Automatic Segmentation of Abdominal Fat in MRI-Scans, Using Graph-Cuts and Image Derived Energies

Anders Nymark Christensen, Christian Thode Larsen, Camilla Maria Mandrup Jensen, Martin Bæk Petersen, Rasmus Larsen, Knut Conradsen, Vedrana Andersen Dahl

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

For many clinical studies changes in the abdominal distribution of fat is an important measure. However, the segmentation of abdominal fat in MRI scans is both difficult and time consuming using manual methods. We present here an automatic and flexible software package, that performs both bias field correction and segmentation of the fat into superficial and deep subcutaneous fat as well as visceral fat with the spinal compartment removed. Assessment when comparing to the gold standard - CT-scans - shows a correlation and bias comparable to manual segmentation. The method is flexible by tuning the image-derived energies used for the segmentation, allowing the method to be applied to other body parts, such as the thighs.
Original languageEnglish
Title of host publicationImage Analysis
Volume10270
PublisherSpringer
Publication date2017
Pages109-120
ISBN (Print)9783319591285
DOIs
Publication statusPublished - 2017
Event20th Scandinavian Conference on Image Analysis - Tromsø, Norway
Duration: 12 Jun 201714 Jun 2017

Conference

Conference20th Scandinavian Conference on Image Analysis
CountryNorway
CityTromsø
Period12/06/201714/06/2017
SeriesLecture Notes in Computer Science
Volume10270
ISSN0302-9743

Keywords

  • Computer Science
  • Image Processing and Computer Vision
  • Pattern Recognition
  • Artificial Intelligence (incl. Robotics)
  • Computer Graphics
  • Data Mining and Knowledge Discovery

Cite this

Christensen, A. N., Larsen, C. T., Mandrup Jensen, C. M., Petersen, M. B., Larsen, R., Conradsen, K., & Dahl, V. A. (2017). Automatic Segmentation of Abdominal Fat in MRI-Scans, Using Graph-Cuts and Image Derived Energies. In Image Analysis (Vol. 10270, pp. 109-120). Springer. Lecture Notes in Computer Science, Vol.. 10270 https://doi.org/10.1007/978-3-319-59129-2_10
Christensen, Anders Nymark ; Larsen, Christian Thode ; Mandrup Jensen, Camilla Maria ; Petersen, Martin Bæk ; Larsen, Rasmus ; Conradsen, Knut ; Dahl, Vedrana Andersen. / Automatic Segmentation of Abdominal Fat in MRI-Scans, Using Graph-Cuts and Image Derived Energies. Image Analysis. Vol. 10270 Springer, 2017. pp. 109-120 (Lecture Notes in Computer Science, Vol. 10270).
@inproceedings{77e37906695c4c6a9dffbcad630a98b1,
title = "Automatic Segmentation of Abdominal Fat in MRI-Scans, Using Graph-Cuts and Image Derived Energies",
abstract = "For many clinical studies changes in the abdominal distribution of fat is an important measure. However, the segmentation of abdominal fat in MRI scans is both difficult and time consuming using manual methods. We present here an automatic and flexible software package, that performs both bias field correction and segmentation of the fat into superficial and deep subcutaneous fat as well as visceral fat with the spinal compartment removed. Assessment when comparing to the gold standard - CT-scans - shows a correlation and bias comparable to manual segmentation. The method is flexible by tuning the image-derived energies used for the segmentation, allowing the method to be applied to other body parts, such as the thighs.",
keywords = "Computer Science, Image Processing and Computer Vision, Pattern Recognition, Artificial Intelligence (incl. Robotics), Computer Graphics, Data Mining and Knowledge Discovery",
author = "Christensen, {Anders Nymark} and Larsen, {Christian Thode} and {Mandrup Jensen}, {Camilla Maria} and Petersen, {Martin B{\ae}k} and Rasmus Larsen and Knut Conradsen and Dahl, {Vedrana Andersen}",
year = "2017",
doi = "10.1007/978-3-319-59129-2_10",
language = "English",
isbn = "9783319591285",
volume = "10270",
pages = "109--120",
booktitle = "Image Analysis",
publisher = "Springer",

}

Christensen, AN, Larsen, CT, Mandrup Jensen, CM, Petersen, MB, Larsen, R, Conradsen, K & Dahl, VA 2017, Automatic Segmentation of Abdominal Fat in MRI-Scans, Using Graph-Cuts and Image Derived Energies. in Image Analysis. vol. 10270, Springer, Lecture Notes in Computer Science, vol. 10270, pp. 109-120, 20th Scandinavian Conference on Image Analysis, Tromsø, Norway, 12/06/2017. https://doi.org/10.1007/978-3-319-59129-2_10

Automatic Segmentation of Abdominal Fat in MRI-Scans, Using Graph-Cuts and Image Derived Energies. / Christensen, Anders Nymark; Larsen, Christian Thode; Mandrup Jensen, Camilla Maria; Petersen, Martin Bæk; Larsen, Rasmus; Conradsen, Knut; Dahl, Vedrana Andersen.

Image Analysis. Vol. 10270 Springer, 2017. p. 109-120 (Lecture Notes in Computer Science, Vol. 10270).

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Automatic Segmentation of Abdominal Fat in MRI-Scans, Using Graph-Cuts and Image Derived Energies

AU - Christensen, Anders Nymark

AU - Larsen, Christian Thode

AU - Mandrup Jensen, Camilla Maria

AU - Petersen, Martin Bæk

AU - Larsen, Rasmus

AU - Conradsen, Knut

AU - Dahl, Vedrana Andersen

PY - 2017

Y1 - 2017

N2 - For many clinical studies changes in the abdominal distribution of fat is an important measure. However, the segmentation of abdominal fat in MRI scans is both difficult and time consuming using manual methods. We present here an automatic and flexible software package, that performs both bias field correction and segmentation of the fat into superficial and deep subcutaneous fat as well as visceral fat with the spinal compartment removed. Assessment when comparing to the gold standard - CT-scans - shows a correlation and bias comparable to manual segmentation. The method is flexible by tuning the image-derived energies used for the segmentation, allowing the method to be applied to other body parts, such as the thighs.

AB - For many clinical studies changes in the abdominal distribution of fat is an important measure. However, the segmentation of abdominal fat in MRI scans is both difficult and time consuming using manual methods. We present here an automatic and flexible software package, that performs both bias field correction and segmentation of the fat into superficial and deep subcutaneous fat as well as visceral fat with the spinal compartment removed. Assessment when comparing to the gold standard - CT-scans - shows a correlation and bias comparable to manual segmentation. The method is flexible by tuning the image-derived energies used for the segmentation, allowing the method to be applied to other body parts, such as the thighs.

KW - Computer Science

KW - Image Processing and Computer Vision

KW - Pattern Recognition

KW - Artificial Intelligence (incl. Robotics)

KW - Computer Graphics

KW - Data Mining and Knowledge Discovery

U2 - 10.1007/978-3-319-59129-2_10

DO - 10.1007/978-3-319-59129-2_10

M3 - Article in proceedings

SN - 9783319591285

VL - 10270

SP - 109

EP - 120

BT - Image Analysis

PB - Springer

ER -

Christensen AN, Larsen CT, Mandrup Jensen CM, Petersen MB, Larsen R, Conradsen K et al. Automatic Segmentation of Abdominal Fat in MRI-Scans, Using Graph-Cuts and Image Derived Energies. In Image Analysis. Vol. 10270. Springer. 2017. p. 109-120. (Lecture Notes in Computer Science, Vol. 10270). https://doi.org/10.1007/978-3-319-59129-2_10