0.71-Å resolution electron tomography enabled by deep learning aided information recovery

Abstract: Electron tomography, as an important 3D imaging method, offers a powerful method to probe the 3D structure of materials from the nano- to the atomic-scale. However, as a grant challenge, radiation intolerance of the nanoscale samples and the missing-wedge-induced information loss and artifacts greatly hindered us from obtaining 3D atomic structures with high fidelity. Here, for the first time, by combining generative adversarial models with state-of-the-art network architectures, we demonstrate the resolution of electron tomography can be improved to 0.71 angstrom which is the highest three-dimensional imaging resolution that has been reported thus far. We also show it is possible to recover the lost information and remove artifacts in the reconstructed tomograms by only acquiring data from -50 to +50 degrees (44% reduction of dosage compared to -90 to +90 degrees full tilt series). In contrast to conventional methods, the deep learning model shows outstanding performance for both macroscopic objects and atomic features solving the long-standing dosage and missing-wedge problems in electron tomography. Our work provides important guidance for the application of machine learning methods to tomographic imaging and sheds light on its applications in other 3D imaging techniques.