Resolving challenges in deep learning-based analyses of histopathological images using explanation methods
Resolving challenges in deep learning-based analyses of histopathological images using explanation methods
复制标题
DOI：
10.1038/s41598-020-62724-2
复制
发表时间：
2020-04-14
影响因子：
4.6
通讯作者：
Binder, Alexander
中科院分区：
文献类型：
--
作者：
Hagele, Miriam;Seegerer, Philipp;Binder, Alexander
深度学习由于其高预测质量最近在数字病理学中越来越受欢迎。然而，医疗领域需要解释和洞察力，以更好地理解标准的定量性能评估。最近，出现了许多解释方法。这项工作展示了这些解释方法生成的热图如何解决基于深度学习的数字组织病理学分析中遇到的常见挑战。我们阐述了偏见，这是典型的固有的组织病理学图像数据。在公开的各种肿瘤实体的苏木精-伊红染色图像中肿瘤组织区分的二进制分类任务中，我们研究了三种类型的偏差：（1）影响整个数据集的偏差，（2）偶然与类标签相关的偏差和（3）采样偏差。虽然标准分析侧重于补丁级评估，但我们提倡像素级热图，它提供了一种更精确和通用的诊断工具。这种见解不仅有助于检测，而且有助于消除常见隐藏偏见的影响，从而提高数据集内和数据集之间的泛化能力。例如，当减少标签偏倚时，我们可以看到受试者工作特征（ROC）曲线下面积改善5%的趋势。因此，解释技术被证明是一个有用的和高度相关的工具，在数字病理学的真实世界的应用程序的生命周期内的开发和部署阶段。
Deep learning has recently gained popularity in digital pathology due to its high prediction quality. However, the medical domain requires explanation and insight for a better understanding beyond standard quantitative performance evaluation. Recently, many explanation methods have emerged. This work shows how heatmaps generated by these explanation methods allow to resolve common challenges encountered in deep learning-based digital histopathology analyses. We elaborate on biases which are typically inherent in histopathological image data. In the binary classification task of tumour tissue discrimination in publicly available haematoxylin-eosin-stained images of various tumour entities, we investigate three types of biases: (1) biases which affect the entire dataset, (2) biases which are by chance correlated with class labels and (3) sampling biases. While standard analyses focus on patch-level evaluation, we advocate pixel-wise heatmaps, which offer a more precise and versatile diagnostic instrument. This insight is shown to not only be helpful to detect but also to remove the effects of common hidden biases, which improves generalisation within and across datasets. For example, we could see a trend of improved area under the receiver operating characteristic (ROC) curve by 5% when reducing a labelling bias. Explanation techniques are thus demonstrated to be a helpful and highly relevant tool for the development and the deployment phases within the life cycle of real-world applications in digital pathology.