A shearlet-based deep learning approach to limited-angle tomographyMS50

In computed tomography (CT), one of the key issues is the limited angle problem. Traditional imaging methodologies are not capable of reconstructing the complete image satisfactorily. In this talk, we will present a deep learning approach to this problem using shearlets as a sparsifying transform.

This presentation is part of Minisymposium “MS50 - Analysis, Optimization, and Applications of Machine Learning in Imaging (3 parts)
organized by: Michael Moeller (University of Siegen) , Gitta Kutyniok (Technische Universität Berlin) .

Gitta Kutyniok (Technische Universität Berlin)
Maximilian März (Technische Universität Berlin)
Wojciech Samek (Fraunhofer Institute for Telecommunications–Heinrich Hertz Institute)
Vignesh Srinivasan (Fraunhofer Institute for Telecommunications–Heinrich Hertz Institute)
computed tomography, deep learning, image reconstruction, inverse problems