Population Shape Collapse in Large Deformation Registration of MR Brain Images

Wei Shao; Gary E Christensen; Hans J Johnson; Joo H Song; Oguz C Durumeric; Casey P Johnson; Joseph J Shaffer; Vincent A Magnotta; Jess G Fiedorowicz; John A Wemmie

doi:10.1109/CVPRW.2016.75

Conference proceeding

Population Shape Collapse in Large Deformation Registration of MR Brain Images

Wei Shao, Gary E Christensen, Hans J Johnson, Joo H Song, Oguz C Durumeric, Casey P Johnson, Joseph J Shaffer, Vincent A Magnotta, Jess G Fiedorowicz and John A Wemmie

2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp.549-557

06/2016

DOI: 10.1109/CVPRW.2016.75

View Online

Abstract

This paper examines the shape collapse problem that occurs when registering a pair of images or a population of images of the brain to a reference (target) image coordinate system using diffeomorphic image registration. Shape collapse occurs when a foreground or background structure in an image with non-zero volume is transformed into a set of zero or near zero volume as measured on a discrete voxel lattice in the target image coordinate system. Shape collapse may occur during image registration when the moving image has a structure that is either missing or does not sufficiently overlap the corresponding structure in the target image[4]. Such a problem is common in image registration algorithms with large degrees of freedom such as many diffeomorphic image registration algorithms. Shape collapse is a concern when mapping functional data. For example, loss of signal may occur when mapping functional data such as fMRI, PET, SPECT using a transformation with a shape collapse if the functional signal occurs at the collapse region. This paper proposes an novel shape collapse measurement algorithm to detect the regions of shape collapse after image registration in pairwise registration. We further compute the shape collapse for a population of pairwise transformations such as occurs when registering many images to a common atlas coordinate system. Experiments are presented using the SyN diffeomorphic image registration algorithm. We demonstrate how changing the input parameters to the SyN registration algorithm can mitigate some of the collapse image registration artifacts.

Brain

Image registration

Correlation

Shape

Shape measurement

diffeomorphic image registration

Urban areas

Lattices

shape collapse

Details

Title: Subtitle: Population Shape Collapse in Large Deformation Registration of MR Brain Images
Creators: Wei Shao - Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
Gary E Christensen - Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
Hans J Johnson - Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
Joo H Song - Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
Oguz C Durumeric - Dept. of Math., Univ. of Iowa, Iowa City, IA, USA
Casey P Johnson - Dept. of Radiol., Univ. of Iowa, Iowa City, IA, USA
Joseph J Shaffer - Dept. of Radiol., Univ. of Iowa, Iowa City, IA, USA
Vincent A Magnotta - Dept. of Radiol., Univ. of Iowa, Iowa City, IA, USA
Jess G Fiedorowicz - Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
John A Wemmie - Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA, USA
Resource Type: Conference proceeding
Publication Details: 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp.549-557
Publisher: IEEE
DOI: 10.1109/CVPRW.2016.75
ISSN: 2160-7508
eISSN: 2160-7516
Language: English
Date published: 06/2016
Academic Unit: Molecular Physiology and Biophysics; Psychiatry; Neurosurgery; Radiation Research Laboratory; Epidemiology; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; Radiology; Mathematics; Iowa Neuroscience Institute; Radiation Oncology
Record Identifier: 9984066146202771

Metrics

15 Record Views

2 Times Cited - Web of Science