发表机构
Tata Memorial Centre-ACTREC（塔塔纪念中心-ACTREC）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出状态感知交互多实例学习，通过保留生物标志物特异性表征并建模交互，在结直肠癌和肺腺癌中提升罕见联合分子表型预测精度。
AI 中文摘要
联合分子表型预测因联合阳性人群稀少以及不同分子状态间组织学特征重叠而变得复杂。现有计算病理学方法通常独立预测生物标志物或将联合阳性表型视为二元终点。独立预测无法建模生物标志物特异性组织学表征之间的交互，而二元联合预测则将双阴性和两种单阳性配置合并为单一阴性类别。我们提出状态感知交互多实例学习（State-Aware Interaction MIL），这是一种弱监督方法，保留生物标志物特异性组织学表征，建模其交互，并监督完整的四态分子配置。我们使用冻结的UNI2-h和CONCH病理学基础模型表征，评估了所提方法在结直肠癌中联合BRAF+/MSI+预测和肺腺癌中EGFR+/TP53+预测的性能。使用UNI2-h时，状态感知交互MIL在结直肠癌（联合阳性患病率6.8%）中达到平均精度0.5566，而NaiveMTL为0.5161；在肺腺癌（联合阳性患病率8.6%）中达到0.2784，而IndependentPair为0.2525。使用CONCH时，状态感知方法在结直肠癌中达到平均精度0.4410，而DirectJoint为0.3932；在肺腺癌中达到0.1659，而DirectJoint为0.1226。这些结果表明，病理学基础模型表征包含用于罕见联合分子表型的预测信息，且在结构化分子状态框架内保留生物标志物特异性表征可改善从组织病理学预测这些表型的性能。
英文摘要
Joint molecular phenotype prediction is complicated by small joint-positive populations and overlapping histological features across alternative molecular states. Existing computational pathology approaches typically predict biomarkers independently or formulate the joint-positive phenotype as a binary endpoint. Independent prediction does not model interactions between biomarker-specific histological representations, whereas binary joint prediction collapses the double-negative and two single-positive configurations into a single negative class. We propose State-Aware Interaction MIL, a weakly supervised method that preserves biomarker-specific histological representations, models their interaction, and supervises the complete four-state molecular configuration. We evaluate the proposed approach for joint BRAF+/MSI+ prediction in colorectal cancer and EGFR+/TP53+ prediction in lung adenocarcinoma using frozen UNI2-h and CONCH pathology foundation-model representations. With UNI2-h, State-Aware Interaction MIL achieved an average precision of 0.5566 in colorectal cancer (joint-positive prevalence 6.8%) compared with 0.5161 for NaiveMTL, and 0.2784 in lung adenocarcinoma (joint-positive prevalence 8.6%) compared with 0.2525 for IndependentPair. With CONCH, State-Aware achieved an average precision of 0.4410 compared with 0.3932 for DirectJoint in colorectal cancer and 0.1659 compared with 0.1226 for DirectJoint in lung adenocarcinoma. These results indicate that pathology foundation-model representations contain predictive information for rare joint molecular phenotypes and that preserving biomarker-specific representations within a structured molecular-state formulation can improve prediction of these phenotypes from histopathology.
CommentsAccepted at the NeurIPS 2026 Workshop on AI at Scale for Clinical Impact (ASCI): Cancer Pathology Foundation Models
