Self-supervised prior learning improves structured illumination microscopy resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Ze-Hao, Weng, Tong-Tian, Shan, Long-Kun, Chen, Xiang-Dong, Guo, Guang-Can, Sun, Fang-Wen, Chen, Tian-Long
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911298728493056
author Wang, Ze-Hao
Weng, Tong-Tian
Shan, Long-Kun
Chen, Xiang-Dong
Guo, Guang-Can
Sun, Fang-Wen
Chen, Tian-Long
author_facet Wang, Ze-Hao
Weng, Tong-Tian
Shan, Long-Kun
Chen, Xiang-Dong
Guo, Guang-Can
Sun, Fang-Wen
Chen, Tian-Long
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22053
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-supervised prior learning improves structured illumination microscopy resolution
Wang, Ze-Hao
Weng, Tong-Tian
Shan, Long-Kun
Chen, Xiang-Dong
Guo, Guang-Can
Sun, Fang-Wen
Chen, Tian-Long
Optics
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.
title Self-supervised prior learning improves structured illumination microscopy resolution
topic Optics
url https://arxiv.org/abs/2511.22053