Bayesian Particle Instance Segmentation for Electron Microscopy Image Quantification.


Type
Article
Change log
Authors
Abstract

Automating the analysis portion of materials characterization by electron microscopy (EM) has the potential to accelerate the process of scientific discovery. To this end, we present a Bayesian deep-learning model for semantic segmentation and localization of particle instances in EM images. These segmentations can subsequently be used to compute quantitative measures such as particle-size distributions, radial- distribution functions, average sizes, and aspect ratios of the particles in an image. Moreover, by making use of the epistemic uncertainty of our model, we obtain uncertainty estimates of its outputs and use these to filter out false-positive predictions and hence produce more accurate quantitative measures. We incorporate our method into the ImageDataExtractor package, as ImageDataExtractor 2.0, which affords a full pipeline to automatically extract particle information for large-scale data-driven materials discovery. Finally, we present and make publicly available the Electron Microscopy Particle Segmentation (EMPS) data set. This is the first human-labeled particle instance segmentation data set, consisting of 465 EM images and their corresponding semantic instance segmentation maps.

Description
Keywords
Bayes Theorem, Humans, Image Processing, Computer-Assisted, Microscopy, Electron, Semantics
Journal Title
J Chem Inf Model
Conference Name
Journal ISSN
1549-9596
1549-960X
Volume Title
61
Publisher
American Chemical Society (ACS)
Rights
All rights reserved
Sponsorship
Royal Academy of Engineering (RAEng) (RCSRF1819\7\10)
STFC (Unknown)
STFC (Unknown)