English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Automated image processing approaches are indispensable for many biomedicalexperiments and help to cope with the increasing amount of microscopy imagedata in a fast and reproducible way. Especially state-of-the-art deeplearning-based approaches most often require large amounts of annotatedtraining data to produce accurate and generalist outputs, but they are oftencompromised by the general lack of those annotated data sets. In this work, wepropose how conditional generative adversarial networks can be utilized togenerate realistic image data for 3D fluorescence microscopy from annotationmasks of 3D cellular structures. In combination with mask simulationapproaches, we demonstrate the generation of fully-annotated 3D microscopy datasets that we make publicly available for training or benchmarking. Anadditional positional conditioning of the cellular structures enables thereconstruction of position-dependent intensity characteristics and allows togenerate image data of different quality levels. A patch-wise working principleand a subsequent full-size reassemble strategy is used to generate image dataof arbitrary size and different organisms. We present this as aproof-of-concept for the automated generation of fully-annotated training datasets requiring only a minimum of manual interaction to alleviate the need ofmanual annotations.

3D fluorescence microscopy data synthesis for segmentation and benchmarking