Deep Learning Supersampled Scanning Transmission Electron Microscopy
This work addresses the need for faster and lower-dose imaging in electron microscopy, which is crucial for materials science and biology, but it is incremental as it builds on existing deep learning applications in compressed sensing.
The paper tackles the problem of increasing resolution and reducing electron dose and scan time in scanning transmission electron microscopy by developing a two-stage multiscale generative adversarial network to supersample micrographs with point-scan coverage reduced to as low as 1/100 px, achieving root mean square errors of 3.23% and 4.54% at 1/16 px and 1/100 px coverage, respectively.
Compressed sensing can increase resolution, and decrease electron dose and scan time of electron microscope point-scan systems with minimal information loss. Building on a history of successful deep learning applications in compressed sensing, we have developed a two-stage multiscale generative adversarial network to supersample scanning transmission electron micrographs with point-scan coverage reduced to 1/16, 1/25, ..., 1/100 px. We propose a novel non-adversarial learning policy to train a unified generator for multiple coverages and introduce an auxiliary network to homogenize prioritization of training data with varied signal-to-noise ratios. This achieves root mean square errors of 3.23% and 4.54% at 1/16 px and 1/100 px coverage, respectively; within 1% of errors for networks trained for each coverage individually. Detailed error distributions are presented for unified and individual coverage generators, including errors per output pixel. In addition, we present a baseline one-stage network for a single coverage and investigate numerical precision for web serving. Source code, training data, and pretrained models are publicly available at https://github.com/Jeffrey-Ede/DLSS-STEM