Application of Kohonen network for automatic point correspondence in 2D medical images

Markaki, VE; Asvestas, PA; Matsopoulos, GK

dc.contributor.author	Markaki, VE	en
dc.contributor.author	Asvestas, PA	en
dc.contributor.author	Matsopoulos, GK	en
dc.date.accessioned	2014-03-01T01:29:52Z
dc.date.available	2014-03-01T01:29:52Z
dc.date.issued	2009	en
dc.identifier.issn	0010-4825	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/19384
dc.subject	Automatic correspondence	en
dc.subject	Global transformation	en
dc.subject	Iterative closest point	en
dc.subject	Kohonen network	en
dc.subject	Local transformation	en
dc.subject	Medical images	en
dc.subject	Point extraction	en
dc.subject	Self organizing maps	en
dc.subject	Similarity measure	en
dc.subject	Template matching	en
dc.subject.classification	Biology	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Engineering, Biomedical	en
dc.subject.classification	Mathematical & Computational Biology	en
dc.subject.other	Automatic correspondence	en
dc.subject.other	Global transformation	en
dc.subject.other	Iterative closest point	en
dc.subject.other	Kohonen network	en
dc.subject.other	Local transformation	en
dc.subject.other	Medical images	en
dc.subject.other	Point extraction	en
dc.subject.other	Similarity measure	en
dc.subject.other	Algorithms	en
dc.subject.other	Education	en
dc.subject.other	Parameter estimation	en
dc.subject.other	Self organizing maps	en
dc.subject.other	Set theory	en
dc.subject.other	Template matching	en
dc.subject.other	Medical imaging	en
dc.subject.other	algorithm	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	clinical article	en
dc.subject.other	computed tomography scanner	en
dc.subject.other	computer assisted tomography	en
dc.subject.other	human	en
dc.subject.other	image analysis	en
dc.subject.other	Kohonen network	en
dc.subject.other	learning	en
dc.subject.other	nuclear magnetic resonance imaging	en
dc.subject.other	nuclear magnetic resonance scanner	en
dc.subject.other	priority journal	en
dc.subject.other	quantitative analysis	en
dc.subject.other	retina image	en
dc.subject.other	Algorithms	en
dc.subject.other	Brain	en
dc.subject.other	Humans	en
dc.subject.other	Image Processing, Computer-Assisted	en
dc.subject.other	Magnetic Resonance Imaging	en
dc.subject.other	Neural Networks (Computer)	en
dc.subject.other	Retina	en
dc.subject.other	Tomography, X-Ray Computed	en
dc.title	Application of Kohonen network for automatic point correspondence in 2D medical images	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.compbiomed.2009.04.006	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.compbiomed.2009.04.006	en
heal.language	English	en
heal.publicationDate	2009	en
heal.abstract	In this paper, a generalized application of Kohonen Network for automatic point correspondence of unimodal medical images is presented. Given a pair of two-dimensional medical images of the same anatomical region and a set of interest points in one of the images, the algorithm detects effectively the set of corresponding points in the second image, by exploiting the properties of the Kohonen self organizing maps (SOMs) and embedding them in a stochastic optimization framework. The correspondences are established by determining the parameters of local transformations that map the interest points of the first image to their corresponding points in the second image. The parameters of each transformation are computed in an iterative way, using a modification of the competitive learning, as implemented by SOMs. The proposed algorithm was tested on medical imaging data from three different modalities (CT, MR and red-free retinal images) subject to known and unknown transformations. The quantitative results in all cases exhibited sub-pixel accuracy. The algorithm also proved to work efficiently in the case of noise corrupted data. Finally. in comparison to a previously published algorithm that was also based on SOMs, as well as two widely used techniques for detection of point correspondences (template matching and iterative closest point), the proposed algorithm exhibits an improved performance in terms of accuracy and robustness. (C) 2009 Elsevier Ltd. All rights reserved.	en
heal.publisher	PERGAMON-ELSEVIER SCIENCE LTD	en
heal.journalName	Computers in Biology and Medicine	en
dc.identifier.doi	10.1016/j.compbiomed.2009.04.006	en
dc.identifier.isi	ISI:000267931000007	en
dc.identifier.volume	39	en
dc.identifier.issue	7	en
dc.identifier.spage	630	en
dc.identifier.epage	645	en