Evaluating skin tone scales for dermatologic dataset labeling: a prospective-comparative study
Vanessa R Weir, Yingjoy Li, Maura C Gillis, Nicholas R Kurtansky, Trina Salvador, Allan C Halpern, Kelly C Nelson, Jenna C Lester, Veronica Rotemberg · 2025
Read Evaluating skin tone scales for dermatologic dataset labeling: a prospective-comparative study by Vanessa R Weir, Yingjoy Li, Maura C Gillis, Nicholas R Kurtansky, Trina Salvador, Allan C Halpern, Kelly C Nelson, Jenna C Lester, Veronica Rotemberg (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-12749783.txt.
Description
Vanessa Weir and co-authors compare skin tone scales for labeling photo datasets in a 2025 study. Skin tone shapes how AI tools score skin disease, so sound labels could help those tools work for all patients. The team tested three hand scales plus a light meter, in person and from photos.
The light meter gave the most exact in-person values. Of the hand scales, the Monk scale grouped tones most tightly and repeated best, though photo scores shifted with light. Tone values pulled from scope images matched the meter poorly. The Monk scale also split AI melanoma scores better than the older Fitzpatrick scale.
Catalog record
| CREATOR | Vanessa R Weir, Yingjoy Li, Maura C Gillis, Nicholas R Kurtansky, Trina Salvador, Allan C Halpern, Kelly C Nelson, Jenna C Lester, Veronica Rotemberg |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |