本文由小咖机器人翻译整理

期刊来源：Nat Med

原文链接：https://doi.org/10.1038/s41591-024-02885-z

摘要内容如下：

尽管监管机构批准的数量不断增加，但基于深度学习的计算病理学系统往往忽视了人口统计学因素对性能的影响，这可能会导致偏差。由于计算病理学已经利用了大型公共数据集，而这些数据集未能充分代表某些人口统计群体，因此这一问题变得更加重要。使用来自癌症基因组图谱（Cancer Genome Atlas）和eBrains脑肿瘤图谱（eBrains Brain Tumor Atlas）的公开可用数据以及内部患者数据，我们发现，当用于对乳腺癌和肺癌进行分型以及预测神经胶质瘤中的IDH1突变时，全玻片图像分类模型在不同人口统计群体中显示出显著的性能差异。例如，当使用常见的建模方法时，我们观察到白人和黑人患者之间的性能差距（在受试者工作特征曲线下的面积）：乳腺癌亚型为3.0%，肺癌亚型为10.9%，神经胶质瘤中IDH1突变预测为16.0%。我们发现，从自我监督的视觉基础模型中获得的更丰富的特征表示减少了组间的性能差异。这些表示提供了对较弱模型的改进，即使这些较弱模型与最先进的偏差缓解策略和建模选择相结合。然而，自我监督的视觉基础模型并不能完全消除这些差异，这突出了在计算病理学中对偏倚缓解工作的持续需求。最后，我们证明了我们的结果可以扩展到患者种族以外的其他人口统计学因素。鉴于这些发现，我们鼓励监管和政策机构将人口分层评估纳入其评估指南。

英文原文如下：

Abstracts

Despite increasing numbers of regulatory approvals, deep learning-based computational pathology systems often overlook the impact of demographic factors on performance, potentially leading to biases. This concern is all the more important as computational pathology has leveraged large public datasets that underrepresent certain demographic groups. Using publicly available data from The Cancer Genome Atlas and the EBRAINS brain tumor atlas, as well as internal patient data, we show that whole-slide image classification models display marked performance disparities across different demographic groups when used to subtype breast and lung carcinomas and to predict IDH1 mutations in gliomas. For example, when using common modeling approaches, we observed performance gaps (in area under the receiver operating characteristic curve) between white and Black patients of 3.0% for breast cancer subtyping, 10.9% for lung cancer subtyping and 16.0% for IDH1 mutation prediction in gliomas. We found that richer feature representations obtained from self-supervised vision foundation models reduce performance variations between groups. These representations provide improvements upon weaker models even when those weaker models are combined with state-of-the-art bias mitigation strategies and modeling choices. Nevertheless, self-supervised vision foundation models do not fully eliminate these discrepancies, highlighting the continuing need for bias mitigation efforts in computational pathology. Finally, we demonstrate that our results extend to other demographic factors beyond patient race. Given these findings, we encourage regulatory and policy agencies to integrate demographic-stratified evaluation into their assessment guidelines.

-----------分割线---------

点击链接：https://www.mediecogroup.com/community/user/vip/categories/ ，成为医咖会员，获取12项专属权益。