Methodologies for Successful Segmentation of HRTEM Images via Neural Network

High throughput analysis of samples has been a topic increasingly discussed in both light and electron microscopy. Deep learning can help implement high throughput analysis by segmenting images in a pixel-by-pixel fashion and classifying these regions. However, to date, relatively little has been done in the realm of automated high resolution transmission electron microscopy (HRTEM) micrograph analysis. Neural networks for HRTEM have, so far, focused on identification of single atomic columns in single materials systems. For true high throughput analysis, networks will need to not only recognize atomic columns but also segment out regions of interest from background for a wide variety of materials. We therefore analyze the requirements for achieving a high performance convolutional neural network for segmentation of nanoparticle regions from amorphous carbon in HRTEM images. We also examine how to achieve generalizability of the neural network to a range of materials. We find that networks trained on micrographs of a single material system result in worse segmentation outcomes than one which is trained on a variety of materials' micrographs. Our final network is able to segment nanoparticle regions from amorphous background with 91% pixelwise accuracy.