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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multiple Instance Learning (MIL) has become the predominant approach forclassification tasks on gigapixel histopathology whole slide images (WSIs).Within the MIL framework, single WSIs (bags) are decomposed into patches(instances), with only WSI-level annotation available. Recent MIL approachesproduce highly informative bag level representations by utilizing thetransformer architecture's ability to model the dependencies between instances.However, when applied to high magnification datasets, problems emerge due tothe large number of instances and the weak supervisory learning signal. Toaddress this problem, we propose to additionally train transformers with anovel Bag Embedding Loss (BEL). BEL forces the model to learn a discriminativebag-level representation by minimizing the distance between bag embeddings ofthe same class and maximizing the distance between different classes. Weevaluate BEL with the Transformer architecture TransMIL on two publiclyavailable histopathology datasets, BRACS and CAMELYON17. We show that with BEL,TransMIL outperforms the baseline models on both datasets, thus contributing tothe clinically highly relevant AI-based tumor classification of histologicalpatient material.

BEL: A Bag Embedding Loss for Transformer enhances Multiple Instance Whole Slide Image Classification