Predicting biological sex in pediatric skeleton X-rays using artificial intelligence
Michael Janisch, Mario Scherkl, Nikolaus Stranger, Hesham Elsayed, Georg Singer, Holger Till, Michael Zellner, Franko Hržić, Sebastian Tschauner · 2025
Read Predicting biological sex in pediatric skeleton X-rays using artificial intelligence by Michael Janisch, Mario Scherkl, Nikolaus Stranger, Hesham Elsayed, Georg Singer, Holger Till, Michael Zellner, Franko Hržić, Sebastian Tschauner (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-12728230.txt.
Description
Michael Janisch and eight co-authors published a 2025 study on computer reading of children's X-rays. Their team asked whether a trained program could predict a child's sex from bone images. They used a large set of trauma scans from young patients. They also asked human raters to judge a smaller set of images for comparison.
The program sorted the scans with fair accuracy across several model sizes. Scores rose with age and were best for teens and for pelvic scans. Human raters agreed with each other far less than the program did. The authors say such tools may help in clinics that read images of children. They also note that results vary by body region and age group.
Catalog record
| CREATOR | Michael Janisch, Mario Scherkl, Nikolaus Stranger, Hesham Elsayed, Georg Singer, Holger Till, Michael Zellner, Franko Hržić, Sebastian Tschauner |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |