Zhu Xiaoyang, Mao Yu, Liu Jizi, Chen Yi, Chen Chuan, Li Yan, Huang Xiao, Gu Ning
Jiangsu Key Laboratory for Biomaterials and Devices, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210009, PR China.
Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, PR China.
Nanoscale. 2023 Sep 14;15(35):14496-14504. doi: 10.1039/d3nr03061j.
Accurate analysis of high-resolution transmission electron microscopy (HRTEM) images is important for the characterization and design of materials. However, conventional analyses rely mostly on manual procedures, which are time-consuming and lack accuracy, especially when the image contrast is low. Here, we propose an advanced analysis method for extracting crystal features from HRTEM images based on a 2D fast Fourier transform and U-Net based deep learning model. By using HRTEM images of iron oxide nanoparticles as examples, we show that our method is capable of providing information on the crystallinity profile, distribution of crystal planes, phases and defects automatically with high accuracy. In an era of data-driven technological development, we believe that deep learning based analysis tools will facilitate great progress in fundamental research on crystalline materials.
高分辨率透射电子显微镜（HRTEM）图像的准确分析对于材料的表征和设计至关重要。然而，传统分析大多依赖于手工操作，既耗时又缺乏准确性，尤其是在图像对比度较低时。在此，我们提出一种基于二维快速傅里叶变换和基于U-Net的深度学习模型从HRTEM图像中提取晶体特征的先进分析方法。以氧化铁纳米颗粒的HRTEM图像为例，我们表明我们的方法能够高精度地自动提供有关结晶度分布、晶面分布、相和缺陷的信息。在数据驱动技术发展的时代，我们相信基于深度学习的分析工具将推动晶体材料基础研究取得巨大进展。
