BGnet: Accurate and rapid background estimation in single-molecule localization microscopy with deep neural nets
arXiv:1909.08151 · doi:10.1073/pnas.1916219117
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.
arXiv comment50 pages, 20 figures
References in corpus (5)
- Fully Convolutional Networks for Semantic Segmentation
- Medical Image Analysis using Convolutional Neural Networks: A Review
- A Review on Deep Learning Techniques Applied to Semantic Segmentation
- Deep-STORM: super-resolution single-molecule microscopy by deep learning
- Measurement-based estimation of global pupil functions in 3D localization microscopy
Cited by in corpus (7)
- Analysis of Super-resolution Single Molecule Localization Microscopy Data: a tutorial
- Multiscale Modeling and Analysis for High-fidelity Interferometric Scattering Microscopy
- Forecasting high-impact research topics via machine learning on evolving knowledge graphs
- Learning an optimal PSF-pair for ultra-dense 3D localization microscopy
- Artefact removal in ground truth and noise model deficient sub-cellular nanoscopy images using auto-encoder deep learning
- Least-squares fitting of Gaussian spots on graphics processing units
- Measuring the Oscillation Frequency Beyond the Diffraction Limit