Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/107659
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Multi-atlas segmentation using manifold learning with deep belief networks
Author: Nascimento, J.
Carneiro, G.
Citation: Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging, 2016 / vol.2016-June, pp.867-871
Publisher: IEEE
Issue Date: 2016
Series/Report no.: IEEE International Symposium on Biomedical Imaging
ISBN: 9781479923502
ISSN: 1945-7928
1945-8452
Conference Name: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI 2016) (13 Apr 2016 - 16 Apr 2016 : Prague, Czech Republic)
Statement of
Responsibility: 
Jacinto C. Nascimento, Gustavo Carneiro
Abstract: This paper proposes a novel combination of manifold learning with deep belief networks for the detection and segmentation of left ventricle (LV) in 2D - ultrasound (US) images. The main goal is to reduce both training and inference complexities while maintaining the segmentation accuracy of machine learning based methods for non-rigid segmentation methodologies. The manifold learning approach used can be viewed as an atlas-based segmentation. It partitions the data into several patches. Each patch proposes a segmentation of the LV that somehow must be fused. This is accomplished by a deep belief network (DBN) multi-classifier that assigns a weight for each patch LV segmentation. The approach is thus threefold: (i) it does not rely on a single segmentation, (ii) it provides a great reduction in the rigid detection phase that is performed at lower dimensional space comparing with the initial contour space, and (iii) DBN's allows for a training process that can produce robust appearance models without the need of large annotated training sets.
Keywords: Manifolds, training, image segmentation, visualization, principal component analysis, complexity theory, context
Rights: © 2016 IEEE
RMID: 0030051609
DOI: 10.1109/ISBI.2016.7493403
Grant ID: http://purl.org/au-research/grants/arc/DP140102794
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107659.pdfRestricted Access797.48 kBAdobe PDFView/Open


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