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

Fluorescence microscopy images contain several channels, each indicating amarker staining the sample. Since many different marker combinations areutilized in practice, it has been challenging to apply deep learning basedsegmentation models, which expect a predefined channel combination for alltraining samples as well as at inference for future application. Recent workcircumvents this problem using a modality attention approach to be effectiveacross any possible marker combination. However, for combinations that do notexist in a labeled training dataset, one cannot have any estimation ofpotential segmentation quality if that combination is encountered duringinference. Without this, not only one lacks quality assurance but one also doesnot know where to put any additional imaging and labeling effort. We hereinpropose a method to estimate segmentation quality on unlabeled images by (i)estimating both aleatoric and epistemic uncertainties of convolutional neuralnetworks for image segmentation, and (ii) training a Random Forest model forthe interpretation of uncertainty features via regression to theircorresponding segmentation metrics. Additionally, we demonstrate that includingthese uncertainty measures during training can provide an improvement onsegmentation performance.

Utilizing Uncertainty Estimation in Deep Learning Segmentation of Fluorescence Microscopy Images with Missing Markers