M20. Inverse Problems in Tomography: Theory, Simulation, and Emerging AI Methods

Tomographic reconstruction is one of the most well-known inverse problems. Despite tomography’s long history, the fundamental interest in it remains unbroken as novel theoretical developments fuel new applications in tomography and, conversely, novel technologies and applications demand an even deeper understanding of the mathematical theory.

This minisymposium aims to bring together leading and upcoming researchers working at the intersection of theory and application, creating bridges between classical approaches and modern innovations. Topics may include the analysis of related operators (such as the Radon transform), microlocal analysis of tomographic inverse problems, uncertainty quantification, and regularization techniques. In addition, the session will highlight the growing impact of machine learning—particularly deep learning methods—in tomographic reconstruction, including data-driven solvers, learned priors, and hybrid models that integrate physics-based and AI-based approaches. Applications span a wide range of imaging sciences, from medical diagnostics and industrial inspection to geophysics, astronomy, and beyond.

Organizers:
Anuj Abhishek, Case Western Reserve University, USA, This email address is being protected from spambots. You need JavaScript enabled to view it.
Richard Huber, University of Graz, Austria, This email address is being protected from spambots. You need JavaScript enabled to view it.
Thilo Strauss, Xi’an Jiaotong-Liverpool University, China, This email address is being protected from spambots. You need JavaScript enabled to view it.

Invited Speakers:
Jonas Bresch, Technical University of Berlin, Germany, This email address is being protected from spambots. You need JavaScript enabled to view it. 
Generalized Radon cumulative distribution transform for pattern recognition

Weihong Guo, Case Western Reserve University, USA, This email address is being protected from spambots. You need JavaScript enabled to view it. 
Fusion-based 3D image super-resolution from truncated k-space data in quantitative magnetic resonance imaging

Benjamin Hackl, University of Graz, Austria, This email address is being protected from spambots. You need JavaScript enabled to view it.
Gratopy: a toolbox for tomographic reconstruction using pixel-driven projection methods

Sean Holman, University of Manchester, UK, This email address is being protected from spambots. You need JavaScript enabled to view it. 
Inverse problems for strain

Luke Lozenski, Technical University of Denmark, Denmark, This email address is being protected from spambots. You need JavaScript enabled to view it. 
Neural representations as proximal regularizers for nano-CT imaging of sustainable cement formulations

Todd Quinto, Tufts University, USA, This email address is being protected from spambots. You need JavaScript enabled to view it. 
A unified perspective on microlocal artifacts in limited data tomography and inverse problems

Marion Savanier, Université Paris-Saclay, France, This email address is being protected from spambots. You need JavaScript enabled to view it.
Plug-and-Play for PET reconstruction with MRI guidance