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

Skin tone as a demographic bias and inconsistent human labeling poseschallenges in dermatology AI. We take another angle to investigate colorcontrast's impact, beyond skin tones, on malignancy detection in skin diseasedatasets: We hypothesize that in addition to skin tones, the color differencebetween the lesion area and skin also plays a role in malignancy detectionperformance of dermatology AI models. To study this, we first propose a robustlabeling method to quantify color contrast scores of each image and validateour method by showing small labeling variations. More importantly, applying ourmethod to \textit{the only} diverse-skin tone and pathologically-confirmed skindisease dataset DDI, yields \textbf{DDI-CoCo Dataset}, and we observe aperformance gap between the high and low color difference groups. Thisdisparity remains consistent across various state-of-the-art (SoTA) imageclassification models, which supports our hypothesis. Furthermore, we study theinteraction between skin tone and color difference effects and suggest thatcolor difference can be an additional reason behind model performance biasbetween skin tones. Our work provides a complementary angle to dermatology AIfor improving skin disease detection.

DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection