Groschner Catherine K, Choi Christina, Scott Mary C
Department of Materials Science and Engineering, University of California Berkeley, Berkeley, CA94720, USA.
Molecular Foundry, Lawrence Berkeley National Laboratory, Berkeley, CA94720, USA.
Microsc Microanal. 2021 May 6:1-8. doi: 10.1017/S1431927621000386.
In the field of transmission electron microscopy, data interpretation often lags behind acquisition methods, as image processing methods often have to be manually tailored to individual datasets. Machine learning offers a promising approach for fast, accurate analysis of electron microscopy data. Here, we demonstrate a flexible two-step pipeline for the analysis of high-resolution transmission electron microscopy data, which uses a U-Net for segmentation followed by a random forest for the detection of stacking faults. Our trained U-Net is able to segment nanoparticle regions from the amorphous background with a Dice coefficient of 0.8 and significantly outperforms traditional image segmentation methods. Using these segmented regions, we are then able to classify whether nanoparticles contain a visible stacking fault with 86% accuracy. We provide this adaptable pipeline as an open-source tool for the community. The combined output of the segmentation network and classifier offer a way to determine statistical distributions of features of interest, such as size, shape, and defect presence, enabling the detection of correlations between these features.
在透射电子显微镜领域，数据解读往往滞后于采集方法，因为图像处理方法通常必须针对单个数据集进行手动调整。机器学习为快速、准确地分析电子显微镜数据提供了一种很有前景的方法。在此，我们展示了一种灵活的两步流程，用于分析高分辨率透射电子显微镜数据，该流程使用U-Net进行分割，然后使用随机森林检测堆垛层错。我们训练的U-Net能够以0.8的Dice系数从非晶背景中分割出纳米颗粒区域，并且显著优于传统的图像分割方法。利用这些分割区域，我们随后能够以86%的准确率对纳米颗粒是否包含可见的堆垛层错进行分类。我们将这个适应性强的流程作为开源工具提供给社区。分割网络和分类器的联合输出提供了一种确定感兴趣特征（如尺寸、形状和缺陷存在情况）统计分布的方法，从而能够检测这些特征之间的相关性。
