Automatic segmentation of low resolution fetal cardiac data using snakes with shape priors

Dindoyal, I. and Lambrou, T. and Deng, J. and Todd-Pokropek, A. (2007) Automatic segmentation of low resolution fetal cardiac data using snakes with shape priors. In: 5th International Symposium on Image and Signal Processing and Analysis; Conference, 27-29 September 2007, Istanbul.

Full content URL: http://www.scopus.com/inward/record.url?eid=2-s2.0...

Full text not available from this repository.

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

This paper presents a level set deformable model to segment all four chambers of the fet al. 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.

Additional Information:Conference Code: 72756
Keywords:Automatic segmentations, Cardiac structures, Data sets, Deformable models, High noises, Leave one outs, Level sets, Low resolutions, Rigid registrations, Segmentation errors, Shape priors, Training datums, Image enhancement, Medical imaging, Signal processing
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:8671
Deposited On:18 Apr 2013 10:55

Repository Staff Only: item control page