Revisiting $Ψ$DONet: microlocally inspired filters for incomplete-data tomographic reconstructions
This work addresses tomographic reconstruction challenges for medical or scientific imaging, but it is incremental as it builds on an existing supervised learning approach.
The paper tackles the problem of incomplete-data tomographic reconstructions by revisiting the $\Psi$DONet method, refining its implementation with microlocally inspired filters to reduce parameters while maintaining or slightly improving reconstruction quality, achieving a proof-of-concept for sparse-angle data.
In this paper, we revisit a supervised learning approach based on unrolling, known as $Ψ$DONet, by providing a deeper microlocal interpretation for its theoretical analysis, and extending its study to the case of sparse-angle tomography. Furthermore, we refine the implementation of the original $Ψ$DONet considering special filters whose structure is specifically inspired by the streak artifact singularities characterizing tomographic reconstructions from incomplete data. This allows to considerably lower the number of (learnable) parameters while preserving (or even slightly improving) the same quality for the reconstructions from limited-angle data and providing a proof-of-concept for the case of sparse-angle tomographic data.