跨癌种生存预测中，多模态模型反而不如单模态，新方法提升泛化能力。
Single Domain Generalization for Multimodal Cross-Cancer Prognosis via Dirac Rebalancer and Distribution Entanglement
- 用稀疏狄拉克重平衡模块增强弱模态信号，缓解强模态主导问题。
- 通过癌症感知分布纠缠融合形态与基因表达特征，提升跨癌种适应性。
- 首次提出单癌种训练跨癌种泛化的评估任务，适合临床实用场景。
深度学习在整合多模态数据进行生存预测方面表现优异，但现有方法主要针对单一癌种，忽视跨癌种泛化挑战。本文首次揭示：尽管临床需求迫切，多模态预后模型在跨癌种场景下的泛化性能往往劣于单模态模型。为此，我们提出新任务——跨癌种单域泛化多模态预后，评估仅在一种癌种上训练的模型能否泛化至未见癌种。识别出两大关键挑战：弱模态特征退化与无效多模态融合。为此引入两个即插即用模块：稀疏狄拉克信息重平衡（SDIR）和癌症感知分布纠缠（CADE）。SDIR通过伯努利稀疏化与狄拉克启发式稳定机制，抑制强模态主导，增强弱模态信号。CADE在潜在空间融合局部形态学线索与全局基因表达，合成目标域分布。在包含四种癌种的基准数据集上实验显示，该方法显著优于基线，为实际、鲁棒的跨癌种多模态预后奠定基础。代码已开源：https://github.com/HopkinsKwong/MCCSDG
原文摘要 · Abstract (English)
Deep learning has shown remarkable performance in integrating multimodal data for survival prediction. However, existing multimodal methods mainly focus on single cancer types and overlook the challenge of generalization across cancers. In this work, we are the first to reveal that multimodal prognosis models often generalize worse than unimodal ones in cross-cancer scenarios, despite the critical need for such robustness in clinical practice. To address this, we propose a new task: Cross-Cancer Single Domain Generalization for Multimodal Prognosis, which evaluates whether models trained on a single cancer type can generalize to unseen cancers. We identify two key challenges: degraded features from weaker modalities and ineffective multimodal integration. To tackle these, we introduce two plug-and-play modules: Sparse Dirac Information Rebalancer (SDIR) and Cancer-aware Distribution Entanglement (CADE). SDIR mitigates the dominance of strong features by applying Bernoulli-based sparsification and Dirac-inspired stabilization to enhance weaker modality signals. CADE, designed to synthesize the target domain distribution, fuses local morphological cues and global gene expression in latent space. Experiments on a four-cancer-type benchmark demonstrate superior generalization, laying the foundation for practical, robust cross-cancer multimodal prognosis. Code is available at https://github.com/HopkinsKwong/MCCSDG
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。