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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Segmentation of objects in microscopy images is required for many biomedicalapplications. We introduce object-centric embeddings (OCEs), which embed imagepatches such that the spatial offsets between patches cropped from the sameobject are preserved. Those learnt embeddings can be used to delineateindividual objects and thus obtain instance segmentations. Here, we showtheoretically that, under assumptions commonly found in microscopy images, OCEscan be learnt through a self-supervised task that predicts the spatial offsetbetween image patches. Together, this forms an unsupervised cell instancesegmentation method which we evaluate on nine diverse large-scale microscopydatasets. Segmentations obtained with our method lead to substantially improvedresults, compared to state-of-the-art baselines on six out of nine datasets,and perform on par on the remaining three datasets. If ground-truth annotationsare available, our method serves as an excellent starting point for supervisedtraining, reducing the required amount of ground-truth needed by one order ofmagnitude, thus substantially increasing the practical applicability of ourmethod. Source code is available at https://github.com/funkelab/cellulus.

Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Images