LV wall segmentation using the variational level set method (LSM) with additional shape constraint for oedema quantification

K Kushsairy Bin Abdul Kadir, Hao Gao, Alex Payne, John Soraghan, C. Berry

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In this paper an automatic algorithm for the left ventricle (LV) wall segmentation and oedema quantification from T2-weighted cardiac magnetic resonance (CMR) images is presented. The extent of myocardial oedema delineates the ischaemic area-at-risk (AAR) after myocardial infarction (MI). Since AAR can be used to estimate the amount of salvageable myocardial post-MI, oedema imaging has potential clinical utility in the management of acute MI patients. This paper presents a new scheme based on the variational level set method (LSM) with additional shape constraint for the segmentation of T2-weighted CMR image. In our approach, shape information of the myocardial wall is utilized to introduce a shape feature of the myocardial wall into the variational level set formulation. The performance of the method is tested using real CMR images (12 patients) and the results of the automatic system are compared to manual segmentation. The mean perpendicular distances between the automatic and manual LV wall boundaries are in the range of 1–2 mm. Bland–Altman analysis on LV wall area indicates there is no consistent bias as a function of LV wall area, with a mean bias of −121 mm2 between individual investigator one (IV1) and LSM, and −122 mm2 between individual investigator two (IV2) and LSM when compared to two investigators. Furthermore, the oedema quantification demonstrates good correlation when compared to an expert with an average error of 9.3% for 69 slices of short axis CMR image from 12 patients.


LanguageEnglish
Article number6007
Number of pages17
JournalPhysics in Medicine and Biology
Volume57
Issue number19
DOIs
Publication statusPublished - 12 Sep 2012

Fingerprint

Heart Ventricles
Edema
Magnetic Resonance Spectroscopy
Myocardial Infarction
Research Personnel

Keywords

  • cardiac dynamics
  • myocardial wall
  • left ventricle
  • oedema quantification
  • cardiac magnetic resonance

Cite this

@article{5f8ecdcda088477caa53d0abd097c952,
title = "LV wall segmentation using the variational level set method (LSM) with additional shape constraint for oedema quantification",
abstract = "In this paper an automatic algorithm for the left ventricle (LV) wall segmentation and oedema quantification from T2-weighted cardiac magnetic resonance (CMR) images is presented. The extent of myocardial oedema delineates the ischaemic area-at-risk (AAR) after myocardial infarction (MI). Since AAR can be used to estimate the amount of salvageable myocardial post-MI, oedema imaging has potential clinical utility in the management of acute MI patients. This paper presents a new scheme based on the variational level set method (LSM) with additional shape constraint for the segmentation of T2-weighted CMR image. In our approach, shape information of the myocardial wall is utilized to introduce a shape feature of the myocardial wall into the variational level set formulation. The performance of the method is tested using real CMR images (12 patients) and the results of the automatic system are compared to manual segmentation. The mean perpendicular distances between the automatic and manual LV wall boundaries are in the range of 1–2 mm. Bland–Altman analysis on LV wall area indicates there is no consistent bias as a function of LV wall area, with a mean bias of −121 mm2 between individual investigator one (IV1) and LSM, and −122 mm2 between individual investigator two (IV2) and LSM when compared to two investigators. Furthermore, the oedema quantification demonstrates good correlation when compared to an expert with an average error of 9.3{\%} for 69 slices of short axis CMR image from 12 patients.",
keywords = "cardiac dynamics, myocardial wall , left ventricle, oedema quantification, cardiac magnetic resonance",
author = "{Kushsairy Bin Abdul Kadir}, K and Hao Gao and Alex Payne and John Soraghan and C. Berry",
year = "2012",
month = "9",
day = "12",
doi = "10.1088/0031-9155/57/19/6007",
language = "English",
volume = "57",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
number = "19",

}

LV wall segmentation using the variational level set method (LSM) with additional shape constraint for oedema quantification. / Kushsairy Bin Abdul Kadir, K; Gao, Hao; Payne, Alex; Soraghan, John; Berry, C.

In: Physics in Medicine and Biology, Vol. 57, No. 19, 6007, 12.09.2012.

Research output: Contribution to journalArticle

TY - JOUR

T1 - LV wall segmentation using the variational level set method (LSM) with additional shape constraint for oedema quantification

AU - Kushsairy Bin Abdul Kadir, K

AU - Gao, Hao

AU - Payne, Alex

AU - Soraghan, John

AU - Berry, C.

PY - 2012/9/12

Y1 - 2012/9/12

N2 - In this paper an automatic algorithm for the left ventricle (LV) wall segmentation and oedema quantification from T2-weighted cardiac magnetic resonance (CMR) images is presented. The extent of myocardial oedema delineates the ischaemic area-at-risk (AAR) after myocardial infarction (MI). Since AAR can be used to estimate the amount of salvageable myocardial post-MI, oedema imaging has potential clinical utility in the management of acute MI patients. This paper presents a new scheme based on the variational level set method (LSM) with additional shape constraint for the segmentation of T2-weighted CMR image. In our approach, shape information of the myocardial wall is utilized to introduce a shape feature of the myocardial wall into the variational level set formulation. The performance of the method is tested using real CMR images (12 patients) and the results of the automatic system are compared to manual segmentation. The mean perpendicular distances between the automatic and manual LV wall boundaries are in the range of 1–2 mm. Bland–Altman analysis on LV wall area indicates there is no consistent bias as a function of LV wall area, with a mean bias of −121 mm2 between individual investigator one (IV1) and LSM, and −122 mm2 between individual investigator two (IV2) and LSM when compared to two investigators. Furthermore, the oedema quantification demonstrates good correlation when compared to an expert with an average error of 9.3% for 69 slices of short axis CMR image from 12 patients.

AB - In this paper an automatic algorithm for the left ventricle (LV) wall segmentation and oedema quantification from T2-weighted cardiac magnetic resonance (CMR) images is presented. The extent of myocardial oedema delineates the ischaemic area-at-risk (AAR) after myocardial infarction (MI). Since AAR can be used to estimate the amount of salvageable myocardial post-MI, oedema imaging has potential clinical utility in the management of acute MI patients. This paper presents a new scheme based on the variational level set method (LSM) with additional shape constraint for the segmentation of T2-weighted CMR image. In our approach, shape information of the myocardial wall is utilized to introduce a shape feature of the myocardial wall into the variational level set formulation. The performance of the method is tested using real CMR images (12 patients) and the results of the automatic system are compared to manual segmentation. The mean perpendicular distances between the automatic and manual LV wall boundaries are in the range of 1–2 mm. Bland–Altman analysis on LV wall area indicates there is no consistent bias as a function of LV wall area, with a mean bias of −121 mm2 between individual investigator one (IV1) and LSM, and −122 mm2 between individual investigator two (IV2) and LSM when compared to two investigators. Furthermore, the oedema quantification demonstrates good correlation when compared to an expert with an average error of 9.3% for 69 slices of short axis CMR image from 12 patients.

KW - cardiac dynamics

KW - myocardial wall

KW - left ventricle

KW - oedema quantification

KW - cardiac magnetic resonance

U2 - 10.1088/0031-9155/57/19/6007

DO - 10.1088/0031-9155/57/19/6007

M3 - Article

VL - 57

JO - Physics in Medicine and Biology

T2 - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 19

M1 - 6007

ER -