发表机构
Technical University of Munich (TUM); Munich Center for Machine Learning (MCML); University of California, Irvine（慕尼黑工业大学; 慕尼黑机器学习中心; 加州大学尔湾分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MIST提出基因组引导的组织学注意力机制，通过基因组标记查询组织学上下文令牌实现多模态融合，在四种癌症外部队列中提升C指数，为肿瘤预后预测提供紧凑有效策略。
AI 中文摘要
多模态生存模型可以结合来自全切片图像和基因组谱的互补预后信息，但在外部队列偏移和计算复杂性的情况下，有效的融合仍然具有挑战性。为了解决这些挑战，我们提出了MIST，即基因组引导的组织学注意力的多模态生存预测。MIST将基因组特征表示为标记，并允许它们在生存预测之前查询紧凑的、基于基础模型衍生的组织学上下文标记。这种设计用组织学上下文丰富分子信息，而不是仅在最后阶段合并单独编码的模态。训练结合了离散时间生存预测与基因组特征掩蔽、WSI丢弃和配对的WSI-基因组对比对齐。在结肠癌、肾癌、肺癌和胶质母细胞瘤队列的四项外部评估中，MIST在主要比较中相对于标准融合基线提高了外部C指数。这些结果支持基因组引导的组织学注意力作为多模态肿瘤结果预测的一种紧凑且有效的策略。我们的代码可在以下网址获取：https URL。
英文摘要
Multimodal survival models can combine complementary prognostic information from whole-slide images and genomic profiles, but effective fusion remains challenging amid external cohort shift and computational complexity. To address these challenges, we propose MIST, multimodal survival prediction with genomic-guided histology attention. MIST represents genomic features as tokens and allows them to query compact foundation-model-derived histology context tokens before survival prediction. This design enriches molecular information with histology context rather than merging separately encoded modalities only at the final stage. Training combines discrete-time survival prediction with genomic feature masking, WSI dropout, and paired WSI-genomics contrastive alignment. Across four external evaluations in colon, renal, lung, and glioblastoma cohorts, MIST improves external C-index over standard fusion baselines in the primary comparisons. These results support genomic-guided histology attention as a compact and effective strategy for multimodal oncology outcome prediction. Our code is available at https://github.com/samiyavuuz/MIST .
CommentsAccepted at the COMPAYL 2026 Workshop on Computational Pathology and Multimodal Data at MICCAI 2026. 11 pages, 2 figures, 4 tables
