MorphDistill: 从病理基础模型中提取统一形态学知识以预测结直肠癌生存率
MorphDistill: Distilling Unified Morphological Knowledge from Pathology Foundation Models for Colorectal Cancer Survival Prediction
AI总结：
本文提出MorphDistill框架，通过多病理基础模型提取互补知识，构建紧凑的结直肠癌特异性编码器，提升生存预测性能。
摘要：
背景：结直肠癌（CRC）仍是全球癌症相关死亡的主要原因。准确的生存预测对于治疗分层至关重要，但现有病理基础模型往往忽视关键的器官特异性特征。方法：我们提出了MorphDistill，一个两阶段框架，通过从多个病理基础模型中提取互补知识，构建紧凑的CRC特异性编码器。在第一阶段，学生编码器通过无维度关注的多教师关系蒸馏和监督对比正则化在大规模结直肠数据集上进行训练。这保留了来自十个基础模型的样本间关系，而无需显式特征对齐。在第二阶段，编码器从全滑片图像中提取补丁级特征，通过基于注意力的多实例学习进行聚合，以预测五年生存率。结果：在Alliance/CALGB 89803队列（n=424，III期CRC）上，MorphDistill实现了AUC为0.68（SD 0.08），比最强基线（AUC 0.63）提高了约8%。它还达到了C指数为0.661和危险比为2.52（95% CI: 1.73-3.65），优于所有基线。在外部TCGA队列（n=562）上，其C指数为0.628，展示了跨数据集的强泛化能力和跨临床亚组的鲁棒性。结论：MorphDistill通过整合多个基础模型的知识到统一编码器中，实现了任务特定的表示学习。这种方法为计算病理学中的预后建模提供了一种高效策略，具有更广泛的应用前景。进一步在更多队列和疾病阶段上验证是必要的。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
