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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Visualizing the details of different cellular structures is of greatimportance to elucidate cellular functions. However, it is challenging toobtain high quality images of different structures directly due to complexcellular environments. Fluorescence staining is a popular technique to labeldifferent structures but has several drawbacks. In particular, label stainingis time consuming and may affect cell morphology, and simultaneous labels areinherently limited. This raises the need of building computational models tolearn relationships between unlabeled microscopy images and labeledfluorescence images, and to infer fluorescence labels of other microscopyimages excluding the physical staining process. We propose to develop a noveldeep model for virtual staining of unlabeled microscopy images. We firstpropose a novel network layer, known as the global pixel transformer layer,that fuses global information from inputs effectively. The proposed globalpixel transformer layer can generate outputs with arbitrary dimensions, and canbe employed for all the regular, down-sampling, and up-sampling operators. Wethen incorporate our proposed global pixel transformer layers and dense blocksto build an U-Net like network. We believe such a design can promote featurereusing between layers. In addition, we propose a multi-scale input strategy toencourage networks to capture features at different scales. We conductevaluations across various fluorescence image prediction tasks to demonstratethe effectiveness of our approach. Both quantitative and qualitative resultsshow that our method outperforms the state-of-the-art approach significantly.It is also shown that our proposed global pixel transformer layer is useful toimprove the fluorescence image prediction results.

Global Pixel Transformers for Virtual Staining of Microscopy Images