networks that can learn graph structure for analysing genomic data-Graph Neural Networks. We trained and evaluated the proposed framework on this *** developed multi-modal DNN achieved higher accuracy than traditional medical approaches. The mean accuracy of the proposed model was 92.5% with an area under the receiver operating characteristic curve of 0.96, suggesting that the multi-modal DNN approach can detect critical morphologic and molecular features of melanoma beyond the limitations of traditional AI and traditional machine learning approaches. The combination of cutting-edge AI may allow access to a broader range of diagnostic data, which can allow dermatologists to make more accurate decisions and refine treatment strategies. However, the application of the framework will have to be validated at a larger scale and more clinical trials need to be conducted to establish whether this novel diagnostic approach will be more effective and feasible.

关键词： convolutional neural networks (CNNs) deep learning genomic data graph neural networks (GNNs) imaging data melanoma multi-modal data integration

来源：评论

学校读者我要写书评

暂无评论

Confound modelling in UK Biobank brain imaging

引用

NEUROIMAGE 2021年 224卷 117002-117002页

作者： Alfaro-Almagro, Fidel McCarthy, Paul Afyouni, Soroosh Andersson, Jesper L. R. Bastiani, Matteo Miller, Karla L. Nichols, Thomas E. Smith, Stephen M. Univ Oxford Nuffield Dept Clin Neurosci FMRIB Wellcome Ctr Integrat Neuroimaging Oxford England Univ Oxford Big Data Inst Oxford England Univ Nottingham Sir Peter Mansfield Imaging Ctr Sch Med Nottingham England Univ Nottingham NIHR Biomed Res Ctr Nottingham England

Dealing with confounds is an essential step in large cohort studies to address problems such as unexplained variance and spurious correlations. UK Biobank is a powerful resource for studying associations between imaging and non-imaging measures such as lifestyle factors and health outcomes, in part because of the large subject numbers. However, the resulting high statistical power also raises the sensitivity to confound effects, which therefore have to be carefully considered. In this work we describe a set of possible confounds (including non-linear effects and interactions that researchers may wish to consider for their studies using such data). We include descriptions of how we can estimate the confounds, and study the extent to which each of these confounds affects the data, and the spurious correlations that may arise if they are not controlled. Finally, we discuss several issues that future studies should consider when dealing with confounds.

关键词： Epidemiological studies Image analysis Confounds multi-modal data integration Big data imaging data modelling Statistica l modelling Machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：