Learning Guided Electron Microscopy with Active Acquisition
This work provides a method for neurobiologists to significantly speed up the acquisition of connectomic datasets using SEM, addressing the bottleneck of uniform imaging.
This paper addresses the inefficiency of uniform data acquisition in single-beam scanning electron microscopes (SEM) by proposing a deep learning-based active acquisition algorithm. The method first captures a low-resolution image and then uses a novel learning approach to select a small subset of pixels for higher-resolution collection, balancing saliency and spatial diversity. This technique accelerates connectomic dataset collection for neurobiology by up to an order of magnitude.
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.