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

For the deployment of artificial intelligence (AI) in high-risk settings,such as healthcare, methods that provide interpretability/explainability orallow fine-grained error analysis are critical. Many recent methods forinterpretability/explainability and fine-grained error analysis use concepts,which are meta-labels that are semantically meaningful to humans. However,there are only a few datasets that include concept-level meta-labels and mostof these meta-labels are relevant for natural images that do not require domainexpertise. Densely annotated datasets in medicine focused on meta-labels thatare relevant to a single disease such as melanoma. In dermatology, skin diseaseis described using an established clinical lexicon that allows clinicians todescribe physical exam findings to one another. To provide a medical datasetdensely annotated by domain experts with annotations useful across multipledisease processes, we developed SkinCon: a skin disease dataset denselyannotated by dermatologists. SkinCon includes 3230 images from the Fitzpatrick17k dataset densely annotated with 48 clinical concepts, 22 of which have atleast 50 images representing the concept. The concepts used were chosen by twodermatologists considering the clinical descriptor terms used to describe skinlesions. Examples include "plaque", "scale", and "erosion". The same conceptswere also used to label 656 skin disease images from the Diverse DermatologyImages dataset, providing an additional external dataset with diverse skin tonerepresentations. We review the potential applications for the SkinCon dataset,such as probing models, concept-based explanations, and concept bottlenecks.Furthermore, we use SkinCon to demonstrate two of these use cases: debuggingmistakes of an existing dermatology AI model with concepts and developinginterpretable models with post-hoc concept bottleneck models.

SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained model debugging and analysis