Dual energy CT and deep learning for an automated volumetric segmentation of the major intracranial tissues: Feasibility and initial findings
This study demonstrates the feasibility of CT-based segmentation of intracranial tissue using DL and VMI. The improved accuracy of the U-Net++ (Aug) compared to the baseline model suggests that spectral information may enhance segmentation performance.
Authors
- Kristina Ydström (ORCID: https://orcid.org/0000-0001-5542-8395)
- Filip Winzell
- Birgitta Ramgren (ORCID: https://orcid.org/0000-0002-7510-431X)
- Veronica Fransson (ORCID: https://orcid.org/0000-0001-5922-3282)
- Sören Christensen (ORCID: https://orcid.org/0000-0003-1242-3724)
- Johan Wassélius (ORCID: https://orcid.org/0000-0003-1896-381X)
- Ida Arvidsson
- Kalle Åström
- Niels Christian Overgaard
- Anders Heyden
Institutions
- Statistics Sweden (SE)
- Schlumberger (British Virgin Islands) (VG)
- Malmö University (SE)
- Lund University (SE)
- Skåne University Hospital (SE)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-12-21
- DOI
- https://doi.org/10.1002/mp.70217
- Primary Topic
- Advanced X-ray and CT Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- VINNOVA
- Skånes universitetssjukhus