Learning Guided Electron Microscopy with Active Acquisition

TL;DR

This paper introduces a deep learning-based method to optimize electron microscopy imaging by selectively acquiring high-resolution data at important pixels, significantly speeding up data collection for neurobiology.

Contribution

It presents a novel learning algorithm that guides active pixel selection in SEM, improving efficiency over uniform acquisition methods.

Findings

Speeded up connectomic data collection by up to ten times

Demonstrated effective pixel selection balancing saliency and diversity

Validated approach on neurobiological imaging tasks

Abstract

Single-beam scanning electron microscopes (SEM) are widely used to acquire massive data sets for biomedical study, material analysis, and fabrication inspection. Datasets are typically acquired with uniform acquisition: applying the electron beam with the same power and duration to all image pixels, even if there is great variety in the pixels' importance for eventual use. Many SEMs are now able to move the beam to any pixel in the field of view without delay, enabling them, in principle, to invest their time budget more effectively with non-uniform imaging. In this paper, we show how to use deep learning to accelerate and optimize single-beam SEM acquisition of images. Our algorithm rapidly collects an information-lossy image (e.g. low resolution) and then applies a novel learning method to identify a small subset of pixels to be collected at higher resolution based on a trade-off between the saliency and spatial diversity. We demonstrate the efficacy of this novel technique for active acquisition by speeding up the task of collecting connectomic datasets for neurobiology by up to an order of magnitude.