Treffer: Simultaneous Reconstruction and Segmentation of CT Scans with Shadowed Data
Title:
Simultaneous Reconstruction and Segmentation of CT Scans with Shadowed Data
Authors:
Contributors:
Department of Computer Science [Copenhagen] (DIKU), Faculty of Science [Copenhagen], University of Copenhagen = Københavns Universitet (UCPH)-University of Copenhagen = Københavns Universitet (UCPH), Technische Universität Munchen - Technical University Munich - Université Technique de Munich (TUM)
Source:
Sixth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM). :308-319
Publisher Information:
HAL CCSD, 2017.
Publication Year:
2017
Collection:
collection:COMUE-NORMANDIE
Subject Geographic:
Original Identifier:
HAL: hal-02118564
Document Type:
Konferenz
conferenceObject<br />Conference papers
Language:
English
Relation:
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-319-58771-4_25
DOI:
10.1007/978-3-319-58771-4_25
Access URL:
Rights:
info:eu-repo/semantics/OpenAccess
Accession Number:
edshal.hal.02118564v1
Database:
HAL
Weitere Informationen
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 minimi-sation 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.