Analysis of medical images often proceeds by applying classification approaches from machine vision, under the assumption that the images have been robustly reconstructed. In the case of strongly ill-posed inverse problems the reconstruction process can lead to considerable artefact in the images which can degrade this classification step. In this talk we present an approach that applies classification algorithms within iterative reconstruction algorithms. Results are presented for some non-linear tomography problems.

This presentation is part of Minisymposium “MS23 - Multi-Modality/Multi-Spectral Imaging and Structural Priors (2 parts)”
organized by: Matthias J. Ehrhardt (University of Cambridge) , Simon Arridge (University College London) .

Authors:

Simon Arridge (University College London)

Keywords: