Deep learning-based segmentation of ultra-low-dose CT images using an optimized nnU-Net model
Conventional FD-nnU-Net models performed poorly on LD-CT images. Dedicated LD-nnU-Net models demonstrated superior performance across cross-validation and external evaluations, enabling accurate segmentation of ultra-low-dose CT images. The trained models are available on our GitHub page.
Authors
- Yazdan Salimi (ORCID: https://orcid.org/0000-0002-1233-9576)
- Habib Zaidi (ORCID: https://orcid.org/0000-0001-7559-5297)
- Sana Boudabbous (ORCID: https://orcid.org/0000-0003-0516-4613)
- René Nkoulou (ORCID: https://orcid.org/0000-0001-6192-0351)
- Hossein Shooli
- Chang Sun (ORCID: https://orcid.org/0000-0002-7039-889X)
- Zahra Mansouri (ORCID: https://orcid.org/0000-0003-2087-9721)
- Mohammad Javad Yazdanpanah (ORCID: https://orcid.org/0000-0001-7098-8331)
- Amirhossein Sanaat (ORCID: https://orcid.org/0000-0001-8437-2060)
Institutions
- Obuda University (HU)
- University Medical Center Groningen (NL)
- Beijing University of Posts and Telecommunications (CN)
- University of Groningen (NL)
- University of Southern Denmark (DK)
- Shiraz University of Medical Sciences (IR)
- University Hospital of Geneva (CH)
- Bushehr University of Medical Sciences (IR)
Publication Details
- Journal
- La radiologia medica
- Published
- 2025-03-18
- DOI
- https://doi.org/10.1007/s11547-025-01989-x
- Citations
- 8
- Primary Topic
- Advanced X-ray and CT Imaging
- Type
- article
- Field-Weighted Citation Impact
- 5.39
Funders
- National Science Foundation
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Université de Genève
- Horizon 2020 Framework Programme
- H2020 Euratom