Image space formalism of convolutional neural networks for k‐space interpolation
The image space formalism of RAKI provides the means for analytical quantitative noise-propagation analysis and human-readable visualization of the effects of the nonlinear activation functions in k-space.
Authors
- István Homolya (ORCID: https://orcid.org/0000-0002-0662-6464)
- Maximilian Gram (ORCID: https://orcid.org/0000-0003-2184-3325)
- Peter Dawood (ORCID: https://orcid.org/0000-0001-7127-607X)
- Peter M. Jakob (ORCID: https://orcid.org/0000-0002-3481-5545)
- Martin Blaimer (ORCID: https://orcid.org/0000-0002-6360-9871)
- Felix Breuer
Institutions
- University of Würzburg (DE)
- Universitätsklinikum Erlangen (DE)
- Fraunhofer Institute for Integrated Circuits (DE)
- Universitätsklinikum Würzburg (DE)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2025-08-05
- DOI
- https://doi.org/10.1002/mrm.70002
- Citations
- 1
- Primary Topic
- Medical Image Segmentation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 1.28