TEMImageNet training library and AtomSegNet deep-learning models for high-precision atom segmentation, localization, denoising, and deblurring of atomic-resolution images.
TEMImageNet training library and AtomSegNet deep-learning models for high-precision atom segmentation, localization, denoising, and deblurring of atomic-resolution images.
复制标题
DOI：
10.1038/s41598-021-84499-w
复制
发表时间：
2021-03-08
影响因子：
4.6
通讯作者：
Xin HL
中科院分区：
文献类型：
--
作者：
Lin R;Zhang R;Wang C;Yang XQ;Xin HL
高精度和鲁棒性的原子分辨率扫描透射电子显微镜 (STEM) 图像的原子分割和定位、降噪和去模糊是一项具有挑战性的任务。尽管阈值、边缘检测和聚类等几种传统算法可以在某些预定义场景中实现合理的性能，但当背景干扰强烈且不可预测时，它们往往会失败。特别是，对于原子分辨率的 STEM 图像，到目前为止，还没有成熟的算法能够在记录图像中存在较大厚度变化时足够鲁棒地分割或检测所有原子柱。在此，我们报告了训练库和深度学习方法的开发，可以对实验图像进行鲁棒且精确的原子分割、定位、去噪和超分辨率处理。尽管使用模拟图像作为训练数据集，深度学习模型可以自适应实验 STEM 图像，并在具有挑战性的对比度条件下在原子检测和定位方面表现出出色的性能，并且精度始终优于最先进的二维高斯拟合方法。更进一步，我们已将深度学习模型部署到具有图形用户界面的桌面应用程序中，并且该应用程序是免费且开源的。我们还建立了 TEM ImageNet 项目网站，方便浏览和下载训练数据。
Atom segmentation and localization, noise reduction and deblurring of atomic-resolution scanning transmission electron microscopy (STEM) images with high precision and robustness is a challenging task. Although several conventional algorithms, such has thresholding, edge detection and clustering, can achieve reasonable performance in some predefined sceneries, they tend to fail when interferences from the background are strong and unpredictable. Particularly, for atomic-resolution STEM images, so far there is no well-established algorithm that is robust enough to segment or detect all atomic columns when there is large thickness variation in a recorded image. Herein, we report the development of a training library and a deep learning method that can perform robust and precise atom segmentation, localization, denoising, and super-resolution processing of experimental images. Despite using simulated images as training datasets, the deep-learning model can self-adapt to experimental STEM images and shows outstanding performance in atom detection and localization in challenging contrast conditions and the precision consistently outperforms the state-of-the-art two-dimensional Gaussian fit method. Taking a step further, we have deployed our deep-learning models to a desktop app with a graphical user interface and the app is free and open-source. We have also built a TEM ImageNet project website for easy browsing and downloading of the training data.
登录
查看更多内容
影响因子：
8.6
作者：
Erni, Rolf;Rossell, Marta D.;Dahmen, Ulrich
通讯作者：
Dahmen, Ulrich
影响因子：
4.6
作者：
Ding, Guanglei;Liu, Yitong;Xin, Huolin L.
通讯作者：
Xin, Huolin L.
影响因子：
4.5
作者：
Pandey, Dinesh;Yin, Xiaoxia;Zhang, Yanchun
通讯作者：
Zhang, Yanchun
影响因子：
8
作者：
BHANDARKAR, SM;ZHANG, YQ;POTTER, WD
通讯作者：
POTTER, WD
影响因子：
8.6
作者：
Fatermans, J.;den Dekker, A. J.;Van Aert, S.
通讯作者：
Van Aert, S.