发表机构
Universitat Politècnica de Catalunya - BarcelonaTech (UPC); IRB Lleida（加泰罗尼亚理工大学; 莱里达生物医学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出CCMIL框架，通过跨模态对比学习从H&E切片直接检索免疫治疗相关分子特征，无需基因组测序，实现可解释的检索与分类预筛选。
AI 中文摘要
胃腺癌是癌症死亡的主要原因之一。尽管已提出“炎症型/非炎症型”亚型来预测免疫治疗反应，但其识别依赖于昂贵的10基因RNA特征。我们提出了一种跨模态对比多实例学习（CCMIL）框架，用于跨模态检索，直接从标准苏木精-伊红（H&E）染色切片中推断这些分子特征。通过利用监督对比目标，CCMIL将视觉形态模式与分子表型对齐到共享潜在空间中。这建立了一个可解释的按病例检索引擎，使病理学家能够查询整张切片图像，以呈现转录组学上相似的邻域，并在推理时无需基因组测序即可近似RNA特征。我们的结果表明，这种检索优先的方法捕捉了肿瘤炎症的连续表型谱，并产生了临床可解释的注意力热图。此外，学习到的表示还支持有竞争力的下游分类，提供了一种实用的分子预筛选策略。
英文摘要
Gastric Adenocarcinoma is a leading cause of cancer mortality. Although "Inflamed/Non-Inflamed" subtypes have been proposed to predict immunotherapy response, their identification relies on a costly 10-gene RNA signature. We propose a Cross-modal Contrastive Multiple Instance Learning (CCMIL) framework for cross-modal retrieval, imputing these molecular signatures directly from standard Hematoxylin & Eosin (H&E) slides. By leveraging a supervised contrastive objective, CCMIL aligns visual morphological patterns with molecular phenotypes into a shared latent space. This establishes an interpretable search-by-case retrieval engine, enabling pathologists to query a whole slide image to surface transcriptomically coherent neighbors and approximate RNA signatures without genomic sequencing at inference. Our results demonstrate that this retrieval-first approach captures the continuous phenotypic spectrum of tumor inflammation and yields clinically interpretable attention heatmaps. Furthermore, the learned representation also supports competitive downstream classification, providing a practical molecular pre-screening strategy.
CommentsAccepted to MICCAI 2026 CaPTion Workshop
