Automatic rib fracture detection on postmortem CT data using deep learning
The performance of nnDetPM, with an average sensitivity of 70.2%, was notable and comparable to that of radiologists. However, more advanced techniques must be explored to decide if DL models can overcome the domain shift factors.
Authors
- Vincent Andrearczyk (ORCID: https://orcid.org/0000-0003-0793-5821)
- Adrien Depeursinge (ORCID: https://orcid.org/0000-0002-2362-0304)
- Silke Grabherr (ORCID: https://orcid.org/0000-0002-9914-2310)
- Stéphane Marchand‐Maillet (ORCID: https://orcid.org/0000-0002-4875-6101)
- Virginie Magnin
- Manel Lopez-Melia (ORCID: https://orcid.org/0009-0004-5195-2543)
- Sami Schranz (ORCID: https://orcid.org/0000-0002-9151-1433)
Institutions
- University of Geneva (CH)
- HES-SO University of Applied Sciences and Arts Western Switzerland (CH)
- University Centre of Legal Medicine (CH)
- University of Lausanne (CH)
Publication Details
- Journal
- International Journal of Legal Medicine
- Published
- 2025-12-04
- DOI
- https://doi.org/10.1007/s00414-025-03669-x
- Citations
- 2
- Primary Topic
- Trauma Management and Diagnosis
- Type
- article
- Field-Weighted Citation Impact
- 4.01
Funders
- Université de Genève