Motion-corrected Noise2Noise denoising for structural analysis of cells and tissues with (cryo-)FIB/SEM.
- 1Informatics Department, CeinsaUAL, CINN-CSIC Associated Unit, Almería University, 04120 Almería, Spain.
- 2Spanish National Research Council (CINN-CSIC), Asturias Health Research Institute (ISPA), 33011 Oviedo, Spain.
Abstract
Motivation
(Cryo-)FIB/SEM enables 3D ultrastructural analysis of cells and tissues at nanoscale resolution. However, its characteristically low signal-to-noise ratio severely hinders interpretation of the volume data. Noise2Noise (N2N) has emerged as a state-of-the-art denoising paradigm with outstanding performance in 3D electron microscopy-particularly cryo-ET-but its direct application to (cryo-)FIB/SEM remains unfeasible due to the inherent acquisition workflows.Results
A method to enable N2N denoising in (cryo-)FIB/SEM is introduced. The input volume is split into even and odd slices, followed by the application of motion correction methods to estimate and compensate for the structural differences between the two subvolumes. The resulting motion-corrected subvolumes are then used to train the N2N model, which is ultimately applied to denoise the original volume. Representative (cryo-)FIB/SEM volumes have been used to validate the method and to demonstrate the critical importance of the motion correction stage for volumes with a slice thickness >10 nm.Availability and implementation
Code is available at https://github.com/microscopy-processing/N2N-REO and https://doi.org/10.5281/zenodo.22303478.
Related
- PANDA: Protein All-atom Nested-tree Denoising Architecture for End-to-End Generation
- Volumetric denoising enables high-throughput volume electron microscopy and efficient downstream analysis
- Simultaneous Denoising and Baseline Correction of Microplate Raman Spectra Using a Dual-Branch U-Net
- Probing and modeling cell–cell communication in 2D biomimetic tissues
- Recovery of genomic and transcriptomic profiles from decades-old FFPE brain tissues
BibTeX
@article{gonzalezruiz2026motioncorrected,
title = {{Motion-corrected Noise2Noise denoising for structural analysis of cells and tissues with (cryo-)FIB/SEM.}},
author = {Vicente González-Ruiz and José-Jesús Fernández},
journal = {Bioinformatics (Oxford, England)},
year = {2026},
month = oct,
doi = {10.1093/bioinformatics/btag765},
url = {https://europepmc.org/article/MED/42885571},
note = {CC BY},
}
RIS
TY - JOUR
TI - Motion-corrected Noise2Noise denoising for structural analysis of cells and tissues with (cryo-)FIB/SEM.
AU - Vicente González-Ruiz
AU - José-Jesús Fernández
PY - 2026
DA - 2026/10/01
JO - Bioinformatics (Oxford, England)
DO - 10.1093/bioinformatics/btag765
UR - https://europepmc.org/article/MED/42885571
AB - Motivation (Cryo-)FIB/SEM enables 3D ultrastructural analysis of cells and tissues at nanoscale resolution. However, its characteristically low signal-to-noise ratio severely hinders interpretation of the volume data. Noise2Noise (N2N) has emerged as a state-of-the-art denoising paradigm with outstanding performance in 3D electron microscopy-particularly cryo-ET-but its direct application to (cryo-)FIB/SEM remains unfeasible due to the inherent acquisition workflows.Results A method to enable N2N denoising in (cryo-)FIB/SEM is introduced. The input volume is split into even and odd slices, followed by the application of motion correction methods to estimate and compensate for the structural differences between the two subvolumes. The resulting motion-corrected subvolumes are then used to train the N2N model, which is ultimately applied to denoise the original volume. Representative (cryo-)FIB/SEM volumes have been used to validate the method and to demonstrate the critical importance of the motion correction stage for volumes with a slice thickness >10 nm.Availability and implementation Code is available at https://github.com/microscopy-processing/N2N-REO and https://doi.org/10.5281/zenodo.22303478.
SN - 1367-4803
SN - 1367-4811
ER -