Deep Learning Segmentation of Complex Features in Atomic-Resolution Phase Contrast Transmission Electron Microscopy Images

TL;DR

This paper demonstrates that deep learning, specifically U-Net, significantly improves segmentation accuracy and robustness in complex phase contrast TEM images of materials like graphene, surpassing traditional methods.

Contribution

The study introduces a deep learning segmentation approach for phase contrast TEM images, showing it outperforms conventional filtering methods in accuracy and robustness.

Findings

Deep learning outperforms Bragg filtering in segmentation accuracy.

U-Net provides more general and robust results.

Source code is made publicly available for further use.

Abstract

Phase contrast transmission electron microscopy (TEM) is a powerful tool for imaging the local atomic structure of materials. TEM has been used heavily in studies of defect structures of 2D materials such as monolayer graphene due to its high dose efficiency. However, phase contrast imaging can produce complex nonlinear contrast, even for weakly-scattering samples. It is therefore difficult to develop fully-automated analysis routines for phase contrast TEM studies using conventional image processing tools. For automated analysis of large sample regions of graphene, one of the key problems is segmentation between the structure of interest and unwanted structures such as surface contaminant layers. In this study, we compare the performance of a conventional Bragg filtering method to a deep learning routine based on the U-Net architecture. We show that the deep learning method is more general, simpler to apply in practice, and produces more accurate and robust results than the conventional algorithm. We provide easily-adaptable source code for all results in this paper, and discuss potential applications for deep learning in fully-automated TEM image analysis.