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

Using features extracted from networks pretrained on ImageNet is a commonpractice in applications of deep learning for digital pathology. However itpresents the downside of missing domain specific image information. In digitalpathology, supervised training data is expensive and difficult to collect. Wepropose a self-supervised method for feature extraction by similarity learningon whole slide images (WSI) that is simple to implement and allows creation ofrobust and compact image descriptors. We train a siamese network, exploitingimage spatial continuity and assuming spatially adjacent tiles in the image aremore similar to each other than distant tiles. Our network outputs featurevectors of length 128, which allows dramatically lower memory storage andfaster processing than networks pretrained on ImageNet. We apply the method ondigital pathology WSIs from the Camelyon16 train set and assess and compare ourmethod by measuring image retrieval of tumor tiles and descriptor pair distanceratio for distant/near tiles in the Camelyon16 test set. We show that ourmethod yields better retrieval task results than existing ImageNet based andgeneric self-supervised feature extraction methods. To the best of ourknowledge, this is also the first published method for self-supervised learningtailored for digital pathology.

Self-Supervised Similarity Learning for Digital Pathology