Skip to content

Iterative reconstruction via preserved structures approach for CT images with limited scan angles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Iterative image reconstruction techniques for computer tomography (CT) are finite iterations of forward-projections and backward projections. One of the major concerns related to this method is deterioration of the reconstructed images due to various image structure deformations during this procedure. This is usually manifested by blotchy and pixelated appearances of the reconstructed image with the effects becoming more pronounced for low and ultra-low scan angles. This paper proposes a new approach for the reconstruction of CT images ensuring the preservation of structural details and reduced image deterioration and deformation. We call this method iterative reconstruction through preserved structures (IR-PS). The results achieved using proposed IR-PS method are evaluated via RMSE (Root Mean Square Error) measure and SSIM (Structural SIMiliarity) index suggesting improvement in quality of reconstructed images.
Original languageEnglish
Title of host publicationIMIP '19: Proceedings of the 2019 International Conference on Intelligent Medicine and Image Processing
PublisherAssociation for Computing Machinery
Pages72-77
Number of pages6
ISBN (Print)978-1-4503-6269-6
DOIs
Publication statusPublished - 22 Apr 2019
Event3rd International Conference on Frontiers of Image Processing - Florence, Italy
Duration: 16 Mar 201918 Mar 2019
http://www.icfip.org/

Conference

Conference3rd International Conference on Frontiers of Image Processing
Abbreviated titleICFIP 2019
CountryItaly
CityFlorence
Period16/03/1918/03/19
Internet address

Documents

  • P004paperBV

    Rights statement: © Association for Computing Machinery 2019. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 2019 International Conference on Intelligent Medicine and Image Processing, http://dx.doi.org/10.1145/3332340.3332354.

    Accepted author manuscript (Post-print), 599 KB, PDF document

Related information

Relations Get citation (various referencing formats)

ID: 12820351