arXiv 2412.026012025-03-19cs.CV

MERGE：用于从全切片组织病理图像预测基因表达的基于多面分层图的GNN

MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images

Stony Brook University（石溪大学）；Indiana University School of Medicine（印第安纳大学医学院）

Aniruddha Ganguly, Debolina Chatterjee, Wentao Huang, Jie Zhang, Alisa Yurovsky, Travis Steele Johnson, Chao Chen

备注：: Main Paper: 8 pages, Supplementary Material: 11 pages, Figures: 19

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有全切片图像基因表达预测方法未充分利用组织位置间相互作用的问题，提出融合多面分层图与GNN的MERGE方法，还评估了ST数据平滑技术，实验显示该方法多指标优于现有最优技术。

摘要：

空间转录组学（Spatial Transcriptomics, ST）的最新进展将组织学图像与空间分辨的基因表达谱配对，使得能够基于图像块预测不同组织位置的基因表达。这为利用局部基因表达改进全切片图像（whole slide image, WSI）预测任务开辟了新可能。然而，现有方法未能充分利用不同组织位置之间的相互作用，而这种相互作用对准确的联合预测至关重要。为解决这一问题，我们提出MERGE（用于基因表达的多面分层图，Multi-faceted hiErarchical gRaph for Gene Expressions），它将多面分层图构建策略与图神经网络（graph neural networks, GNN）相结合，以提升从WSI进行基因表达预测的效果。通过基于空间特征和形态特征对组织图像块进行聚类，并纳入簇内和簇间边，我们的方法在GNN学习过程中促进了远距离组织位置之间的相互作用。作为另一项贡献，我们评估了多种缓解ST数据中伪影所需的数据平滑技术，这些伪影通常由技术缺陷导致。我们提倡采用更具生物学合理性的基因感知平滑方法。基因表达预测的实验结果表明，我们的GNN方法在多个指标上均优于现有最优技术。

英文摘要：

Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods fail to fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce MERGE (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques across multiple metrics.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。