Isotropic reconstruction of 3D fluorescence microscopy images using convolutional neural networks

TL;DR

This paper introduces a convolutional neural network approach to convert anisotropic fluorescence microscopy images into isotropic ones, improving downstream analysis and outperforming traditional deconvolution and super-resolution methods.

Contribution

The authors develop an end-to-end CNN that learns to restore isotropic resolution from anisotropic microscopy data, demonstrating superior performance over existing techniques.

Findings

Improved isotropic resolution in synthetic and real datasets.

Enhanced accuracy in 3D segmentation tasks.

Outperforms traditional deconvolution and super-resolution methods.

Abstract

Fluorescence microscopy images usually show severe anisotropy in axial versus lateral resolution. This hampers downstream processing, i.e. the automatic extraction of quantitative biological data. While deconvolution methods and other techniques to address this problem exist, they are either time consuming to apply or limited in their ability to remove anisotropy. We propose a method to recover isotropic resolution from readily acquired anisotropic data. We achieve this using a convolutional neural network that is trained end-to-end from the same anisotropic body of data we later apply the network to. The network effectively learns to restore the full isotropic resolution by restoring the image under a trained, sample specific image prior. We apply our method to $3$ synthetic and $3$ real datasets and show that our results improve on results from deconvolution and state-of-the-art super-resolution techniques. Finally, we demonstrate that a standard 3D segmentation pipeline performs on the output of our network with comparable accuracy as on the full isotropic data.