Self-supervised prior learning improves structured illumination microscopy resolution

TL;DR

This paper introduces SIMFormer, a self-supervised learning framework that enhances structured illumination microscopy resolution beyond traditional limits, achieving approximately 45 nm resolution and improved robustness, enabling faster, large-scale super-resolution imaging.

Contribution

The paper presents a novel self-supervised, data-driven prior learning method for SIM reconstruction that surpasses existing resolution limits and improves noise robustness.

Findings

Achieves approximately 45 nm resolution in SIM imaging.

Resolves features comparable to STORM-level resolution.

Enhances noise robustness with SIMFormer+.

Abstract

Structured illumination microscopy (SIM) is a wide-field super-resolution technique normally limited to roughly twice the diffraction-limited resolution ($\approx 100$--$200$~nm). Surpassing this bound is a classic ill-posed inverse problem: recovering high-frequency structure from band-limited raw data. We introduce SIMFormer, a fully blind SIM reconstruction framework that learns a powerful, data-driven prior directly from raw images via self-supervision. This learned prior regularizes the solution and enables reliable extrapolation beyond the optical transfer function cutoff, yielding an effective resolution of approximately 45~nm. We validate SIMFormer on synthetic data and the BioSR dataset, where it resolves features such as flattened endoplasmic reticulum lipid bilayers previously reported to require STORM-level resolution. A self-distilled variant, SIMFormer+, further improves noise robustness while preserving high resolution at extremely low photon counts. These results show that learned priors can substantially extend SIM resolution and robustness, enabling rapid, large-scale imaging with STORM-level detail.