Optimal transport unlocks end-to-end learning for single-molecule localization

Romain Seailles, Jean Baptiste Masson, Jean Ponce, Julien Mairal

Keywords: Single Molecule Localization Microscopy, SMLM, High-Density, Learning, Deep Learning, Inverse Problems, Iterative Refinement

TL;DR: We present an end-to-end learning model for single-molecule localization microscopy that combines an optimal transport loss function with an iterative neural network. It achieves state-of-the-art performance on synthetic benchmarks and real images.

Abstract:

Single‑molecule localization microscopy (SMLM) allows reconstructing cellular organelles and biology-relevant structures far beyond the limited spatial resolution imposed by optics constrains, using tagged biomolecule positions. Currently, efficient SMLM requires non‑overlapping emitting fluorophores, to ensure proper image deconvolution leading to long acquisition times that hinders live‑cell imaging. Recent deep‑learning approaches can handle denser emissions, but they rely on variants of non‑maximum suppression (NMS) layers, which are unfortunately non‑differentiable and may discard true positives with their local fusion strategy.
In this presentation, we reformulate the SMLM training objective as a set‑matching problem, deriving an optimal‑transport loss that eliminates the need for NMS during inference and enables end‑to‑end training.
Additionally, we propose an iterative neural network that integrates knowledge of the microscope’s optical system inside our model. Experiments on synthetic benchmarks and real biological data show that both our new loss function and architecture surpass the state of the art at moderate and high emitter densities. Code is available at https://github.com/RSLLES/SHOT.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 16705