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

Existing tools for explaining the output of image classifiers can be dividedinto white-box, which rely on access to the model internals, and black-box,agnostic to the model. As the usage of AI in the medical domain grows, so toodoes the usage of explainability tools. Existing work on medical imageexplanations focuses on white-box tools, such as gradcam. However, there areclear advantages to switching to a black-box tool, including the ability to useit with any classifier and the wide selection of black-box tools available. Onstandard images, black-box tools are as precise as white-box. In this paper wecompare the performance of several black-box methods against gradcam on a braincancer MRI dataset. We demonstrate that most black-box tools are not suitablefor explaining medical image classifications and present a detailed analysis ofthe reasons for their shortcomings. We also show that one black-box tool, acausal explainability-based rex, performs as well as \gradcam.

MRxaI: Black-Box Explainability for Image Classifiers in a Medical Setting