Trainable segmentation for transmission electron microscope images of inorganic nanoparticles.

RESUMEN

Measurement of the size, shape and composition of nanoparticles is routinely performed using transmission electron microscopy and related techniques. Typically, distinguishing particles from the background in an image is performed using the intensity of each pixel, creating two sets of pixels to separate particles from background. However, this separation of intensity can be difficult if the contrast in an image is low, or if the intensity of the background varies significantly. In this study, an approach that takes into account additional image features (such as boundaries and texture) was investigated to study electron microscope images of metallic nanoparticles. In this 'trainable segmentation' approach, the user labels examples of particle and background pixels in order to train a machine learning algorithm to distinguish between particles and background. The performance of different machine learning algorithms was investigated, in addition to the effect of using different features to aid the segmentation. Overall, a trainable segmentation approach was found to perform better than use of an intensity threshold to distinguish between particles and background in electron microscope images.