融合病理图像与空间基因组数据，提升癌症预后预测能力
JASPR: Joint Spatial Representation learning of histology and spatial genomics for improved virtual genomic screening and clinical prognostication
- 通过跨模态重建学习联合空间表征，保留组织形态与基因表达的空间关系
- 在乳腺癌数据上实现对9248个基因的高效预测，显著优于单一模态方法
- 适合肿瘤生物标志物发现与精准医学研究者使用
近期研究表明，肿瘤的空间特性对理解疾病生物学和预测患者预后至关重要。这些空间特性正通过互补模态逐步揭示：空间转录组（ST）捕捉空间分辨的分子状态，而苏木精-伊红染色全切片图像（HE）反映组织形态。尽管已有融合方法出现，但能有效学习联合表示并整合多模态空间上下文的模型仍较缺乏。本文提出JASPR（联合空间表征学习），一种自监督深度学习框架，通过跨模态重建目标，将HE图像与ST数据融合，同时保留HE图像中的空间上下文和ST谱型的空间结构。该框架采用共享模块捕捉跨模态通用空间特征，而模态特异性专家则编码形态学与基因组数据的独特属性。我们在乳腺癌数据集上训练并验证JASPR，结果表明其学习到的联合表征显著提升了基于HE图像对9,248个基因的预测性能，并具备乳腺癌预后的判别价值。
原文摘要 · Abstract (English)
Recent studies have shown that spatial properties of tumors are critical for understanding disease biology and predicting patient outcomes. These spatial properties are increasingly uncovered through complementary modalities: spatial transcriptomics (ST) captures spatially-resolved molecular states, while hematoxylin and eosin-stained whole slide images (HE) reveal tissue morphology. While approaches are emerging to fuse these modalities, effective methods that learn not only joint representations but also incorporate spatial context across modalities are lacking. Here, we present JASPR (Joint Spatial Representation learning), a self-supervised deep learning framework that integrates HE images and ST data through a cross-modal reconstruction objective that incorporates spatial context within HE images and ST profiles. It employs shared modules to capture universal spatial properties across modalities, while modality-specific experts encode features unique to morphological and genomic data. We train and validate JASPR on breast cancer datasets, demonstrating that its learned joint representation substantially improves HE-based prediction of 9,248 genes and provides prognostic value for breast cancer outcomes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。