3D fluorescence microscopy data synthesis for segmentation and benchmarking

TL;DR

This paper introduces a method using conditional GANs to generate realistic, fully-annotated 3D fluorescence microscopy data from masks, aiding training and benchmarking with minimal manual effort.

Contribution

It presents a novel approach combining GANs and mask simulation to produce customizable, fully-annotated 3D microscopy datasets for training and benchmarking.

Findings

Generated realistic 3D microscopy data with positional intensity variations.

Produced datasets of arbitrary size and different organisms.

Made the datasets publicly available for community use.

Abstract

Automated image processing approaches are indispensable for many biomedical experiments and help to cope with the increasing amount of microscopy image data in a fast and reproducible way. Especially state-of-the-art deep learning-based approaches most often require large amounts of annotated training data to produce accurate and generalist outputs, but they are often compromised by the general lack of those annotated data sets. In this work, we propose how conditional generative adversarial networks can be utilized to generate realistic image data for 3D fluorescence microscopy from annotation masks of 3D cellular structures. In combination with mask simulation approaches, we demonstrate the generation of fully-annotated 3D microscopy data sets that we make publicly available for training or benchmarking. An additional positional conditioning of the cellular structures enables the reconstruction of position-dependent intensity characteristics and allows to generate image data of different quality levels. A patch-wise working principle and a subsequent full-size reassemble strategy is used to generate image data of arbitrary size and different organisms. We present this as a proof-of-concept for the automated generation of fully-annotated training data sets requiring only a minimum of manual interaction to alleviate the need of manual annotations.