Return
Bridging Imaging and Genomics: Domain Knowledge Guided Spatial Transcriptomics Analysis
DOI:10.1016/j.inffus.2025.103746.png)
Abstract
En 中文
• Use LLMs and curated summaries to generate informative gene representations. • Leverage vision models to extract multi-scale features from whole slide images. • Propose a multi-modal expert fusion to align gene and image features effectively. • Extensive experiments on three datasets show consistent gains over SOTA methods.
Keywords:
Spatial Transcriptomics
Computational Pathology
Large Language Model
Domain Knowledge
Multimodal Learning
Generative AI
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
15.5
Papers:
4.1K
Citations:
2.7W

