Enhancing joint reconstruction and segmentation with non-convex Bregman iteration
Abstract
All imaging modalities such as computed tomography (CT), emission tomography and magnetic resonance imaging (MRI) require a reconstruction approach to produce an image. A common image processing task for applications that utilise those modalities is image segmentation, typically performed posterior to the reconstruction. We explore a new approach that combines reconstruction and segmentation in a unified framework. We derive a variational model that consists of a total variation regularised reconstruction from undersampled measurements and a Chan-Vese based segmentation. We extend the variational regularisation scheme to a Bregman iteration framework to improve the reconstruction and therefore the segmentation. We develop a novel alternating minimisation scheme that solves the non-convex optimisation problem with provable convergence guarantees. Our results for synthetic and real data show that both reconstruction and segmentation are improved compared to the classical sequential approach.
Cite
@article{arxiv.1807.01660,
title = {Enhancing joint reconstruction and segmentation with non-convex Bregman iteration},
author = {Veronica Corona and Martin Benning and Matthias J. Ehrhardt and Lynn F. Gladden and Richard Mair and Andi Reci and Andrew J. Sederman and Stefanie Reichelt and Carola-Bibiane Schoenlieb},
journal= {arXiv preprint arXiv:1807.01660},
year = {2019}
}