Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications

Eranga Ukwatta, Martin Rajchl, James White, Farhad Pashakhanloo, Daniel Herzka, Elliot McVeigh, Albert C. Lardo, Natalia Trayanova, Fijoy Vadakkumpadan

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

Abstract

Accurate reconstruction of the three-dimensional (3D) geometry of a myocardial infarct from two-dimensional (2D) multi-slice image sequences has important applications in the clinical evaluation and treatment of patients with ischemic cardiomyopathy. However, this reconstruction is challenging because the resolution of common clinical scans used to acquire infarct structure, such as short-axis, late-gadolinium enhanced cardiac magnetic resonance (LGE-CMR) images, is low, especially in the out-of-plane direction. In this study, we propose a novel technique to reconstruct the 3D infarct geometry from low resolution clinical images. Our methodology is based on a function called logarithm of odds (LogOdds), which allows the broader class of linear combinations in the LogOdds vector space as opposed to being limited to only a convex combination in the binary label space. To assess the efficacy of the method, we used high-resolution LGE-CMR images of 36 human hearts in vivo, and 3 canine hearts ex vivo. The infarct was manually segmented in each slice of the acquired images, and the manually segmented data were downsampled to clinical resolution. The developed method was then applied to the downsampled image slices, and the resulting reconstructions were compared with the manually segmented data. Several existing reconstruction techniques were also implemented, and compared with the proposed method. The results show that the LogOdds method significantly outperforms all the other tested methods in terms of region overlap.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2015: Image Processing
PublisherSPIE
Volume9413
ISBN (Print)9781628415032
DOIs
StatePublished - 2015
EventMedical Imaging 2015: Image Processing - Orlando, United States
Duration: Feb 24 2015Feb 26 2015

Other

OtherMedical Imaging 2015: Image Processing
CountryUnited States
CityOrlando
Period2/24/152/26/15

Fingerprint

Computer-Assisted Image Processing
Gadolinium
Magnetic resonance
Myocardial Infarction
Geometry
Vector spaces
geometry
logarithms
Labels
gadolinium
Magnetic Resonance Spectroscopy
magnetic resonance
vector spaces
Cardiomyopathies
Canidae
methodology
evaluation
high resolution
Direction compound

Keywords

  • Image-based Reconstruction
  • Interpolation
  • Logarithm of Odds
  • Myocardial Infarct

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Ukwatta, E., Rajchl, M., White, J., Pashakhanloo, F., Herzka, D., McVeigh, E., ... Vadakkumpadan, F. (2015). Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications. In Medical Imaging 2015: Image Processing (Vol. 9413). [94132W] SPIE. https://doi.org/10.1117/12.2082113

Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications. / Ukwatta, Eranga; Rajchl, Martin; White, James; Pashakhanloo, Farhad; Herzka, Daniel; McVeigh, Elliot; Lardo, Albert C.; Trayanova, Natalia; Vadakkumpadan, Fijoy.

Medical Imaging 2015: Image Processing. Vol. 9413 SPIE, 2015. 94132W.

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

Ukwatta, E, Rajchl, M, White, J, Pashakhanloo, F, Herzka, D, McVeigh, E, Lardo, AC, Trayanova, N & Vadakkumpadan, F 2015, Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications. in Medical Imaging 2015: Image Processing. vol. 9413, 94132W, SPIE, Medical Imaging 2015: Image Processing, Orlando, United States, 2/24/15. https://doi.org/10.1117/12.2082113
Ukwatta E, Rajchl M, White J, Pashakhanloo F, Herzka D, McVeigh E et al. Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications. In Medical Imaging 2015: Image Processing. Vol. 9413. SPIE. 2015. 94132W https://doi.org/10.1117/12.2082113
Ukwatta, Eranga ; Rajchl, Martin ; White, James ; Pashakhanloo, Farhad ; Herzka, Daniel ; McVeigh, Elliot ; Lardo, Albert C. ; Trayanova, Natalia ; Vadakkumpadan, Fijoy. / Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications. Medical Imaging 2015: Image Processing. Vol. 9413 SPIE, 2015.
@inproceedings{38f238737e4749478139cdd3d5277358,
title = "Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications",
abstract = "Accurate reconstruction of the three-dimensional (3D) geometry of a myocardial infarct from two-dimensional (2D) multi-slice image sequences has important applications in the clinical evaluation and treatment of patients with ischemic cardiomyopathy. However, this reconstruction is challenging because the resolution of common clinical scans used to acquire infarct structure, such as short-axis, late-gadolinium enhanced cardiac magnetic resonance (LGE-CMR) images, is low, especially in the out-of-plane direction. In this study, we propose a novel technique to reconstruct the 3D infarct geometry from low resolution clinical images. Our methodology is based on a function called logarithm of odds (LogOdds), which allows the broader class of linear combinations in the LogOdds vector space as opposed to being limited to only a convex combination in the binary label space. To assess the efficacy of the method, we used high-resolution LGE-CMR images of 36 human hearts in vivo, and 3 canine hearts ex vivo. The infarct was manually segmented in each slice of the acquired images, and the manually segmented data were downsampled to clinical resolution. The developed method was then applied to the downsampled image slices, and the resulting reconstructions were compared with the manually segmented data. Several existing reconstruction techniques were also implemented, and compared with the proposed method. The results show that the LogOdds method significantly outperforms all the other tested methods in terms of region overlap.",
keywords = "Image-based Reconstruction, Interpolation, Logarithm of Odds, Myocardial Infarct",
author = "Eranga Ukwatta and Martin Rajchl and James White and Farhad Pashakhanloo and Daniel Herzka and Elliot McVeigh and Lardo, {Albert C.} and Natalia Trayanova and Fijoy Vadakkumpadan",
year = "2015",
doi = "10.1117/12.2082113",
language = "English (US)",
isbn = "9781628415032",
volume = "9413",
booktitle = "Medical Imaging 2015: Image Processing",
publisher = "SPIE",

}

TY - GEN

T1 - Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications

AU - Ukwatta, Eranga

AU - Rajchl, Martin

AU - White, James

AU - Pashakhanloo, Farhad

AU - Herzka, Daniel

AU - McVeigh, Elliot

AU - Lardo, Albert C.

AU - Trayanova, Natalia

AU - Vadakkumpadan, Fijoy

PY - 2015

Y1 - 2015

N2 - Accurate reconstruction of the three-dimensional (3D) geometry of a myocardial infarct from two-dimensional (2D) multi-slice image sequences has important applications in the clinical evaluation and treatment of patients with ischemic cardiomyopathy. However, this reconstruction is challenging because the resolution of common clinical scans used to acquire infarct structure, such as short-axis, late-gadolinium enhanced cardiac magnetic resonance (LGE-CMR) images, is low, especially in the out-of-plane direction. In this study, we propose a novel technique to reconstruct the 3D infarct geometry from low resolution clinical images. Our methodology is based on a function called logarithm of odds (LogOdds), which allows the broader class of linear combinations in the LogOdds vector space as opposed to being limited to only a convex combination in the binary label space. To assess the efficacy of the method, we used high-resolution LGE-CMR images of 36 human hearts in vivo, and 3 canine hearts ex vivo. The infarct was manually segmented in each slice of the acquired images, and the manually segmented data were downsampled to clinical resolution. The developed method was then applied to the downsampled image slices, and the resulting reconstructions were compared with the manually segmented data. Several existing reconstruction techniques were also implemented, and compared with the proposed method. The results show that the LogOdds method significantly outperforms all the other tested methods in terms of region overlap.

AB - Accurate reconstruction of the three-dimensional (3D) geometry of a myocardial infarct from two-dimensional (2D) multi-slice image sequences has important applications in the clinical evaluation and treatment of patients with ischemic cardiomyopathy. However, this reconstruction is challenging because the resolution of common clinical scans used to acquire infarct structure, such as short-axis, late-gadolinium enhanced cardiac magnetic resonance (LGE-CMR) images, is low, especially in the out-of-plane direction. In this study, we propose a novel technique to reconstruct the 3D infarct geometry from low resolution clinical images. Our methodology is based on a function called logarithm of odds (LogOdds), which allows the broader class of linear combinations in the LogOdds vector space as opposed to being limited to only a convex combination in the binary label space. To assess the efficacy of the method, we used high-resolution LGE-CMR images of 36 human hearts in vivo, and 3 canine hearts ex vivo. The infarct was manually segmented in each slice of the acquired images, and the manually segmented data were downsampled to clinical resolution. The developed method was then applied to the downsampled image slices, and the resulting reconstructions were compared with the manually segmented data. Several existing reconstruction techniques were also implemented, and compared with the proposed method. The results show that the LogOdds method significantly outperforms all the other tested methods in terms of region overlap.

KW - Image-based Reconstruction

KW - Interpolation

KW - Logarithm of Odds

KW - Myocardial Infarct

UR - http://www.scopus.com/inward/record.url?scp=84943385810&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943385810&partnerID=8YFLogxK

U2 - 10.1117/12.2082113

DO - 10.1117/12.2082113

M3 - Conference contribution

AN - SCOPUS:84943385810

SN - 9781628415032

VL - 9413

BT - Medical Imaging 2015: Image Processing

PB - SPIE

ER -