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

Whole-slide image (WSI) analysis plays a crucial role in cancer diagnosis andtreatment. In addressing the demands of this critical task, self-supervisedlearning (SSL) methods have emerged as a valuable resource, leveraging theirefficiency in circumventing the need for a large number of annotations, whichcan be both costly and time-consuming to deploy supervised methods.Nevertheless, patch-wise representation may exhibit instability in performance,primarily due to class imbalances stemming from patch selection within WSIs. Inthis paper, we introduce Nearby Patch Contrastive Learning (NearbyPatchCL), anovel self-supervised learning method that leverages nearby patches as positivesamples and a decoupled contrastive loss for robust representation learning.Our method demonstrates a tangible enhancement in performance for downstreamtasks involving patch-level multi-class classification. Additionally, we curatea new dataset derived from WSIs sourced from the Canine Cutaneous CancerHistology, thus establishing a benchmark for the rigorous evaluation ofpatch-level multi-class classification methodologies. Intensive experimentsshow that our method significantly outperforms the supervised baseline andstate-of-the-art SSL methods with top-1 classification accuracy of 87.56%. Ourmethod also achieves comparable results while utilizing a mere 1% of labeleddata, a stark contrast to the 100% labeled data requirement of otherapproaches. Source code: https://github.com/nvtien457/NearbyPatchCL

NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level Multi-Class Classification in Whole-Slide Images