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

In many histopathology tasks, sample classification depends on morphologicaldetails in tissue or single cells that are only visible at the highestmagnification. For a pathologist, this implies tedious zooming in and out,while for a computational decision support algorithm, it leads to the analysisof a huge number of small image patches per whole slide image (WSI).Attention-based multiple instance learning (MIL), where attention estimation islearned in a weakly supervised manner, has been successfully applied incomputational histopathology, but it is challenged by large numbers ofirrelevant patches, reducing its accuracy. Here, we present an active learningapproach to the problem. Querying the expert to annotate regions of interest ina WSI guides the formation of high-attention regions for MIL. We train anattention-based MIL and calculate a confidence metric for every image in thedataset to select the most uncertain WSIs for expert annotation. We test ourapproach on the CAMELYON17 dataset classifying metastatic lymph node sectionsin breast cancer. With a novel attention guiding loss, this leads to anaccuracy boost of the trained models with few regions annotated for each class.Active learning thus improves WSIs classification accuracy, leads to faster andmore robust convergence, and speeds up the annotation process. It may in thefuture serve as an important contribution to train MIL models in the clinicallyrelevant context of cancer classification in histopathology.

Active Learning Enhances Classification of Histopathology Whole Slide Images with Attention-based Multiple Instance Learning