Deep Learning for Isotropic Super-Resolution from Non-Isotropic 3D Electron Microscopy

06/09/2017
by   Larissa Heinrich, et al.
0

The most sophisticated existing methods to generate 3D isotropic super-resolution (SR) from non-isotropic electron microscopy (EM) are based on learned dictionaries. Unfortunately, none of the existing methods generate practically satisfying results. For 2D natural images, recently developed super-resolution methods that use deep learning have been shown to significantly outperform the previous state of the art. We have adapted one of the most successful architectures (FSRCNN) for 3D super-resolution, and compared its performance to a 3D U-Net architecture that has not been used previously to generate super-resolution. We trained both architectures on artificially downscaled isotropic ground truth from focused ion beam milling scanning EM (FIB-SEM) and tested the performance for various hyperparameter settings. Our results indicate that both architectures can successfully generate 3D isotropic super-resolution from non-isotropic EM, with the U-Net performing consistently better. We propose several promising directions for practical application.

READ FULL TEXT
research
05/26/2023

AI-based analysis of super-resolution microscopy: Biological discovery in the absence of ground truth

The nanoscale resolution of super-resolution microscopy has now enabled ...
research
11/22/2020

Cryo-ZSSR: multiple-image super-resolution based on deep internal learning

Single-particle cryo-electron microscopy (cryo-EM) is an emerging imagin...
research
10/25/2020

Weighted-CEL0 sparse regularisation for molecule localisation in super-resolution microscopy with Poisson data

We propose a continuous non-convex variational model for Single Molecule...
research
04/08/2021

Stable deep neural network architectures for mitochondria segmentation on electron microscopy volumes

Electron microscopy (EM) allows the identification of intracellular orga...
research
07/27/2022

Towards quantitative super-resolution microscopy: Molecular maps with statistical guarantees

Quantifying the number of molecules from fluorescence microscopy measure...
research
11/28/2016

Multi-resolution Data Fusion for Super-Resolution Electron Microscopy

Perhaps surprisingly, the total electron microscopy (EM) data collected ...
research
06/25/2020

Deep Learning for Cornea Microscopy Blind Deblurring

The goal of this project is to build a deep-learning solution that deblu...

Please sign up or login with your details

Forgot password? Click here to reset