Border Samuel P, Ginley Brandon, Tomaszewski John E, Sarder Pinaki
Department of Pathology & Anatomical Sciences University at Buffalo.
Proc SPIE Int Soc Opt Eng. 2022 Feb-Mar;12039. doi: 10.1117/12.2613503. Epub 2022 Apr 4.
The incorporation of automated computational tools has a great amount of potential to positively influence the field of pathology. However, pathologists and regulatory agencies are reluctant to trust the output of complex models such as Convolutional Neural Networks (CNNs) due to their usual implementation as black-box tools. Increasing the interpretability of quantitative analyses is a critical line of research in order to increase the adoption of modern Machine Learning (ML) pipelines in clinical environments. Towards that goal, we present , a Graphical User Interface (GUI) designed to facilitate quantitative assessments of datasets of annotated histological compartments. Additionally, we introduce the use of hand-engineered feature visualizations to highlight regions within each structure that contribute to particular feature values. These feature visualizations can then be paired with feature hierarchy determinations in order to view which regions within an image are significant to a particular sub-group within the dataset. As a use case, we analyzed a dataset of old and young mouse kidney sections with glomeruli annotated. We highlight some of the functional components within that allow non-computational experts to efficiently navigate a new dataset as well as allowing for easier transition to downstream computational analyses.
自动化计算工具的融入有很大潜力对病理学领域产生积极影响。然而，病理学家和监管机构不愿信任诸如卷积神经网络（CNN）等复杂模型的输出结果，因为它们通常作为黑箱工具来使用。提高定量分析的可解释性是一项关键的研究方向，以便在临床环境中增加现代机器学习（ML）流程的采用率。为了实现这一目标，我们展示了一个图形用户界面（GUI），其设计目的是便于对带注释的组织学区域数据集进行定量评估。此外，我们引入了手工设计的特征可视化方法，以突出每个结构中对特定特征值有贡献的区域。然后，这些特征可视化可以与特征层次确定相结合，以便查看图像中的哪些区域对数据集中的特定子组具有重要意义。作为一个用例，我们分析了一个带有注释肾小球的老年和幼年小鼠肾脏切片数据集。我们突出了其中一些功能组件，这些组件使非计算专家能够有效地浏览新数据集，并便于向下游计算分析过渡。
