Automatic left ventricle segmentation in T2 weighted CMR images

K Kushsairy Bin Abdul Kadir, A. Payne, John Soraghan, C. Berry

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

3 Citations (Scopus)

Abstract

An automatic left ventricle (LV) segmentation method for T2 weighted Cardiac Magnetic Resonance (CMR) image is presented. The method takes multi-slice T2 weighted CMR images from the basal to the apex of the heart. Inter-slice and intra-slice fuzzy reasoning is used to guide the centre point detection for each slice. Morphological filtering is used in the reconstruction to homogenise the blood pool region. Then radial search Fuzzy Multiscale Edge Detection (FMED) is used to segment the endocardium and the epicardium of the LV. Evaluation of the method is performed on 6 patient with approximately 42 slices of real T2 weighted MRI data. The quantitative result of the automatic method compared to those obtained from manual segmentation by a skilled clinician are very encouraging, with correlation scores of 96.2% correlation for the endocardium and 85.7% correlation for the epicardium.
LanguageEnglish
Title of host publicationImage Processing and Communications Challenges 2
PublisherSpringer
Pages247-254
Number of pages8
ISBN (Print)9783642162954
DOIs
Publication statusPublished - 2010

Publication series

NameAdvances in intelligent and soft computing
PublisherSpringer
Volume84

Fingerprint

Magnetic resonance
Edge detection
Magnetic resonance imaging
Blood

Keywords

  • CMR images
  • image processing
  • ventricle segmentation

Cite this

Kushsairy Bin Abdul Kadir, K., Payne, A., Soraghan, J., & Berry, C. (2010). Automatic left ventricle segmentation in T2 weighted CMR images. In Image Processing and Communications Challenges 2 (pp. 247-254). (Advances in intelligent and soft computing; Vol. 84). Springer. https://doi.org/10.1007/978-3-642-16295-4_28
Kushsairy Bin Abdul Kadir, K ; Payne, A. ; Soraghan, John ; Berry, C. / Automatic left ventricle segmentation in T2 weighted CMR images. Image Processing and Communications Challenges 2. Springer, 2010. pp. 247-254 (Advances in intelligent and soft computing).
@inproceedings{25a1b799d3bf49f0bd916f3e102c8d29,
title = "Automatic left ventricle segmentation in T2 weighted CMR images",
abstract = "An automatic left ventricle (LV) segmentation method for T2 weighted Cardiac Magnetic Resonance (CMR) image is presented. The method takes multi-slice T2 weighted CMR images from the basal to the apex of the heart. Inter-slice and intra-slice fuzzy reasoning is used to guide the centre point detection for each slice. Morphological filtering is used in the reconstruction to homogenise the blood pool region. Then radial search Fuzzy Multiscale Edge Detection (FMED) is used to segment the endocardium and the epicardium of the LV. Evaluation of the method is performed on 6 patient with approximately 42 slices of real T2 weighted MRI data. The quantitative result of the automatic method compared to those obtained from manual segmentation by a skilled clinician are very encouraging, with correlation scores of 96.2{\%} correlation for the endocardium and 85.7{\%} correlation for the epicardium.",
keywords = "CMR images, image processing, ventricle segmentation",
author = "{Kushsairy Bin Abdul Kadir}, K and A. Payne and John Soraghan and C. Berry",
year = "2010",
doi = "10.1007/978-3-642-16295-4_28",
language = "English",
isbn = "9783642162954",
series = "Advances in intelligent and soft computing",
publisher = "Springer",
pages = "247--254",
booktitle = "Image Processing and Communications Challenges 2",

}

Kushsairy Bin Abdul Kadir, K, Payne, A, Soraghan, J & Berry, C 2010, Automatic left ventricle segmentation in T2 weighted CMR images. in Image Processing and Communications Challenges 2. Advances in intelligent and soft computing, vol. 84, Springer, pp. 247-254. https://doi.org/10.1007/978-3-642-16295-4_28

Automatic left ventricle segmentation in T2 weighted CMR images. / Kushsairy Bin Abdul Kadir, K; Payne, A.; Soraghan, John; Berry, C.

Image Processing and Communications Challenges 2. Springer, 2010. p. 247-254 (Advances in intelligent and soft computing; Vol. 84).

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

TY - GEN

T1 - Automatic left ventricle segmentation in T2 weighted CMR images

AU - Kushsairy Bin Abdul Kadir, K

AU - Payne, A.

AU - Soraghan, John

AU - Berry, C.

PY - 2010

Y1 - 2010

N2 - An automatic left ventricle (LV) segmentation method for T2 weighted Cardiac Magnetic Resonance (CMR) image is presented. The method takes multi-slice T2 weighted CMR images from the basal to the apex of the heart. Inter-slice and intra-slice fuzzy reasoning is used to guide the centre point detection for each slice. Morphological filtering is used in the reconstruction to homogenise the blood pool region. Then radial search Fuzzy Multiscale Edge Detection (FMED) is used to segment the endocardium and the epicardium of the LV. Evaluation of the method is performed on 6 patient with approximately 42 slices of real T2 weighted MRI data. The quantitative result of the automatic method compared to those obtained from manual segmentation by a skilled clinician are very encouraging, with correlation scores of 96.2% correlation for the endocardium and 85.7% correlation for the epicardium.

AB - An automatic left ventricle (LV) segmentation method for T2 weighted Cardiac Magnetic Resonance (CMR) image is presented. The method takes multi-slice T2 weighted CMR images from the basal to the apex of the heart. Inter-slice and intra-slice fuzzy reasoning is used to guide the centre point detection for each slice. Morphological filtering is used in the reconstruction to homogenise the blood pool region. Then radial search Fuzzy Multiscale Edge Detection (FMED) is used to segment the endocardium and the epicardium of the LV. Evaluation of the method is performed on 6 patient with approximately 42 slices of real T2 weighted MRI data. The quantitative result of the automatic method compared to those obtained from manual segmentation by a skilled clinician are very encouraging, with correlation scores of 96.2% correlation for the endocardium and 85.7% correlation for the epicardium.

KW - CMR images

KW - image processing

KW - ventricle segmentation

UR - http://www.ellibs.com/book/9783642162954

U2 - 10.1007/978-3-642-16295-4_28

DO - 10.1007/978-3-642-16295-4_28

M3 - Conference contribution book

SN - 9783642162954

T3 - Advances in intelligent and soft computing

SP - 247

EP - 254

BT - Image Processing and Communications Challenges 2

PB - Springer

ER -

Kushsairy Bin Abdul Kadir K, Payne A, Soraghan J, Berry C. Automatic left ventricle segmentation in T2 weighted CMR images. In Image Processing and Communications Challenges 2. Springer. 2010. p. 247-254. (Advances in intelligent and soft computing). https://doi.org/10.1007/978-3-642-16295-4_28