Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography

Tatiana Bubba, Mathilde Galinier, Matti Lassas, Marco Prato, Luca Ratti, Samuli Siltanen

Research output: Contribution to journalArticlepeer-review

11 Citations (SciVal)


We propose a novel convolutional neural network (CNN), called ΨDONet, designed for learning pseudodifferential operators (ΨDOs) in the context of linear inverse problems. Our starting point is the Iterative Soft Thresholding Algorithm (ISTA), a well-known algorithm to solve sparsity-promoting minimization problems. We show that, under rather general assumptions on the forward operator, the unfolded iterations of ISTA can be interpreted as the successive layers of a CNN, which in turn provides fairly general network architectures that, for a specific choice of the parameters involved, allow to reproduce ISTA, or a perturbation of ISTA for which we can bound the coefficients of the filters. Our case study is the limited-angle X-ray transform and its application to limited-angle computed tomography (LA-CT). In particular, we prove that, in the case of LA-CT, the operations of upscaling, downscaling and convolution, which characterize our ΨDONet and most deep learning schemes, can be exactly determined by combining the convolutional nature of the limited angle X-ray transform and basic properties defining an orthogonal wavelet system. We test two different implementations of ΨDONet on simulated data from limited angle geometry, generated from the ellipse data set. Both implementations provide equally good and noteworthy preliminary results, showing the potential of the approach we propose and paving the way to applying the same idea to other convolutional operators which are ΨDOs or Fourier integral operators.
Original languageEnglish
Pages (from-to)470-505
Number of pages36
JournalSIAM Journal on Imaging Sciences
Issue number2
Early online date3 May 2021
Publication statusPublished - 31 Dec 2021


Dive into the research topics of 'Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography'. Together they form a unique fingerprint.

Cite this