融合多个病理大模型知识，提升结直肠癌生存预测准确率
MorphDistill: Distilling Unified Morphological Knowledge from Pathology Foundation Models for Colorectal Cancer Survival Prediction
- 通过多教师关系蒸馏，从十多个大模型中提取共性形态特征
- 在424例患者数据上实现0.68的AUC，较最优基线提升8%
- 模型轻量且泛化性强，适合临床实用与跨队列推广
结直肠癌（CRC）仍是全球癌症致死主因之一。精准生存预测对治疗分层至关重要，但现有病理大模型常忽略器官特异性特征。本文提出MorphDistill，一种两阶段框架，将多个病理大模型的互补知识蒸馏为一个紧凑的、针对结直肠癌的编码器。第一阶段，学生编码器通过无维度依赖的多教师关系蒸馏，并结合监督对比正则化，在大规模结直肠数据集上训练，保留了来自十个基础模型的样本间关系，无需显式特征对齐。第二阶段，编码器从全切片图像中提取局部特征，通过注意力加权的多实例学习进行聚合，预测五年生存率。在Alliance/CALGB 89803队列（n=424，III期CRC）上，MorphDistill达到AUC 0.68（SD 0.08），相比最强基线（AUC 0.63）相对提升约8%；同时获得C-index 0.661，风险比2.52（95% CI: 1.73–3.65），优于所有基线。在外部TCGA队列（n=562）上，C-index达0.628，表明其在不同数据集间具有强泛化能力，且在各类临床亚组中表现稳健。结论：MorphDistill通过整合多个基础模型的知识，构建统一的特定任务编码器，为计算病理学中的预后建模提供高效策略，具备向更广肿瘤领域拓展的潜力。需在更多队列和疾病分期中进一步验证。
原文摘要 · Abstract (English)
Background: Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide. Accurate survival prediction is essential for treatment stratification, yet existing pathology foundation models often overlook organ-specific features critical for CRC prognostication. Methods: We propose MorphDistill, a two-stage framework that distills complementary knowledge from multiple pathology foundation models into a compact CRC-specific encoder. In Stage I, a student encoder is trained using dimension-agnostic multi-teacher relational distillation with supervised contrastive regularization on large-scale colorectal datasets. This preserves inter-sample relationships from ten foundation models without explicit feature alignment. In Stage II, the encoder extracts patch-level features from whole-slide images, which are aggregated via attention-based multiple instance learning to predict five-year survival. Results: On the Alliance/CALGB 89803 cohort (n=424, stage III CRC), MorphDistill achieves an AUC of 0.68 (SD 0.08), an approximately 8% relative improvement over the strongest baseline (AUC 0.63). It also attains a C-index of 0.661 and a hazard ratio of 2.52 (95% CI: 1.73-3.65), outperforming all baselines. On an external TCGA cohort (n=562), it achieves a C-index of 0.628, demonstrating strong generalization across datasets and robustness across clinical subgroups. Conclusion: MorphDistill enables task-specific representation learning by integrating knowledge from multiple foundation models into a unified encoder. This approach provides an efficient strategy for prognostic modeling in computational pathology, with potential for broader oncology applications. Further validation across additional cohorts and disease stages is warranted.
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。