Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: On-line re-training and segmentation with reduction of the training set: application to the left ventricle detection in ultrasound imaging
Author: Nascimento, J.
Carneiro, G.
Citation: Proceedings of the 19th IEEE International Conference on Image Processing, held in Orlando, Florida, 30 September-3 October, 2012: pp.2001-2004
Publisher: IEEE
Publisher Place: USA
Issue Date: 2012
Series/Report no.: IEEE International Conference on Image Processing ICIP
ISBN: 9781467325325
ISSN: 1522-4880
Conference Name: IEEE International Conference on Image Processing (19th : 2012 : Orlando, Florida)
Statement of
Jacinto C. Nascimento and Gustavo Carneiro
Abstract: The segmentation of the left ventricle (LV) still constitutes an active research topic in medical image processing field. The problem is usually tackled using pattern recognition methodologies. The main difficulty with pattern recognition methods is its dependence of a large manually annotated training sets for a robust learning strategy. However, in medical imaging, it is difficult to obtain such large annotated data. In this paper, we propose an on-line semi-supervised algorithm capable of reducing the need of large training sets. The main difference regarding semi-supervised techniques is that, the proposed framework provides both an on-line retraining and segmentation, instead of on-line retraining and offline segmentation. Our proposal is applied to a fully automatic LV segmentation with substantially reduced training sets while maintaining good segmentation accuracy.
Keywords: Image segmentation
measurement uncertainty
semisupervised learning
ultrasonic imaging
Rights: © 2012 IEEE
DOI: 10.1109/ICIP.2012.6467281
Published version:
Appears in Collections:Aurora harvest 4
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.