Super-compression of large electron microscopy time series by deep compressive sensing learning

Siming Zheng; Chunyang Wang; Xin Yuan; Huolin L Xin

doi:10.1016/j.patter.2021.100292

Super-compression of large electron microscopy time series by deep compressive sensing learning

Patterns (N Y). 2021 Jun 24;2(7):100292. doi: 10.1016/j.patter.2021.100292. eCollection 2021 Jul 9.

Authors

Siming Zheng¹, Chunyang Wang¹, Xin Yuan², Huolin L Xin¹

Affiliations

¹ Department of Physics and Astronomy, University of California, Irvine, Irvine, CA, USA.
² Bell Labs, 600 Mountain Avenue, Murray Hill, NJ 07974, USA.

Abstract

The development of ultrafast detectors for electron microscopy (EM) opens a new door to exploring dynamics of nanomaterials; however, it raises grand challenges for big data processing and storage. Here, we combine deep learning and temporal compressive sensing (TCS) to propose a novel EM big data compression strategy. Specifically, TCS is employed to compress sequential EM images into a single compressed measurement; an end-to-end deep learning network is leveraged to reconstruct the original images. Owing to the significantly improved compression efficiency and built-in denoising capability of the deep learning framework over conventional JPEG compression, compressed videos with a compression ratio of up to 30 can be reconstructed with high fidelity. Using this approach, considerable encoding power, memory, and transmission bandwidth can be saved, allowing it to be deployed to existing detectors. We anticipate the proposed technique will have far-reaching applications in edge computing for EM and other imaging techniques.

Keywords: TEM; big data; compression; compressive sensing; deep learning; direct detection device; direct electron detection; electron microscopy; in situ.