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/

Zendy Plus

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

Zendy Tools

Zendy Open

Pathological glomerulus classification plays a key role in the diagnosis ofnephropathy. As the difference between different subcategories is subtle,doctors often refer to slides from different staining methods to makedecisions. However, creating correspondence across various stains islabor-intensive, bringing major difficulties in collecting data and training avision-based algorithm to assist nephropathy diagnosis. This paper provides analternative solution for integrating multi-stained visual cues for glomerulusclassification. Our approach, named generator-to-classifier (G2C), is atwo-stage framework. Given an input image from a specified stain, severalgenerators are first applied to estimate its appearances in other stainingmethods, and a classifier follows to combine visual cues from different stainsfor prediction (whether it is pathological, or which type of pathology it has).We optimize these two stages in a joint manner. To provide a reasonableinitialization, we pre-train the generators in an unlabeled reference set underan unpaired image-to-image translation task, and then fine-tune them togetherwith the classifier. We conduct experiments on a glomerulus type classificationdataset collected by ourselves (there are no publicly available datasets forthis purpose). Although joint optimization slightly harms the authenticity ofthe generated patches, it boosts classification performance, suggesting moreeffective visual cues are extracted in an automatic way. We also transfer ourmodel to a public dataset for breast cancer classification, and outperform thestate-of-the-arts significantly.

G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification