Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: The use of on-line co-training to reduce the training set size in pattern recognition methods: application to left ventricle segmentation in ultrasound
Author: Carneiro, G.
Nascimento, J.
Citation: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, held in Rhode Island, USA, 16-21 June 2012: pp. 948-955
Publisher: IEEE
Publisher Place: USA
Issue Date: 2012
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781467312264
ISSN: 1063-6919
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition (25th : 2012 : Providence, Rhode Island)
Statement of
Gustavo Carneiro and Jacinto C. Nascimnento
Abstract: The use of statistical pattern recognition models to segment the left ventricle of the heart in ultrasound images has gained substantial attention over the last few years. The main obstacle for the wider exploration of this methodology lies in the need for large annotated training sets, which are used for the estimation of the statistical model parameters. In this paper, we present a new on-line co-training methodology that reduces the need for large training sets for such parameter estimation. Our approach learns the initial parameters of two different models using a small manually annotated training set. Then, given each frame of a test sequence, the methodology not only produces the segmentation of the current frame, but it also uses the results of both classifiers to re-train each other incrementally. This on-line aspect of our approach has the advantages of producing segmentation results and re-training the classifiers on the fly as frames of a test sequence are presented, but it introduces a harder learning setting compared to the usual off-line co-training, where the algorithm has access to the whole set of un-annotated training samples from the beginning. Moreover, we introduce the use of the following new types of classifiers in the co-training framework: deep belief network and multiple model probabilistic data association. We show that our method leads to a fully automatic left ventricle segmentation system that achieves state-of-the-art accuracy on a public database with training sets containing at least twenty annotated images.
Rights: © 2012 IEEE
DOI: 10.1109/CVPR.2012.6247770
Published version:
Appears in Collections:Aurora harvest 4
Computer Science publications

Files in This Item:
File Description SizeFormat 
  Restricted Access
Restricted Access586.47 kBAdobe PDFView/Open

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