Simultaneous reconstruction and segmentation of CT scans with shadowed data

TY - GEN

T1 - Simultaneous reconstruction and segmentation of CT scans with shadowed data

AU - Lauze, Francois Bernard

AU - Quéau, Yvain

AU - Plenge, Esben

N1 - Conference code: 6

PY - 2017/6

Y1 - 2017/6

N2 - We propose a variational approach for simultaneous reconstruction and multiclass segmentation of X-ray CT images, with limited field of view and missing data. We propose a simple energy minimisation approach, loosely based on a Bayesian rationale. The resulting non convex problem is solved by alternating reconstruction steps using an iterated relaxed proximal gradient, and a proximal approach for the segmentation. Preliminary results on synthetic data demonstrate the potential of the approach for synchrotron imaging applications.

AB - We propose a variational approach for simultaneous reconstruction and multiclass segmentation of X-ray CT images, with limited field of view and missing data. We propose a simple energy minimisation approach, loosely based on a Bayesian rationale. The resulting non convex problem is solved by alternating reconstruction steps using an iterated relaxed proximal gradient, and a proximal approach for the segmentation. Preliminary results on synthetic data demonstrate the potential of the approach for synchrotron imaging applications.

U2 - 10.1007/978-3-319-58771-4_25

DO - 10.1007/978-3-319-58771-4_25

M3 - Article in proceedings

SN - 978-3-319-58770-7

T3 - Lecture notes in computer science

SP - 308

EP - 319

BT - Scale Space and Variational Methods in Computer Vision

A2 - Lauze, Francois

A2 - Dong, Yiqiu

A2 - Dahl, Anders Bjorholm

PB - Springer

T2 - 6th International Conference on Scale Space and Variational Methods in Computer Vision

Y2 - 4 June 2017 through 8 June 2017

ER -