Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging.
Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging.
复制标题
DOI：
10.1145/3368555.3384468
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Ré C
中科院分区：
文献类型：
--
作者：
Oakden-Rayner L;Dunnmon J;Carneiro G;Ré C
用于医学图像分析的机器学习模型通常在训练或测试期间未识别的重要子集上表现不佳。例如，癌症检测模型的总体性能可能很高，但该模型可能仍然始终错过罕见但侵袭性的癌症亚型。我们把这个问题称为隐藏分层，并观察到它是由于不完全描述数据集中有意义的变化而产生的。虽然隐藏分层可以大大降低机器学习模型的临床疗效，但其影响仍然难以衡量。在这项工作中，我们评估了几种可能的技术来测量隐藏的分层效应的效用，并通过对CIFAR-100基准数据集和多个真实世界的医学成像数据集的合成实验来表征这些效应。使用这些测量技术，我们发现有证据表明，隐藏分层可能发生在患病率低、标签质量低、微妙的区别特征或虚假相关性的未识别成像子集中，并且它可能导致临床重要子集的相对性能差异超过20%。最后，我们讨论了我们的研究结果的临床意义，并建议隐藏分层的评估应该是医学成像中任何机器学习部署的关键组成部分。
Machine learning models for medical image analysis often suffer from poor performance on important subsets of a population that are not identified during training or testing. For example, overall performance of a cancer detection model may be high, but the model may still consistently miss a rare but aggressive cancer subtype. We refer to this problem as hidden stratification, and observe that it results from incompletely describing the meaningful variation in a dataset. While hidden stratification can substantially reduce the clinical efficacy of machine learning models, its effects remain difficult to measure. In this work, we assess the utility of several possible techniques for measuring hidden stratification effects, and characterize these effects both via synthetic experiments on the CIFAR-100 benchmark dataset and on multiple real-world medical imaging datasets. Using these measurement techniques, we find evidence that hidden stratification can occur in unidentified imaging subsets with low prevalence, low label quality, subtle distinguishing features, or spurious correlates, and that it can result in relative performance differences of over 20% on clinically important subsets. Finally, we discuss the clinical implications of our findings, and suggest that evaluation of hidden stratification should be a critical component of any machine learning deployment in medical imaging.