Reconstruction in inverse problems is often one step in a procedure where the reconstructions is used for decision making associated to a task. The talk will use statistical decision theory for extending recent iterative learned methods to include tasks that can be formulated as a supervised learning task, e.g., segmentation, comparison, classification, registration, or caption generation. We will outline this framework and show examples of task based reconstructions in the context of tomographic imaging.

This presentation is part of Minisymposium “MS65 - Machine learning techniques for image reconstruction (2 parts)”
organized by: Markus Haltmeier (University Innsbruck) , Linh Nguyen (University of Idaho) .

Authors:

Ozan Öktem (KTH - Royal Institute of Technology)

Jonas Adler (KTH Royal Institute of Technology)

Keywords:

computed tomography, computer vision, deep learning, image compression, image reconstruction, image registration, image segmentation, inverse problems, machine learning, statistical inverse estimation methods