让病理模型更稳定：通过新损失函数减少设备差异干扰。
Enabling clinical use of foundation models for computational pathology
- 训练时引入鲁棒性损失，抑制扫描仪和预处理带来的干扰
- 在6155名患者、27042张切片上测试，分类准确率提升
- 无需重训基础模型，适合临床部署的实用型系统开发
计算病理学中的基础模型有望推动高性能、泛化能力强的深度学习系统发展。然而，当前基础模型不仅捕捉生物相关特征，还包含预处理和扫描仪相关的变异，导致下游任务模型预测偏差。本文提出在下游模型训练中引入新型鲁棒性损失，显著降低对技术变异性的影响。通过一个精心设计的综合性实验设置，使用来自6,155名患者的27,042张全幻灯片图像，从8个知名病理基础模型中训练数千个模型。该方法在大幅提高鲁棒性的同时，聚焦于生物相关特征，提升了分类准确率。该方案无需重新训练基础模型，即可缓解其鲁棒性不足的问题，使模型更适用于真实临床场景。
原文摘要 · Abstract (English)
Foundation models for computational pathology are expected to facilitate the development of high-performing, generalisable deep learning systems. However, in addition to biologically relevant features, current foundation models also capture pre-analytic and scanner-specific variation that bias the predictions made by downstream task-specific models trained on these features. Here we show that introducing novel robustness losses during downstream model training reduces sensitivity to technical variability. A purpose-designed comprehensive experimentation setup with 27,042 whole-slide images from 6,155 patients is used to train thousands of models from the features of eight well-known foundation models for computational pathology. In addition to a substantial improvement in robustness, our approach improves classification accuracy by focusing on biologically relevant features. It mitigates robustness limitations of foundation models for computational pathology without retraining the foundation models themselves, enabling development of models that are more suitable in real-world clinical use.
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。