Tomographic image reconstruction using training images

Research output: Contribution to journalJournal articleResearchpeer-review

187 Downloads (Pure)


We describe and examine an algorithm for tomographic image reconstruction where prior knowledge about the solution is available in the form of training images. We first construct a non-negative dictionary based on prototype elements from the training images; this problem is formulated within the framework of sparse learning as a regularized non-negative matrix factorization. Incorporating the dictionary as a prior in a convex reconstruction problem, we then find an approximate solution with a sparse representation in the dictionary. The dictionary is applied to non-overlapping patches of the image, which reduces the computational complexity compared to previous formulations. Computational experiments clarify the choice and interplay of the model parameters and the regularization parameters, and we show that in few-projection low-dose settings our algorithm is competitive with total variation regularization and tends to include more texture and more correct edges.
Original languageEnglish
JournalJournal of Computational and Applied Mathematics
Pages (from-to)243-258
Publication statusPublished - 2017


  • Tomography
  • Dictionary learning
  • Inverse problems
  • Regularization
  • Image reconstruction

Fingerprint Dive into the research topics of 'Tomographic image reconstruction using training images'. Together they form a unique fingerprint.

Cite this