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

Deep learning has recently gained popularity in digital pathology due to itshigh prediction quality. However, the medical domain requires explanation andinsight for a better understanding beyond standard quantitative performanceevaluation. Recently, explanation methods have emerged, which are so far stillrarely used in medicine. This work shows their application to generate heatmapsthat allow to resolve common challenges encountered in deep learning-baseddigital histopathology analyses. These challenges comprise biases typicallyinherent to histopathology data. We study binary classification tasks of tumortissue discrimination in publicly available haematoxylin and eosin slides ofvarious tumor entities and investigate three types of biases: (1) biases whichaffect the entire dataset, (2) biases which are by chance correlated with classlabels and (3) sampling biases. While standard analyses focus on patch-levelevaluation, we advocate pixel-wise heatmaps, which offer a more precise andversatile diagnostic instrument and furthermore help to reveal biases in thedata. This insight is shown to not only detect but also to be helpful to removethe effects of common hidden biases, which improves generalization within andacross datasets. For example, we could see a trend of improved area under thereceiver operating characteristic curve by 5% when reducing a labeling bias.Explanation techniques are thus demonstrated to be a helpful and highlyrelevant tool for the development and the deployment phases within the lifecycle of real-world applications in digital pathology.

Resolving challenges in deep learning-based analyses of histopathological images using explanation methods