Application of Graph Neural Networks for biomedical data
الملخص
The rapid advancement of biomedical data collection technology has enabled compre- hensive data analysis, but traditional meth- ods often struggle with complex and irregu- lar data. While Convolutional Neural Net- works (CNNs) have improved biomedical im- age analysis, they are less effective for non- Euclidean data like graphs. In contrast, Graph Neural Networks (GNNs) offer a promising so- lution by capturing complex relationships and topological structures in graph data. This final work provides an overview of GNN applications and challenges in biomedical data analysis. Core GNN models, including Graph Convolutional Networks (GCN), Graph Atten- tion Networks (GAT), and GraphSAGE, are explained and then implemented through two detailed case studies, demonstrating their fea- sibility and effectiveness. Overall, this work highlights the potential of GNNs in bioinformatics, providing robust sup- port for analyzing complex biomedical data and offering insights for future research and development in this field
الكلمات المفتاحية
غير متوفر
التخصصات
رسائل وأطاريح مشابهة
- Graph Neural Networks: Techniques and Applications Zhiqian Chen · 2020
- On the Adversarial Robustness of Graph Neural Networks Sofiane Ennadir · Dalarna University Library · 2026
- Spiking graph neural networks: A survey Sathvik Murli · Rutgers University · 2026
- The expressivity and explainability of graph neural networks Matthew Morris · University of Oxford · 2026
- Neural network optimization of Speckle-based phase-contrast X-ray imaging for mammography applications Sofía Naranjo Barros · 2025
- Convolutional neural networks for mammograph analysis A. Pereira · 2025
