In this talk, I will introduce a new algorithm for Computed Tomography that simultaneously computes a reconstruction and a corresponding segmentation. Our algorithm uses learned dictionaries for both the reconstruction and the segmentation, constructed via discriminative dictionary learning using a set of corresponding images and segmentations. Numerical simulations demonstrate that our method provides better results than the other simultaneous reconstruction and segmentation methods or dictionary-based methods, especially when there are not sufficient projections.

This presentation is part of Minisymposium “MS43 - Variational Image Segmentation: Methods and Applications”
organized by: Jack Spencer (University of Liverpool) .

Authors:

Yiqiu Dong (Technical University of Denmark)

Per Christian Hansen (Technical University of Denmark)

Hans Martin Kjer (Technical University of Denmark)

Keywords:

computed tomography, image reconstruction, image segmentation, inverse problems