Reconstructing cerebrovascular networks under local physiological constraints by integer programming

Markus Rempfler*, Matthias Schneider, Giovanna D. Ielacqua, Xianghui Xiao, Stuart R Stock, Jan Klohs, Gábor Székely, Bjoern Andres, Bjoern H. Menze

*Corresponding author for this work

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

We introduce a probabilistic approach to vessel network extraction that enforces physiological constraints on the vessel structure. The method accounts for both image evidence and geometric relationships between vessels by solving an integer program, which is shown to yield the maximum a posteriori (MAP) estimate to a probabilistic model. Starting from an overconnected network, it is pruning vessel stumps and spurious connections by evaluating the local geometry and the global connectivity of the graph. We utilize a high-resolution micro computed tomography (μCT) dataset of a cerebrovascular corrosion cast to obtain a reference network and learn the prior distributions of our probabilistic model and we perform experiments on in-vivo magnetic resonance microangiography (μMRA) images of mouse brains. We finally discuss properties of the networks obtained under different tracking and pruning approaches.

Original languageEnglish (US)
Pages (from-to)86-94
Number of pages9
JournalMedical Image Analysis
Volume25
Issue number1
DOIs
StatePublished - Oct 1 2015

Fingerprint

Integer programming
Statistical Models
Corrosion
Magnetic resonance
Tomography
Brain
Magnetic Resonance Spectroscopy
Geometry
Experiments
Datasets

Keywords

  • Cerebrovascular networks
  • Integer programming
  • Vascular network extraction
  • Vessel segmentation
  • Vessel tracking

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Rempfler, M., Schneider, M., Ielacqua, G. D., Xiao, X., Stock, S. R., Klohs, J., ... Menze, B. H. (2015). Reconstructing cerebrovascular networks under local physiological constraints by integer programming. Medical Image Analysis, 25(1), 86-94. https://doi.org/10.1016/j.media.2015.03.008
Rempfler, Markus ; Schneider, Matthias ; Ielacqua, Giovanna D. ; Xiao, Xianghui ; Stock, Stuart R ; Klohs, Jan ; Székely, Gábor ; Andres, Bjoern ; Menze, Bjoern H. / Reconstructing cerebrovascular networks under local physiological constraints by integer programming. In: Medical Image Analysis. 2015 ; Vol. 25, No. 1. pp. 86-94.
@article{ca015f0bd03445a4ab5769de3454a801,
title = "Reconstructing cerebrovascular networks under local physiological constraints by integer programming",
abstract = "We introduce a probabilistic approach to vessel network extraction that enforces physiological constraints on the vessel structure. The method accounts for both image evidence and geometric relationships between vessels by solving an integer program, which is shown to yield the maximum a posteriori (MAP) estimate to a probabilistic model. Starting from an overconnected network, it is pruning vessel stumps and spurious connections by evaluating the local geometry and the global connectivity of the graph. We utilize a high-resolution micro computed tomography (μCT) dataset of a cerebrovascular corrosion cast to obtain a reference network and learn the prior distributions of our probabilistic model and we perform experiments on in-vivo magnetic resonance microangiography (μMRA) images of mouse brains. We finally discuss properties of the networks obtained under different tracking and pruning approaches.",
keywords = "Cerebrovascular networks, Integer programming, Vascular network extraction, Vessel segmentation, Vessel tracking",
author = "Markus Rempfler and Matthias Schneider and Ielacqua, {Giovanna D.} and Xianghui Xiao and Stock, {Stuart R} and Jan Klohs and G{\'a}bor Sz{\'e}kely and Bjoern Andres and Menze, {Bjoern H.}",
year = "2015",
month = "10",
day = "1",
doi = "10.1016/j.media.2015.03.008",
language = "English (US)",
volume = "25",
pages = "86--94",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "1",

}

Rempfler, M, Schneider, M, Ielacqua, GD, Xiao, X, Stock, SR, Klohs, J, Székely, G, Andres, B & Menze, BH 2015, 'Reconstructing cerebrovascular networks under local physiological constraints by integer programming', Medical Image Analysis, vol. 25, no. 1, pp. 86-94. https://doi.org/10.1016/j.media.2015.03.008

Reconstructing cerebrovascular networks under local physiological constraints by integer programming. / Rempfler, Markus; Schneider, Matthias; Ielacqua, Giovanna D.; Xiao, Xianghui; Stock, Stuart R; Klohs, Jan; Székely, Gábor; Andres, Bjoern; Menze, Bjoern H.

In: Medical Image Analysis, Vol. 25, No. 1, 01.10.2015, p. 86-94.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Reconstructing cerebrovascular networks under local physiological constraints by integer programming

AU - Rempfler, Markus

AU - Schneider, Matthias

AU - Ielacqua, Giovanna D.

AU - Xiao, Xianghui

AU - Stock, Stuart R

AU - Klohs, Jan

AU - Székely, Gábor

AU - Andres, Bjoern

AU - Menze, Bjoern H.

PY - 2015/10/1

Y1 - 2015/10/1

N2 - We introduce a probabilistic approach to vessel network extraction that enforces physiological constraints on the vessel structure. The method accounts for both image evidence and geometric relationships between vessels by solving an integer program, which is shown to yield the maximum a posteriori (MAP) estimate to a probabilistic model. Starting from an overconnected network, it is pruning vessel stumps and spurious connections by evaluating the local geometry and the global connectivity of the graph. We utilize a high-resolution micro computed tomography (μCT) dataset of a cerebrovascular corrosion cast to obtain a reference network and learn the prior distributions of our probabilistic model and we perform experiments on in-vivo magnetic resonance microangiography (μMRA) images of mouse brains. We finally discuss properties of the networks obtained under different tracking and pruning approaches.

AB - We introduce a probabilistic approach to vessel network extraction that enforces physiological constraints on the vessel structure. The method accounts for both image evidence and geometric relationships between vessels by solving an integer program, which is shown to yield the maximum a posteriori (MAP) estimate to a probabilistic model. Starting from an overconnected network, it is pruning vessel stumps and spurious connections by evaluating the local geometry and the global connectivity of the graph. We utilize a high-resolution micro computed tomography (μCT) dataset of a cerebrovascular corrosion cast to obtain a reference network and learn the prior distributions of our probabilistic model and we perform experiments on in-vivo magnetic resonance microangiography (μMRA) images of mouse brains. We finally discuss properties of the networks obtained under different tracking and pruning approaches.

KW - Cerebrovascular networks

KW - Integer programming

KW - Vascular network extraction

KW - Vessel segmentation

KW - Vessel tracking

UR - http://www.scopus.com/inward/record.url?scp=84939463976&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939463976&partnerID=8YFLogxK

U2 - 10.1016/j.media.2015.03.008

DO - 10.1016/j.media.2015.03.008

M3 - Article

VL - 25

SP - 86

EP - 94

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 1

ER -