探究病理基础模型对同源重组缺陷的回归预测影响
Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency
AI总结：
本研究探讨了病理基础模型在预测同源重组缺陷评分中的影响，通过实验发现基于基础模型的模型在预测准确性方面优于基线，并提出了缓解数据不平衡的上采样策略。
摘要：
在计算病理学的多个领域中，预训练于大规模病理数据的基础模型已取得了巨大成功，但它们对回归生物标志物预测的影响仍处于探索阶段。在本工作中，我们系统地评估了病理基础模型在回归任务中的表现，通过预测同源重组缺陷（HRD）评分——一种对个性化癌症治疗至关重要的生物标志物。在多个实例学习框架中，我们使用五种最先进的基础模型从整个切片图像（WSI）中提取像素级特征，并评估其与基于对比学习的特征相比的影响。模型被训练以根据这些提取的特征，在乳腺、子宫内膜和肺癌队列中预测连续的HRD评分。广泛的实验表明，基于基础模型特征训练的模型在预测准确性和泛化能力方面均优于基线，同时在基础模型之间表现出系统性差异。此外，我们提出了一种基于分布的上采样策略，以缓解这些数据集中的目标不平衡问题，显著提高了对少数但临床重要的患者群体的召回率和平衡准确率。此外，我们通过消融研究探讨了不同采样策略和实例袋大小的影响。我们的结果强调了大规模病理预训练在更精确和可转移的回归生物标志物预测中的优势，展示了其在推动人工智能驱动的精准肿瘤学中的潜力。
英文摘要：
Foundation models pretrained on large-scale histopathology data have found great success in various fields of computational pathology, but their impact on regressive biomarker prediction remains underexplored. In this work, we systematically evaluate histopathological foundation models for regression-based tasks, demonstrated through the prediction of homologous recombination deficiency (HRD) score - a critical biomarker for personalized cancer treatment. Within multiple instance learning frameworks, we extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models, and evaluate their impact compared to contrastive learning-based features. Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts from two public medical data collections. Extensive experiments demonstrate that models trained on foundation model features consistently outperform the baseline in terms of predictive accuracy and generalization capabilities while exhibiting systematic differences among the foundation models. Additionally, we propose a distribution-based upsampling strategy to mitigate target imbalance in these datasets, significantly improving the recall and balanced accuracy for underrepresented but clinically important patient populations. Furthermore, we investigate the impact of different sampling strategies and instance bagsizes by ablation studies. Our results highlight the benefits of large-scale histopathological pretraining for more precise and transferable regressive biomarker prediction, showcasing its potential to advance AI-driven precision oncology.
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。
