Explainable multimodal AI for skin lesion risk prediction via 3D imaging and clinical data

Zheng Wang, Mengnan Tai, Hui Hu, Hao Yuan, Chong Wang, Hongyang Fu, Jianglin Zhang · 2025

Read Explainable multimodal AI for skin lesion risk prediction via 3D imaging and clinical data by Zheng Wang, Mengnan Tai, Hui Hu, Hao Yuan, Chong Wang, Hongyang Fu, Jianglin Zhang (2025) 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/pmc-12749747.txt.

Description

Zheng Wang and co-authors build an explainable AI that judges skin spot risk from full-body 3D photos plus medical facts, in a 2025 paper. Skin lesions vary wildly in look, and judging them taxes even experts. Black-box AI may score well yet leave doctors unable to see its reasons.

Using a public data set of 1,075 patients, the team extracted 41 clinical and lesion features and full-body 3D images. A plain regression model handled the facts, while image networks read the photos; explanation tools then showed which features and image areas drove each call. Image models reached about 87 percent accuracy on their test task. Transparent risk scores could help dermatology teams triage moles with more trust.

Catalog record

CREATORZheng Wang, Mengnan Tai, Hui Hu, Hao Yuan, Chong Wang, Hongyang Fu, Jianglin Zhang
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE31 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12749747

Browse the full library · About the Tower of Babel