Generation of synthetic CT–like imaging of the spine from biplanar radiographs: comparison of different deep learning architectures
This study demonstrated the feasibility of generating spine sCT images from biplanar radiographs using GAN and CNN-INR models. While neither model achieved clinical-grade outputs, the GAN architecture showed greater potential for generating anatomically accurate and visually realistic images. These findings highlight the promise of sCT image generation from biplanar radiographs as an innovative approach to reducing radiation exposure and improving imaging accessibility, with GANs emerging as the more promising avenue for further research and clinical integration.
Authors
- Massimo Bottini
- Victor E. Staartjes (ORCID: https://orcid.org/0000-0003-1039-2098)
- Erik Edström (ORCID: https://orcid.org/0000-0002-8781-1169)
- Carlo Serra (ORCID: https://orcid.org/0000-0002-7305-550X)
- Luca Regli (ORCID: https://orcid.org/0000-0003-4639-4474)
- Raffaele Da Mutten (ORCID: https://orcid.org/0000-0002-2645-0865)
- Maria L. Gandía-González (ORCID: https://orcid.org/0000-0002-5683-1300)
- Olivier Zanier (ORCID: https://orcid.org/0000-0002-3286-3770)
- Adrian Elmi‐Terander (ORCID: https://orcid.org/0000-0002-3776-6136)
Institutions
- University of Lucerne (CH)
- University of Zurich (CH)
- Hospital Universitario La Paz (ES)
- Karolinska Institutet (SE)
- University Hospital of Zurich (CH)
Publication Details
- Journal
- Neurosurgical FOCUS
- Published
- 2025-07-01
- DOI
- https://doi.org/10.3171/2025.4.focus25170
- Citations
- 2
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 1.35