Image Restoration Using Functional and Anatomical Information Fusion with Application to SPECT-MRI Images

Image restoration is usually viewed as an ill-posed problem in image processing, since there is no unique solution associated with it. The quality of restored image closely depends on the constraints imposed of the characteristics of the solution. In this paper, we propose an original extension of t...

Full description

Saved in:
Bibliographic Details
Main Authors: S. Benameur, M. Mignotte, J. Meunier, J.-P. Soucy
Format: Article
Language:English
Published: Wiley 2009-01-01
Series:International Journal of Biomedical Imaging
Online Access:http://dx.doi.org/10.1155/2009/843160
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850216875097587712
author S. Benameur
M. Mignotte
J. Meunier
J.-P. Soucy
author_facet S. Benameur
M. Mignotte
J. Meunier
J.-P. Soucy
author_sort S. Benameur
collection DOAJ
description Image restoration is usually viewed as an ill-posed problem in image processing, since there is no unique solution associated with it. The quality of restored image closely depends on the constraints imposed of the characteristics of the solution. In this paper, we propose an original extension of the NAS-RIF restoration technique by using information fusion as prior information with application in SPECT medical imaging. That extension allows the restoration process to be constrained by efficiently incorporating, within the NAS-RIF method, a regularization term which stabilizes the inverse solution. Our restoration method is constrained by anatomical information extracted from a high resolution anatomical procedure such as magnetic resonance imaging (MRI). This structural anatomy-based regularization term uses the result of an unsupervised Markovian segmentation obtained after a preliminary registration step between the MRI and SPECT data volumes from each patient. This method was successfully tested on 30 pairs of brain MRI and SPECT acquisitions from different subjects and on Hoffman and Jaszczak SPECT phantoms. The experiments demonstrated that the method performs better, in terms of signal-to-noise ratio, than a classical supervised restoration approach using a Metz filter.
format Article
id doaj-art-2f58a454752e4a4994508b9f0d606a28
institution OA Journals
issn 1687-4188
1687-4196
language English
publishDate 2009-01-01
publisher Wiley
record_format Article
series International Journal of Biomedical Imaging
spelling doaj-art-2f58a454752e4a4994508b9f0d606a282025-08-20T02:08:12ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962009-01-01200910.1155/2009/843160843160Image Restoration Using Functional and Anatomical Information Fusion with Application to SPECT-MRI ImagesS. Benameur0M. Mignotte1J. Meunier2J.-P. Soucy3Department of Computer Science and Operations Research (DIRO), University of Montreal, CP 6128l, Station Centre-Ville, P.O. Box 6128, Montréal, QC, H3C 3J7, CanadaDepartment of Computer Science and Operations Research (DIRO), University of Montreal, CP 6128l, Station Centre-Ville, P.O. Box 6128, Montréal, QC, H3C 3J7, CanadaDepartment of Computer Science and Operations Research (DIRO), University of Montreal, CP 6128l, Station Centre-Ville, P.O. Box 6128, Montréal, QC, H3C 3J7, CanadaMcConnell Brain Imaging Centre, Montreal Neurological Institute, 3801 University Street, Montréal, QC, H3A 2B4, CanadaImage restoration is usually viewed as an ill-posed problem in image processing, since there is no unique solution associated with it. The quality of restored image closely depends on the constraints imposed of the characteristics of the solution. In this paper, we propose an original extension of the NAS-RIF restoration technique by using information fusion as prior information with application in SPECT medical imaging. That extension allows the restoration process to be constrained by efficiently incorporating, within the NAS-RIF method, a regularization term which stabilizes the inverse solution. Our restoration method is constrained by anatomical information extracted from a high resolution anatomical procedure such as magnetic resonance imaging (MRI). This structural anatomy-based regularization term uses the result of an unsupervised Markovian segmentation obtained after a preliminary registration step between the MRI and SPECT data volumes from each patient. This method was successfully tested on 30 pairs of brain MRI and SPECT acquisitions from different subjects and on Hoffman and Jaszczak SPECT phantoms. The experiments demonstrated that the method performs better, in terms of signal-to-noise ratio, than a classical supervised restoration approach using a Metz filter.http://dx.doi.org/10.1155/2009/843160
spellingShingle S. Benameur
M. Mignotte
J. Meunier
J.-P. Soucy
Image Restoration Using Functional and Anatomical Information Fusion with Application to SPECT-MRI Images
International Journal of Biomedical Imaging
title Image Restoration Using Functional and Anatomical Information Fusion with Application to SPECT-MRI Images
title_full Image Restoration Using Functional and Anatomical Information Fusion with Application to SPECT-MRI Images
title_fullStr Image Restoration Using Functional and Anatomical Information Fusion with Application to SPECT-MRI Images
title_full_unstemmed Image Restoration Using Functional and Anatomical Information Fusion with Application to SPECT-MRI Images
title_short Image Restoration Using Functional and Anatomical Information Fusion with Application to SPECT-MRI Images
title_sort image restoration using functional and anatomical information fusion with application to spect mri images
url http://dx.doi.org/10.1155/2009/843160
work_keys_str_mv AT sbenameur imagerestorationusingfunctionalandanatomicalinformationfusionwithapplicationtospectmriimages
AT mmignotte imagerestorationusingfunctionalandanatomicalinformationfusionwithapplicationtospectmriimages
AT jmeunier imagerestorationusingfunctionalandanatomicalinformationfusionwithapplicationtospectmriimages
AT jpsoucy imagerestorationusingfunctionalandanatomicalinformationfusionwithapplicationtospectmriimages