Automatic segmentation of low resolution fet al. cardiac data using snakes with shape priors

I. Dindoyal; T. Lambrou; J. Deng; A. Todd-Pokropek

doi:10.1109/ISPA.2007.4383751

Automatic segmentation of low resolution fet al. cardiac data using snakes with shape priors

I. Dindoyal, T. Lambrou, J. Deng, A. Todd-Pokropek

Computing Science

University College London

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

4 Citations (Scopus)

Abstract

This paper presents a level set deformable model to segment all four chambers of the fetal heart simultaneously. We show its results in 2D on 53 images taken from only 8 datasets. Due to our lack of sufficient data we built only a mean template from the training data instead of a full active shape model. Using rigid registration the template was registered to unseen images and the snakes were guided by individual chamber priors as they evolved in unison to segment missing cardiac structures in the presence of high noise. Using a leave one out approach most of the segmentation errors are within 3 pixels of manually traced contours.

Original language	English
Title of host publication	2007 5th International Symposium on Image and Signal Processing and Analysis
Publisher	IEEE Explore
Pages	538-543
DOIs	https://doi.org/10.1109/ISPA.2007.4383751
Publication status	Published - 2007
Event	5th International Symposium on Image and Signal Processing and Analysis - Istanbul, Turkey, Istanbul, Turkey Duration: 27 Sept 2007 → 29 Sept 2007

Conference

Conference	5th International Symposium on Image and Signal Processing and Analysis
Country/Territory	Turkey
City	Istanbul
Period	27/09/07 → 29/09/07

Bibliographical note

Published in: 2007 5th International Symposium on Image and Signal Processing and Analysis
cited By 3

Access to Document

10.1109/ISPA.2007.4383751

https://www.scopus.com/inward/record.uri?eid=2-s2.0-47949123432&doi=10.1109%2fISPA.2007.4383751&partnerID=40&md5=e17e6c48034f7cc634d43707fdd1735b

Cite this

Dindoyal, I, Lambrou, T, Deng, J & Todd-Pokropek, A 2007, Automatic segmentation of low resolution fet al. cardiac data using snakes with shape priors. in 2007 5th International Symposium on Image and Signal Processing and Analysis. IEEE Explore, pp. 538-543, 5th International Symposium on Image and Signal Processing and Analysis, Istanbul, Turkey, 27/09/07. https://doi.org/10.1109/ISPA.2007.4383751

@inproceedings{003cdea0f3f44622b6702490204cd8e2,

title = "Automatic segmentation of low resolution fet al. cardiac data using snakes with shape priors",

abstract = "This paper presents a level set deformable model to segment all four chambers of the fetal heart simultaneously. We show its results in 2D on 53 images taken from only 8 datasets. Due to our lack of sufficient data we built only a mean template from the training data instead of a full active shape model. Using rigid registration the template was registered to unseen images and the snakes were guided by individual chamber priors as they evolved in unison to segment missing cardiac structures in the presence of high noise. Using a leave one out approach most of the segmentation errors are within 3 pixels of manually traced contours.",

author = "I. Dindoyal and T. Lambrou and J. Deng and A. Todd-Pokropek",

note = "Published in: 2007 5th International Symposium on Image and Signal Processing and Analysis cited By 3; 5th International Symposium on Image and Signal Processing and Analysis ; Conference date: 27-09-2007 Through 29-09-2007",

year = "2007",

doi = "10.1109/ISPA.2007.4383751",

language = "English",

pages = "538--543",

booktitle = "2007 5th International Symposium on Image and Signal Processing and Analysis",

publisher = "IEEE Explore",

}

TY - GEN

T1 - Automatic segmentation of low resolution fet al. cardiac data using snakes with shape priors

AU - Dindoyal, I.

AU - Lambrou, T.

AU - Deng, J.

AU - Todd-Pokropek, A.

N1 - Published in: 2007 5th International Symposium on Image and Signal Processing and Analysis cited By 3

PY - 2007

Y1 - 2007

N2 - This paper presents a level set deformable model to segment all four chambers of the fetal heart simultaneously. We show its results in 2D on 53 images taken from only 8 datasets. Due to our lack of sufficient data we built only a mean template from the training data instead of a full active shape model. Using rigid registration the template was registered to unseen images and the snakes were guided by individual chamber priors as they evolved in unison to segment missing cardiac structures in the presence of high noise. Using a leave one out approach most of the segmentation errors are within 3 pixels of manually traced contours.

AB - This paper presents a level set deformable model to segment all four chambers of the fetal heart simultaneously. We show its results in 2D on 53 images taken from only 8 datasets. Due to our lack of sufficient data we built only a mean template from the training data instead of a full active shape model. Using rigid registration the template was registered to unseen images and the snakes were guided by individual chamber priors as they evolved in unison to segment missing cardiac structures in the presence of high noise. Using a leave one out approach most of the segmentation errors are within 3 pixels of manually traced contours.

U2 - 10.1109/ISPA.2007.4383751

DO - 10.1109/ISPA.2007.4383751

M3 - Published conference contribution

SP - 538

EP - 543

BT - 2007 5th International Symposium on Image and Signal Processing and Analysis

PB - IEEE Explore

T2 - 5th International Symposium on Image and Signal Processing and Analysis

Y2 - 27 September 2007 through 29 September 2007

ER -

Automatic segmentation of low resolution fet al. cardiac data using snakes with shape priors

Abstract

Conference

Bibliographical note

Access to Document

Fingerprint

Cite this