Quantitative assessment of single-image super-resolution in myocardial scar imaging

Hiroshi Ashikaga, Heidi L. Estner, Daniel Herzka, Elliot R. McVeigh, Henry R Halperin

Research output: Contribution to journalArticle

Abstract

Single-image super resolution is a process of obtaining a high-resolution image from a set of low-resolution observations by signal processing. While super resolution has been demonstrated to improve image quality in scaled down images in the image domain, its effects on the Fourier-based image acquisition technique, such as MRI, remains unknown. We performed high-resolution ex vivo late gadolinium enhancement (LGE) magnetic resonance imaging (0.4×0.4×0.4 mm3) in postinfarction swine hearts (n=24). The swine hearts were divided into the training set (n=14) and the test set (n=10), and in all hearts, low-resolution images were simulated from the high-resolution images. In the training set, super-resolution dictionaries with pairs of small matching patches of the high- and low-resolution images were created. In the test set, super resolution recovered high-resolution images from low-resolution images using the dictionaries. The same algorithm was also applied to patient LGE (n=4) to assess its effects. Compared with interpolated images, super resolution significantly improved basic image quality indices (P

Original languageEnglish (US)
Article number18000512
JournalIEEE Journal of Translational Engineering in Health and Medicine
Volume2
Issue number1
DOIs
StatePublished - 2014

Fingerprint

Image resolution
Optical resolving power
Cicatrix
Gadolinium
Imaging techniques
Swine
Glossaries
Image quality
Magnetic Resonance Imaging
Image acquisition
Magnetic resonance
Magnetic resonance imaging
Signal processing

Keywords

  • Image processing
  • image quality
  • magnetic resonance imaging
  • myocardial scar

ASJC Scopus subject areas

  • Biomedical Engineering
  • Medicine(all)

Cite this

@article{a24510bea0294ae68ba0b470f344777a,
title = "Quantitative assessment of single-image super-resolution in myocardial scar imaging",
abstract = "Single-image super resolution is a process of obtaining a high-resolution image from a set of low-resolution observations by signal processing. While super resolution has been demonstrated to improve image quality in scaled down images in the image domain, its effects on the Fourier-based image acquisition technique, such as MRI, remains unknown. We performed high-resolution ex vivo late gadolinium enhancement (LGE) magnetic resonance imaging (0.4×0.4×0.4 mm3) in postinfarction swine hearts (n=24). The swine hearts were divided into the training set (n=14) and the test set (n=10), and in all hearts, low-resolution images were simulated from the high-resolution images. In the training set, super-resolution dictionaries with pairs of small matching patches of the high- and low-resolution images were created. In the test set, super resolution recovered high-resolution images from low-resolution images using the dictionaries. The same algorithm was also applied to patient LGE (n=4) to assess its effects. Compared with interpolated images, super resolution significantly improved basic image quality indices (P",
keywords = "Image processing, image quality, magnetic resonance imaging, myocardial scar",
author = "Hiroshi Ashikaga and Estner, {Heidi L.} and Daniel Herzka and McVeigh, {Elliot R.} and Halperin, {Henry R}",
year = "2014",
doi = "10.1109/JTEHM.2014.2303806",
language = "English (US)",
volume = "2",
journal = "IEEE Journal of Translational Engineering in Health and Medicine",
issn = "2168-2372",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Quantitative assessment of single-image super-resolution in myocardial scar imaging

AU - Ashikaga, Hiroshi

AU - Estner, Heidi L.

AU - Herzka, Daniel

AU - McVeigh, Elliot R.

AU - Halperin, Henry R

PY - 2014

Y1 - 2014

N2 - Single-image super resolution is a process of obtaining a high-resolution image from a set of low-resolution observations by signal processing. While super resolution has been demonstrated to improve image quality in scaled down images in the image domain, its effects on the Fourier-based image acquisition technique, such as MRI, remains unknown. We performed high-resolution ex vivo late gadolinium enhancement (LGE) magnetic resonance imaging (0.4×0.4×0.4 mm3) in postinfarction swine hearts (n=24). The swine hearts were divided into the training set (n=14) and the test set (n=10), and in all hearts, low-resolution images were simulated from the high-resolution images. In the training set, super-resolution dictionaries with pairs of small matching patches of the high- and low-resolution images were created. In the test set, super resolution recovered high-resolution images from low-resolution images using the dictionaries. The same algorithm was also applied to patient LGE (n=4) to assess its effects. Compared with interpolated images, super resolution significantly improved basic image quality indices (P

AB - Single-image super resolution is a process of obtaining a high-resolution image from a set of low-resolution observations by signal processing. While super resolution has been demonstrated to improve image quality in scaled down images in the image domain, its effects on the Fourier-based image acquisition technique, such as MRI, remains unknown. We performed high-resolution ex vivo late gadolinium enhancement (LGE) magnetic resonance imaging (0.4×0.4×0.4 mm3) in postinfarction swine hearts (n=24). The swine hearts were divided into the training set (n=14) and the test set (n=10), and in all hearts, low-resolution images were simulated from the high-resolution images. In the training set, super-resolution dictionaries with pairs of small matching patches of the high- and low-resolution images were created. In the test set, super resolution recovered high-resolution images from low-resolution images using the dictionaries. The same algorithm was also applied to patient LGE (n=4) to assess its effects. Compared with interpolated images, super resolution significantly improved basic image quality indices (P

KW - Image processing

KW - image quality

KW - magnetic resonance imaging

KW - myocardial scar

UR - http://www.scopus.com/inward/record.url?scp=84926486666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926486666&partnerID=8YFLogxK

U2 - 10.1109/JTEHM.2014.2303806

DO - 10.1109/JTEHM.2014.2303806

M3 - Article

VL - 2

JO - IEEE Journal of Translational Engineering in Health and Medicine

JF - IEEE Journal of Translational Engineering in Health and Medicine

SN - 2168-2372

IS - 1

M1 - 18000512

ER -