Transformer-based and CNN-based models for clinically effective 2D and 3D pelvic bone segmentation in CT imaging
Our results confirm the efficacy of deep learning-based segmentation for pelvic fracture analysis, with high accuracy and computational efficiency supporting potential clinical integration. The models presented here demonstrate high accuracy and computational efficiency, offering a strong foundation for potential clinical integration into automated trauma imaging systems, pending external validation and workflow assessment.
Authors
- Shabnam Jafarpoor Nesheli
- Seyed Masoud Rezaeijo (ORCID: https://orcid.org/0000-0002-4525-0025)
- Maryam Sabet
- Parvin Sadat Mirzaghavami (ORCID: https://orcid.org/0000-0003-2779-0842)
- Mohammadreza Elhaie
- Abolfazl Koozari (ORCID: https://orcid.org/0009-0009-5149-8914)
- Maryam Abidi
- Alireza Eftekhar
- Najme Janghorban Lariche
- Saleh Rouhi (ORCID: https://orcid.org/0009-0001-2313-1068)
Institutions
- Isfahan University of Medical Sciences (IR)
- Zanjan University of Medical Sciences (IR)
- University of Science and Culture (IR)
- Ahvaz Jundishapur University of Medical Sciences (IR)
- Kermanshah University of Medical Sciences (IR)
- Technical and Vocational University (IR)
- Fasa University of Medical Sciences (IR)
Publication Details
- Journal
- BMC Musculoskeletal Disorders
- Published
- 2025-12-26
- DOI
- https://doi.org/10.1186/s12891-025-09444-8
- Primary Topic
- Pelvic and Acetabular Injuries
- Type
- article
- Field-Weighted Citation Impact
- 0.00