NP-SAM: Implementing the Segment Anything Model for Easy Nanoparticle Segmentation in Electron Microscopy Images

Abstract

Despite the numerous existing (semi)automated workflows for image segmentation of electron microscopy pictures of nanoparticles for statistical size and shape determination the prevalent approach to particle counting still is doing so in cumbersome manual fashion. Here, we present an easily implementable, low entry barrier workflow for nanoparticle segmentation, which eliminates the need for manual particle counting. It is based on the recently released segment anything model and widely distributed, well maintained, python libraries. We explore the impressive zero shot performance of the segment anything model and present approaches for subsequent filtering of outputs to minimize over and under segmentation on a range of different electron microscopy images of nanoparticles. Furthermore, we introduce a novel methodology for handling partial overlap between nanoparticles, which comprise one of the biggest obstacles for many automated segmentation algorithms. Our presented workflow is easily adaptable, and we encourage the community to further build on the work we present here.