Crossmark

A two-stage deep learning approach for forensic age and sex determination from hand-wrist radiographs: an anatomical pose estimation and multi-task model

Crossref DOI link: https://doi.org/10.1007/s00414-026-03729-w

Published Online: 2026-03-07

Published Print: 2026-07

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Çatak, Cumali https://orcid.org/0000-0003-1721-5182
Ocak, Mert https://orcid.org/0000-0001-6832-6208
Çolak, Doğan https://orcid.org/0009-0001-1544-7062
Funding

Funding for this research was provided by:

Social Science University of Ankara
License Information

Text and Data Mining valid from 2026-03-07

Version of Record valid from 2026-03-07
More Information

Article History

Received: 19 November 2025

Accepted: 18 January 2026

First Online: 7 March 2026

Declarations

:

: This study uses publicly available radiographic datasets (RSNA and Roboflow HandBone). No human subjects were recruited and no additional radiographic data were acquired; therefore, ethical approval was not required.

: Informed consent was not required as the study utilized anonymized, publicly available datasets.

: The authors have no relevant financial or non-financial interests to disclose. All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.

Document is current

Any future updates will be listed below