H2-Surv：面向生存预测的层级双曲多模态表征学习
H2-Surv: Hierarchical Hyperbolic Multimodal Representation Learning for Survival Prediction
把全切片图像的多级结构（patch→WSI→患者）与基因组层级一起嵌入共享双曲空间，并用序数对比损失保持风险分数的连续性；做病理图像层级建模或需要保留样本间细粒度序关系时，这套双曲层级编码加序数对比目标可直接迁移。
原文依据 maps multimodal features into a shared hyperbolic space and explicitly encodes intra-modal and inter-modal hierarchies
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论结合组织病理图像与基因组数据的多模态学习用于癌症生存预测是一个有前景的研究方向。然而，现有方法仍存在两个关键局限。第一，大多数方法在欧氏特征空间中运作，难以刻画组织病理学中从图像块到全切片图像再到患者、以及基因组学中从基因到通路再到患者的内在层级结构。第二，它们通常将生存时间离散化为粗糙的风险区间，忽略了同一区间内样本之间细粒度的序数关系，因而无法捕捉生存结局的连续排序特性。为解决上述问题，我们提出 H2-Surv，一个用于生存预测的双曲层级多模态学习框架。H2-SurvNet 首先采用双曲层级信息建模（H2IM）模块，将多模态特征映射到共享双曲空间，并显式编码跨图像块、全切片图像、患者、基因与通路的模态内与模态间层级结构。在此表征之上，我们设计了时序序数对比学习（TOCL）模块，通过对比目标施加序数风险排序，对生存结局的时序演进进行建模，从而促进所学风险分数的连续性。在 TCGA、CPTAC 与 NLST 的异构队列上的大量实验表明，H2-SurvNet 持续优于最优的多模态生存预测方法，并在多样数据分布下展现出强鲁棒性与泛化能力。源代码将在论文录用后发布。
英文原文摘要 1749 字符
Cancer survival prediction through multimodal learning that combines histopathology images with genomic data represents a promising research direction. However, current approaches still suffer from two key limitations. First, most methods operate in a Euclidean feature space, which makes it difficult to capture the intrinsic hierarchies in histopathology, where information is organized from patches to whole-slide images to patients, and in genomics, where it progresses from genes to pathways to patients. Second, they typically discretize survival times into coarse risk intervals, neglecting fine-grained ordinal relationships among samples within the same interval and thus failing to capture the continuous ranking characteristics of survival outcomes.To address these issues, we propose \ourmethod, a hyperbolic hierarchical multimodal learning framework for survival prediction. H2-SurvNet first employs a **hyperbolic hierarchical information modeling** (H2IM) module that maps multimodal features into a shared hyperbolic space and explicitly encodes intra-modal and inter-modal hierarchies across patches, WSIs, patients, genes, and pathways. On top of this representation, we design a **Temporal Ordinal Contrastive learning** (TOCL) module that models the temporal progression of survival outcomes by enforcing ordinal risk ordering through contrastive objectives, thereby promoting continuity in the learned risk scores.Extensive experiments on heterogeneous cohorts from TCGA, CPTAC, and NLST demonstrate that H2-SurvNet consistently outperforms state-of-the-art multimodal survival prediction methods and exhibits strong robustness and generalization across diverse data distributions. Source code will be released upon acceptance.