A neural network to create super‐resolution MR from multiple 2D brain scans of pediatric patients
We demonstrate that deep learning methods can successfully reconstruct 3D HR images from 2D LR ones, potentially unlocking datasets for retrospective study and advancing research in the long-term effects of pediatric cancer. Our model outperforms standard interpolation, both in perceptual quality and for autocontouring. Further work is needed to validate it for additional structural analysis tasks.
Authors
- Marcel van Herk (ORCID: https://orcid.org/0000-0001-6448-898X)
- Eliana Vásquez Osorio (ORCID: https://orcid.org/0000-0003-0741-994X)
- Anna France (ORCID: https://orcid.org/0000-0002-6227-9401)
- A. Davey (ORCID: https://orcid.org/0000-0002-8377-5113)
- Ed Smith (ORCID: https://orcid.org/0000-0002-4849-1465)
- Marianne Aznar (ORCID: https://orcid.org/0000-0001-6452-0310)
- J. Benitez-Aurioles
- Peter Sitch (ORCID: https://orcid.org/0009-0007-0367-6814)
- Shermaine Pan
Institutions
- Manchester Academic Health Science Centre (GB)
- University of Manchester (GB)
- The Christie NHS Foundation Trust (GB)
Publication Details
- Journal
- Medical Physics
- Published
- 2024-12-10
- DOI
- https://doi.org/10.1002/mp.17563
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Cancer Research UK
- National Institute for Health and Care Research
- National Institutes of Health
- Manchester Biomedical Research Centre
- Medical Research Council
- Engineering and Physical Sciences Research Council