Diffeomorphic Upsampling of Serially Acquired Sparse 2D Cross-Sections in Cardiac MRI

Brian C. Lee, Daniel J. Tward, Jinchi Wei, Dnyanesh Tipre, Robert G. Weiss, Michael I. Miller, Siamak Ardekani

Abstract

In this paper, we propose a new technique for interpolating shapes in order to upsample a sparsely acquired serial-section image stack. The method is based on a maximum a posteriori estimation strategy which models neighboring sections as observations of random deformations of an image to be estimated. We show the computation of diffeomorphic trajectories between observed sections and define estimated upsampled image sections as a Jacobian-weighted sum of flowing images at corresponding distances along those trajectories. We apply this methodology to upsample stacks of sparse 2D magnetic resonance cross-sections through live mouse hearts. We show that the proposed method results in smoother and more accurate reconstructions over linear interpolation, and report a Dice coefficient of 0.8727 against ground truth segmentations in our dataset and statistically significant improvements in both left ventricular segmentation accuracy and image intensity estimates.

Original languageEnglish (US)
Title of host publication2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4491-4495
Number of pages5
ISBN (Electronic)9781538613115
DOIs
StatePublished - Jul 2019
Event41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 - Berlin, Germany
Duration: Jul 23 2019Jul 27 2019

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Conference

Conference41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
CountryGermany
CityBerlin
Period7/23/197/27/19

Fingerprint

Magnetic resonance imaging
Trajectories
Magnetic resonance
Interpolation
Magnetic Resonance Spectroscopy
Datasets

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Lee, B. C., Tward, D. J., Wei, J., Tipre, D., Weiss, R. G., Miller, M. I., & Ardekani, S. (2019). Diffeomorphic Upsampling of Serially Acquired Sparse 2D Cross-Sections in Cardiac MRI. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 (pp. 4491-4495). [8856317] (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2019.8856317

Diffeomorphic Upsampling of Serially Acquired Sparse 2D Cross-Sections in Cardiac MRI. / Lee, Brian C.; Tward, Daniel J.; Wei, Jinchi; Tipre, Dnyanesh; Weiss, Robert G.; Miller, Michael I.; Ardekani, Siamak.

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 4491-4495 8856317 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

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

Lee, BC, Tward, DJ, Wei, J, Tipre, D, Weiss, RG, Miller, MI & Ardekani, S 2019, Diffeomorphic Upsampling of Serially Acquired Sparse 2D Cross-Sections in Cardiac MRI. in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019., 8856317, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, Institute of Electrical and Electronics Engineers Inc., pp. 4491-4495, 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019, Berlin, Germany, 7/23/19. https://doi.org/10.1109/EMBC.2019.8856317
Lee BC, Tward DJ, Wei J, Tipre D, Weiss RG, Miller MI et al. Diffeomorphic Upsampling of Serially Acquired Sparse 2D Cross-Sections in Cardiac MRI. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 4491-4495. 8856317. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/EMBC.2019.8856317
Lee, Brian C. ; Tward, Daniel J. ; Wei, Jinchi ; Tipre, Dnyanesh ; Weiss, Robert G. ; Miller, Michael I. ; Ardekani, Siamak. / Diffeomorphic Upsampling of Serially Acquired Sparse 2D Cross-Sections in Cardiac MRI. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 4491-4495 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
@inproceedings{37cc5879ce3a48d1a9bcbaef87df7628,
title = "Diffeomorphic Upsampling of Serially Acquired Sparse 2D Cross-Sections in Cardiac MRI",
abstract = "In this paper, we propose a new technique for interpolating shapes in order to upsample a sparsely acquired serial-section image stack. The method is based on a maximum a posteriori estimation strategy which models neighboring sections as observations of random deformations of an image to be estimated. We show the computation of diffeomorphic trajectories between observed sections and define estimated upsampled image sections as a Jacobian-weighted sum of flowing images at corresponding distances along those trajectories. We apply this methodology to upsample stacks of sparse 2D magnetic resonance cross-sections through live mouse hearts. We show that the proposed method results in smoother and more accurate reconstructions over linear interpolation, and report a Dice coefficient of 0.8727 against ground truth segmentations in our dataset and statistically significant improvements in both left ventricular segmentation accuracy and image intensity estimates.",
author = "Lee, {Brian C.} and Tward, {Daniel J.} and Jinchi Wei and Dnyanesh Tipre and Weiss, {Robert G.} and Miller, {Michael I.} and Siamak Ardekani",
year = "2019",
month = "7",
doi = "10.1109/EMBC.2019.8856317",
language = "English (US)",
series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4491--4495",
booktitle = "2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019",

}

TY - GEN

T1 - Diffeomorphic Upsampling of Serially Acquired Sparse 2D Cross-Sections in Cardiac MRI

AU - Lee, Brian C.

AU - Tward, Daniel J.

AU - Wei, Jinchi

AU - Tipre, Dnyanesh

AU - Weiss, Robert G.

AU - Miller, Michael I.

AU - Ardekani, Siamak

PY - 2019/7

Y1 - 2019/7

N2 - In this paper, we propose a new technique for interpolating shapes in order to upsample a sparsely acquired serial-section image stack. The method is based on a maximum a posteriori estimation strategy which models neighboring sections as observations of random deformations of an image to be estimated. We show the computation of diffeomorphic trajectories between observed sections and define estimated upsampled image sections as a Jacobian-weighted sum of flowing images at corresponding distances along those trajectories. We apply this methodology to upsample stacks of sparse 2D magnetic resonance cross-sections through live mouse hearts. We show that the proposed method results in smoother and more accurate reconstructions over linear interpolation, and report a Dice coefficient of 0.8727 against ground truth segmentations in our dataset and statistically significant improvements in both left ventricular segmentation accuracy and image intensity estimates.

AB - In this paper, we propose a new technique for interpolating shapes in order to upsample a sparsely acquired serial-section image stack. The method is based on a maximum a posteriori estimation strategy which models neighboring sections as observations of random deformations of an image to be estimated. We show the computation of diffeomorphic trajectories between observed sections and define estimated upsampled image sections as a Jacobian-weighted sum of flowing images at corresponding distances along those trajectories. We apply this methodology to upsample stacks of sparse 2D magnetic resonance cross-sections through live mouse hearts. We show that the proposed method results in smoother and more accurate reconstructions over linear interpolation, and report a Dice coefficient of 0.8727 against ground truth segmentations in our dataset and statistically significant improvements in both left ventricular segmentation accuracy and image intensity estimates.

UR - http://www.scopus.com/inward/record.url?scp=85077890957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077890957&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2019.8856317

DO - 10.1109/EMBC.2019.8856317

M3 - Conference contribution

C2 - 31946863

AN - SCOPUS:85077890957

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 4491

EP - 4495

BT - 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -