Attention guided fair artificial intelligence modeling for skin cancer diagnosis

Mingcheng Zhu, Mingxuan Liu, Han Yuan, Yilin Ning, Zhiyao Luo, Tingting Zhu, Nan Liu · 2026

Read Attention guided fair artificial intelligence modeling for skin cancer diagnosis by Mingcheng Zhu, Mingxuan Liu, Han Yuan, Yilin Ning, Zhiyao Luo, Tingting Zhu, Nan Liu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13638983.txt.

Description

Mingcheng Zhu and six colleagues report a 2026 artificial intelligence system designed to diagnose skin cancer more fairly across genders. Earlier fairness work focused on skin tone, while gender bias in skin image models had received little attention.

Their algorithm, LesionAttn, steers the model's attention toward the lesion itself, much as a clinician would focus on the spot rather than surrounding features. Tested on two large image collections, it cut gender bias while keeping accuracy high, beating other bias-reduction methods. The authors present attention guidance as a practical route toward diagnostic tools that serve patients more evenly.

Catalog record

CREATORMingcheng Zhu, Mingxuan Liu, Han Yuan, Yilin Ning, Zhiyao Luo, Tingting Zhu, Nan Liu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE35300
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13638983

Browse the full library · About the Tower of Babel