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

Cervical glandular cell (GC) detection is a key step in computer-aideddiagnosis for cervical adenocarcinomas screening. It is challenging toaccurately recognize GCs in cervical smears in which squamous cells are themajor. Widely existing Out-Of-Distribution (OOD) data in the entire smear leadsdecreasing reliability of machine learning system for GC detection. Although,the State-Of-The-Art (SOTA) deep learning model can outperform pathologists inpreselected regions of interest, the mass False Positive (FP) prediction withhigh probability is still unsolved when facing such gigapixel whole slideimage. This paper proposed a novel PolarNet based on the morphological priorknowledge of GC trying to solve the FP problem via a self-attention mechanismin eight-neighbor. It estimates the polar orientation of nucleus of GC. As aplugin module, PolarNet can guide the deep feature and predicted confidence ofgeneral object detection models. In experiments, we discovered that generalmodels based on four different frameworks can reject FP in small image set andincrease the mean of average precision (mAP) by $\text{0.007}\sim\text{0.015}$in average, where the highest exceeds the recent cervical cell detection model0.037. By plugging PolarNet, the deployed C++ program improved by 8.8\% onaccuracy of top-20 GC detection from external WSIs, while sacrificing 14.4 s ofcomputational time. Code is available inhttps://github.com/Chrisa142857/PolarNet-GCdet

Cervical Glandular Cell Detection from Whole Slide Image with Out-Of-Distribution Data