Vein segmentation using shape-based Markov random fields

Phillip G. D. Ward, Nicholas J. Ferris, Parnesh Raniga, Amanda C. L. Ng, David G. Barnes, David L. Dowe, Gary F. Egan

Research output: Chapter in Book/Report/Conference proceedingConference PaperOtherpeer-review

Abstract

The magnetic susceptibility of haemoglobin is modulated by oxygen saturation, providing a mechanism to non-invasively measure oxygen extraction fraction. When combined with perfusion techniques, quantitative susceptibility mapping facilitates regional measurement of cerebral metabolic rate of oxygen consumption. However, accurate measurement requires a complete vein map to measure anatomical variance in the metabolic demands of tissue. In this work we present a novel shape-based Markov Random Field technique to segmentation the cerebral veins that provides accurate and complete vein maps. The shape-based graph underpinning the model controls the spatial relationships between voxels and enforces cylindrical geometry, allowing increased sensitivity with accurate vein boundaries.

LanguageEnglish
Title of host publication2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1133-1136
Number of pages4
ISBN (Electronic)9781509011711, 9781509011728
ISBN (Print)9781509011735
DOIs
Publication statusPublished - 15 Jun 2017
EventIEEE International Symposium on Biomedical Imaging (ISBI) 2017 - Melbourne Convention and Exhibition Centre, Melbourne, Australia
Duration: 18 Apr 201721 Apr 2017
Conference number: 14th
http://biomedicalimaging.org/2017/

Conference

ConferenceIEEE International Symposium on Biomedical Imaging (ISBI) 2017
Abbreviated titleISBI 2017
CountryAustralia
CityMelbourne
Period18/04/1721/04/17
OtherISBI is a joint initiative from the IEEE Signal Processing Society (SPS) and the IEEE Engineering in Medicine and Biology Society (EMBS). The 2017 meeting will include tutorials, and a scientific program composed of plenary talks, invited special sessions, challenges, as well as oral and poster presentations of peer-reviewed papers.
Internet address

Keywords

  • Oxygen extraction fraction
  • Quantitative susceptibility mapping
  • Vein segmentation

Cite this

Ward, P. G. D., Ferris, N. J., Raniga, P., Ng, A. C. L., Barnes, D. G., Dowe, D. L., & Egan, G. F. (2017). Vein segmentation using shape-based Markov random fields. In 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017 (pp. 1133-1136). [7950716] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISBI.2017.7950716
Ward, Phillip G. D. ; Ferris, Nicholas J. ; Raniga, Parnesh ; Ng, Amanda C. L. ; Barnes, David G. ; Dowe, David L. ; Egan, Gary F. / Vein segmentation using shape-based Markov random fields. 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 1133-1136
@inproceedings{0f6ad97bdac14cbda44d7803ad367d2c,
title = "Vein segmentation using shape-based Markov random fields",
abstract = "The magnetic susceptibility of haemoglobin is modulated by oxygen saturation, providing a mechanism to non-invasively measure oxygen extraction fraction. When combined with perfusion techniques, quantitative susceptibility mapping facilitates regional measurement of cerebral metabolic rate of oxygen consumption. However, accurate measurement requires a complete vein map to measure anatomical variance in the metabolic demands of tissue. In this work we present a novel shape-based Markov Random Field technique to segmentation the cerebral veins that provides accurate and complete vein maps. The shape-based graph underpinning the model controls the spatial relationships between voxels and enforces cylindrical geometry, allowing increased sensitivity with accurate vein boundaries.",
keywords = "Oxygen extraction fraction, Quantitative susceptibility mapping, Vein segmentation",
author = "Ward, {Phillip G. D.} and Ferris, {Nicholas J.} and Parnesh Raniga and Ng, {Amanda C. L.} and Barnes, {David G.} and Dowe, {David L.} and Egan, {Gary F.}",
year = "2017",
month = "6",
day = "15",
doi = "10.1109/ISBI.2017.7950716",
language = "English",
isbn = "9781509011735",
pages = "1133--1136",
booktitle = "2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Ward, PGD, Ferris, NJ, Raniga, P, Ng, ACL, Barnes, DG, Dowe, DL & Egan, GF 2017, Vein segmentation using shape-based Markov random fields. in 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017., 7950716, IEEE, Institute of Electrical and Electronics Engineers, pp. 1133-1136, IEEE International Symposium on Biomedical Imaging (ISBI) 2017, Melbourne, Australia, 18/04/17. https://doi.org/10.1109/ISBI.2017.7950716

Vein segmentation using shape-based Markov random fields. / Ward, Phillip G. D.; Ferris, Nicholas J.; Raniga, Parnesh; Ng, Amanda C. L.; Barnes, David G.; Dowe, David L.; Egan, Gary F.

2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 1133-1136 7950716.

Research output: Chapter in Book/Report/Conference proceedingConference PaperOtherpeer-review

TY - GEN

T1 - Vein segmentation using shape-based Markov random fields

AU - Ward, Phillip G. D.

AU - Ferris, Nicholas J.

AU - Raniga, Parnesh

AU - Ng, Amanda C. L.

AU - Barnes, David G.

AU - Dowe, David L.

AU - Egan, Gary F.

PY - 2017/6/15

Y1 - 2017/6/15

N2 - The magnetic susceptibility of haemoglobin is modulated by oxygen saturation, providing a mechanism to non-invasively measure oxygen extraction fraction. When combined with perfusion techniques, quantitative susceptibility mapping facilitates regional measurement of cerebral metabolic rate of oxygen consumption. However, accurate measurement requires a complete vein map to measure anatomical variance in the metabolic demands of tissue. In this work we present a novel shape-based Markov Random Field technique to segmentation the cerebral veins that provides accurate and complete vein maps. The shape-based graph underpinning the model controls the spatial relationships between voxels and enforces cylindrical geometry, allowing increased sensitivity with accurate vein boundaries.

AB - The magnetic susceptibility of haemoglobin is modulated by oxygen saturation, providing a mechanism to non-invasively measure oxygen extraction fraction. When combined with perfusion techniques, quantitative susceptibility mapping facilitates regional measurement of cerebral metabolic rate of oxygen consumption. However, accurate measurement requires a complete vein map to measure anatomical variance in the metabolic demands of tissue. In this work we present a novel shape-based Markov Random Field technique to segmentation the cerebral veins that provides accurate and complete vein maps. The shape-based graph underpinning the model controls the spatial relationships between voxels and enforces cylindrical geometry, allowing increased sensitivity with accurate vein boundaries.

KW - Oxygen extraction fraction

KW - Quantitative susceptibility mapping

KW - Vein segmentation

UR - http://www.scopus.com/inward/record.url?scp=85023209041&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2017.7950716

DO - 10.1109/ISBI.2017.7950716

M3 - Conference Paper

SN - 9781509011735

SP - 1133

EP - 1136

BT - 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Ward PGD, Ferris NJ, Raniga P, Ng ACL, Barnes DG, Dowe DL et al. Vein segmentation using shape-based Markov random fields. In 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 1133-1136. 7950716 https://doi.org/10.1109/ISBI.2017.7950716