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

Digital pathology enables remote access or consults and powerful imageanalysis algorithms. However, the slide digitization process can createartifacts such as out-of-focus (OOF). OOF is often only detected upon carefulreview, potentially causing rescanning and workflow delays. Although scan-timeoperator screening for whole-slide OOF is feasible, manual screening for OOFaffecting only parts of a slide is impractical. We developed a convolutionalneural network (ConvFocus) to exhaustively localize and quantify the severityof OOF regions on digitized slides. ConvFocus was developed using our refinedsemi-synthetic OOF data generation process, and evaluated using realwhole-slide images spanning 3 different tissue types and 3 different staintypes that were digitized by two different scanners. ConvFocus's predictionswere compared with pathologist-annotated focus quality grades across 514distinct regions representing 37,700 35x35 $\mu$m image patches, and 21digitized "z-stack" whole-slide images that contain known OOF patterns. Whencompared to pathologist-graded focus quality, ConvFocus achieved Spearman rankcoefficients of 0.81 and 0.94 on two scanners, and reproduced the expected OOFpatterns from z-stack scanning. We also evaluated the impact of OOF on theaccuracy of a state-of-the-art metastatic breast cancer detector and saw aconsistent decrease in performance with increasing OOF. Comprehensivewhole-slide OOF categorization could enable rescans prior to pathologistreview, potentially reducing the impact of digitization focus issues on theclinical workflow. We show that the algorithm trained on our semi-synthetic OOFdata generalizes well to real OOF regions across tissue types, stains, andscanners. Finally, quantitative OOF maps can flag regions that might otherwisebe misclassified by image analysis algorithms, preventing OOF-induced errors.

Whole-Slide Image Focus Quality: Automatic Assessment and Impact on AI Cancer Detection