<scp>P11</scp>.04: Novel automatic coupled ellipse fitting tool for fetal arm adipose tissue quantification in <scp>2D</scp> ultrasound images across gestation
Lists
Only you see this
Abstract
To evaluate a new clinical tool to automatically approximate by two ellipses the fetal arm adipose tissue area in a transverse section at mid-humeral level on 2D ultrasound images across a range of gestational ages. Fetal arm adipose tissue was automatically measured on 15 cross-sectional ultrasound images at mid-humeral level from optimally healthy fetuses between 21 and 31 weeks of gestation using a novel image analysis measurement tool (Rueda et al. IEEE ISBI 2013). The measurement tool is based on fitting two ellipses simultaneously to the inner and outer boundaries of the adipose tissue layer. The tool is based on structural and oriented edge information to delineate the tissue boundaries and guide the fitting. The final estimation of the adipose tissue layer is obtained from the area between both fitted ellipses. The new methodology was compared to manual delineations, measured twice by the same clinical expert on each of the 15 images. The differences between between automatic and the average manual measurements were assessed using a Bland-Altman plot obtaining a mean of −1.86 mm2 and a standard deviation of 40.46 mm2. Supporting information can be found in the online version of this abstract Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.
BibTeX
@inproceedings{rueda2013scp,
author = {Sylvia Rueda and Caroline L. Knight and J. Alison Noble and Aris T. Papageorghiou},
title = {{<scp>P11</scp>.04: Novel automatic coupled ellipse fitting tool for fetal arm adipose tissue quantification in <scp>2D</scp> ultrasound images across gestation}},
booktitle = {Ultrasound},
year = {2013},
doi = {10.1002/uog.13053},
}Loading related content...