Fast improvement of TEM image with low-dose electrons by deep learning

TL;DR

This paper introduces a deep learning-based method to enhance low-dose TEM images, enabling high-quality in situ observations at high frame rates with minimal electron exposure.

Contribution

A convolutional neural network pipeline is developed to improve low-dose TEM images, allowing real-time, high-quality imaging at 125 fps with significantly reduced electron dose.

Findings

Image quality comparable to high-dose images at 5 e- per pixel

Processing time of approximately 8 ms enables real-time imaging

Enables in situ observation of electron-beam-sensitive samples

Abstract

Low-electron-dose observation is indispensable for observing various samples using a transmission electron microscope; consequently, image processing has been used to improve transmission electron microscopy (TEM) images. To apply such image processing to in situ observations, we here apply a convolutional neural network to TEM imaging. Using a dataset that includes short-exposure images and long-exposure images, we develop a pipeline for processed short-exposure images, based on end-to-end training. The quality of images acquired with a total dose of approximately 5 e- per pixel becomes comparable to that of images acquired with a total dose of approximately 1000 e- per pixel. Because the conversion time is approximately 8 ms, in situ observation at 125 fps is possible. This imaging technique enables in situ observation of electron-beam-sensitive specimens.