用基因指导图像特征对齐，提升病理切片与基因表达的匹配精度。
RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistency
- 基于排名一致性损失实现基因与图像特征跨模态对齐
- 在7个公开数据集上显著提升预测性能与对齐稳定性
- 适合做病理多模态分析、基因表达定位的研究者
空间转录组学（ST）通过映射组织内基因表达提供了关键的空间信息，有助于深入研究细胞异质性和组织结构。然而，由于固有的空间扭曲和模态特异性差异，将ST数据与组织病理图像对齐面临挑战。现有方法主要依赖直接对齐，往往无法捕捉复杂的跨模态关系。为此，我们提出一种新框架，利用基于排名的对齐损失对齐基因与图像特征，保留模态间相对相似性，实现稳健的多尺度对齐。为进一步增强对齐稳定性，采用教师-学生网络架构进行自监督知识蒸馏，作为模态内稳定性的正则项，防止图像表示在跨模态对齐过程中发生漂移。在七个公开数据集上的大量实验表明，该方法在基因表达预测、全片分类和生存分析任务中均优于现有方法，表现出更优的对齐效果与预测性能。代码已开源：https://github.com/winston52/RankByGene。
原文摘要 · Abstract (English)
Spatial transcriptomics (ST) provides essential spatial context by mapping gene expression within tissue, enabling detailed study of cellular heterogeneity and tissue organization. However, aligning ST data with histology images poses challenges due to inherent spatial distortions and modality-specific variations. Existing methods largely rely on direct alignment, which often fails to capture complex cross-modal relationships. To address these limitations, we propose a novel framework that aligns gene and image features using a ranking-based alignment loss, preserving relative similarity across modalities and enabling robust multi-scale alignment. To further enhance the alignment's stability, we employ self-supervised knowledge distillation with a teacher-student network architecture, which serves as an intra-modal stability regularizer that prevents image-representation drift during cross-modal alignment. Extensive experiments on seven public datasets that encompass gene expression prediction, slide-level classification, and survival analysis demonstrate the efficacy of our method, showing improved alignment and predictive performance over existing methods. Code is available at https://github.com/winston52/RankByGene.
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。