Combining deep learning with SUPPOSe and compressed sensing for SNR-enhanced localization of overlapping emitters

Abstract

We present gSUPPOSe, a novel, to the best of our knowledge, gradient-based implementation of the SUPPOSe algorithm that we have developed for the localization of single emitters. We study the performance of gSUPPOSe and compressed sensing STORM (CS-STORM) on simulations of single-molecule localization microscopy (SMLM) images at different fluorophore densities and in a wide range of signal-to-noise ratio conditions. We also study the combination of these methods with prior image denoising by means of a deep convolutional network. Our results show that gSUPPOSe can address the localization of multiple overlapping emitters even at a low number of acquired photons, outperforming CS-STORM in our quantitative analysis and having better computational times. We also demonstrate that image denoising greatly improves CS-STORM, showing the potential of deep learning enhanced localization on existing SMLM algorithms. The software developed in this work is available as open source Python libraries.

Document Details

Document Type
Pub Defense Publication
Publication Date
Feb 03, 2022
Source ID
10.1364/ao.444610

Entities

People

  • Alejandro Mazzeo
  • Axel M. Lacapmesure
  • Guillermo D. Brinatti Vazquez
  • Oscar E. Martinez
  • Sandra Martı́nez

Organizations

  • Air Force Office of Scientific Research
  • University of Buenos Aires

Tags

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computer Vision.
  • Radio communications and signal processing.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks