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

Tissue phenotyping is a fundamental task in learning objectivecharacterizations of histopathologic biomarkers within the tumor-immunemicroenvironment in cancer pathology. However, whole-slide imaging (WSI) is acomplex computer vision in which: 1) WSIs have enormous image resolutions withprecludes large-scale pixel-level efforts in data curation, and 2) diversity ofmorphological phenotypes results in inter- and intra-observer variability intissue labeling. To address these limitations, current efforts have proposedusing pretrained image encoders (transfer learning from ImageNet,self-supervised pretraining) in extracting morphological features frompathology, but have not been extensively validated. In this work, we conduct asearch for good representations in pathology by training a variety ofself-supervised models with validation on a variety of weakly-supervised andpatch-level tasks. Our key finding is in discovering that Vision Transformersusing DINO-based knowledge distillation are able to learn data-efficient andinterpretable features in histology images wherein the different attentionheads learn distinct morphological phenotypes. We make evaluation code andpretrained weights publicly-available at:https://github.com/Richarizardd/Self-Supervised-ViT-Path.

Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology