BGnet: Accurate and rapid background estimation in single-molecule localization microscopy with deep neural nets

TL;DR

BGnet is a deep neural network that accurately and rapidly estimates structured background in single-molecule microscopy images, significantly improving localization precision and super-resolution image quality.

Contribution

The paper introduces BGnet, a novel deep learning approach for fast and precise background estimation in complex single-molecule microscopy images, including those with engineered PSFs.

Findings

BGnet accurately estimates background across various PSFs.

Background correction improves localization precision.

Enhanced super-resolution reconstructions achieved.

Abstract

Background fluorescence, especially when it exhibits undesired spatial features, is a primary factor for reduced image quality in optical microscopy. Structured background is particularly detrimental when analyzing single-molecule images for 3D localization microscopy or single-molecule tracking. Here, we introduce BGnet, a deep neural network with a U-net-type architecture, as a general method to rapidly estimate the background underlying the image of a point source with excellent accuracy, even when point spread function (PSF) engineering is in use to create complex PSF shapes. We trained BGnet to extract the background from images of various PSFs and show that the identification is accurate for a wide range of different interfering background structures constructed from many spatial frequencies. Furthermore, we demonstrate that the obtained background-corrected PSF images, both for simulated and experimental data, lead to a substantial improvement in localization precision. Finally, we verify that structured background estimation with BGnet results in higher quality of super-resolution reconstructions of biological structures.