Pontalba Justin Tyler, Gwynne-Timothy Thomas, David Ephraim, Jakate Kiran, Androutsos Dimitrios, Khademi April
Image Analysis in Medicine Lab (IAMLAB), Ryerson University, Toronto, ON, Canada.
Pathcore Inc., Toronto, ON, Canada.
Front Bioeng Biotechnol. 2019 Nov 1;7:300. doi: 10.3389/fbioe.2019.00300. eCollection 2019.
Image analysis tools for cancer, such as automatic nuclei segmentation, are impacted by the inherent variation contained in pathology image data. Convolutional neural networks (CNN), demonstrate success in generalizing to variable data, illustrating great potential as a solution to the problem of data variability. In some CNN-based segmentation works for digital pathology, authors apply color normalization (CN) to reduce color variability of data as a preprocessing step prior to prediction, while others do not. Both approaches achieve reasonable performance and yet, the reasoning for utilizing this step has not been justified. It is therefore important to evaluate the necessity and impact of CN for deep learning frameworks, and its effect on downstream processes. In this paper, we evaluate the effect of popular CN methods on CNN-based nuclei segmentation frameworks.
用于癌症的图像分析工具，如自动细胞核分割，会受到病理图像数据中固有变异的影响。卷积神经网络（CNN）在泛化到可变数据方面取得了成功，显示出作为解决数据变异性问题的一种解决方案的巨大潜力。在一些基于CNN的数字病理学分割工作中，作者在预测前将颜色归一化（CN）作为预处理步骤来减少数据的颜色变异性，而另一些作者则不这样做。两种方法都取得了合理的性能，然而，使用这一步骤的理由尚未得到证实。因此，评估CN对于深度学习框架的必要性和影响及其对下游流程的作用非常重要。在本文中，我们评估了流行的CN方法对基于CNN的细胞核分割框架的影响。
