Joint reconstruction and segmentation from undersampled MRI dataMS5

Magnetic resonance imaging often deals with fast acquisition techniques and incomplete measurements, posing challenges in the reconstruction and further analysis of the data (e.g. segmentation). We propose a method to jointly reconstruct and segment undersampled MRI data. Our model consists of a total variation regularised reconstruction and a Chan-Vese based segmentation. We develop an algorithm based on a splitting approach that solves efficiently the two minimisation subproblems. We present results for synthetic and real data.

This presentation is part of Minisymposium “MS5 - Learning and adaptive approaches in image processing (2 parts)
organized by: Kostas Papafitsoros (Weierstrass Institute Berlin) , Michael Hintermüller (Humboldt University and Weierstrass Institute Berlin) .

Veronica Corona (University of Cambridge)
image reconstruction, image segmentation, inverse problems