ScholarDeck

AI / informaticsJournal of the American Medical Informatics Association : JAMIA · 2026

Fairness aware subset selection for advancing equity in skin cancer detection.

Yehuda Perry, Abdulaziz A Almuzaini, Adewole S Adamson … Vivek K Singh

Read paper

DermatologyAI / informatics

FAIR-SCAN improves fairness in skin cancer detection with a smaller training dataset.

Fairness aware subset selection for advancing equity in skin cancer detection.

Yehuda Perry et al. · Journal of the American Medical Informatics Association : JAMIA · 2026

Background

Skin cancer is the most common malignancy in the United States, with more than five million cases diagnosed annually among 3.3 million individuals.

Purpose

Skin cancer is the most common malignancy in the United States, with more than five million cases diagnosed annually among 3.3 million individuals.

Methods

We evaluated its effectiveness using images from Diverse Dermatology Images (DDI) and Fitzpatrick 17K.

50%

Results

FAIR-SCAN achieved its improvements with half the training images

More results

DISCUSSION: These findings highlight the importance of strategic data selection in mitigating bias in AI-driven diagnostics.

FAIR-SCAN's data-centric approach enhances both precision and equity in skin cancer detection.

“

Conclusion

Strategic data selection is critical for equitable AI-driven diagnostics. FAIR-SCAN advances fairness and accuracy in skin cancer detection, supporting development of trustworthy clinical AI systems.

Post

Fairness aware subset selection for advancing equity in skin cancer detection.

FAIR-SCAN improves fairness in skin cancer detection with a smaller training dataset.

Related papers