Limited-angle computed tomography with deep image and physics priors

Semih Barutcu*, Selin Aslan, Aggelos K. Katsaggelos, Doğa Gürsoy

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

7 Scopus citations


Computed tomography is a well-established x-ray imaging technique to reconstruct the three-dimensional structure of objects. It has been used extensively in a variety of fields, from diagnostic imaging to materials and biological sciences. One major challenge in some applications, such as in electron or x-ray tomography systems, is that the projections cannot be gathered over all the angles due to the sample holder setup or shape of the sample. This results in an ill-posed problem called the limited angle reconstruction problem. Typical image reconstruction in this setup leads to distortion and artifacts, thereby hindering a quantitative evaluation of the results. To address this challenge, we use a generative model to effectively constrain the solution of a physics-based approach. Our approach is self-training that can iteratively learn the nonlinear mapping from partial projections to the scanned object. Because our approach combines the data likelihood and image prior terms into a single deep network, it is computationally tractable and improves performance through an end-to-end training. We also complement our approach with total-variation regularization to handle high-frequency noise in reconstructions and implement a solver based on alternating direction method of multipliers. We present numerical results for various degrees of missing angle range and noise levels, which demonstrate the effectiveness of the proposed approach.

Original languageEnglish (US)
Article number17740
JournalScientific reports
Issue number1
StatePublished - Dec 2021

ASJC Scopus subject areas

  • General


Dive into the research topics of 'Limited-angle computed tomography with deep image and physics priors'. Together they form a unique fingerprint.

Cite this