Thoracic non-rigid registration combining self-organizing maps and radial basis functions

Matsopoulos, GK; Mouravliansky, NA; Asvestas, PA; Delibasis, KK; Kouloulias, V

dc.contributor.author	Matsopoulos, GK	en
dc.contributor.author	Mouravliansky, NA	en
dc.contributor.author	Asvestas, PA	en
dc.contributor.author	Delibasis, KK	en
dc.contributor.author	Kouloulias, V	en
dc.date.accessioned	2014-03-01T01:23:12Z
dc.date.available	2014-03-01T01:23:12Z
dc.date.issued	2005	en
dc.identifier.issn	1361-8415	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/16870
dc.subject	Computed tomography	en
dc.subject	Kohonen neural network	en
dc.subject	Non-rigid registration	en
dc.subject	Radial basis functions	en
dc.subject	Self-organizing maps	en
dc.subject	Stage III non-small cell lung cancer	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Engineering, Biomedical	en
dc.subject.classification	Radiology, Nuclear Medicine & Medical Imaging	en
dc.subject.other	Cells	en
dc.subject.other	Data acquisition	en
dc.subject.other	Database systems	en
dc.subject.other	Mathematical models	en
dc.subject.other	Neural networks	en
dc.subject.other	Patient monitoring	en
dc.subject.other	Radiotherapy	en
dc.subject.other	Scanning	en
dc.subject.other	Tomography	en
dc.subject.other	Tumors	en
dc.subject.other	Computed Tomography (CT)	en
dc.subject.other	Neural network model	en
dc.subject.other	Non-rigid registration scheme	en
dc.subject.other	Self-organizing maps	en
dc.subject.other	Medical imaging	en
dc.subject.other	adult	en
dc.subject.other	analytical error	en
dc.subject.other	anatomy	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	breathing mechanics	en
dc.subject.other	cancer radiotherapy	en
dc.subject.other	cancer staging	en
dc.subject.other	clinical article	en
dc.subject.other	computer assisted tomography	en
dc.subject.other	controlled study	en
dc.subject.other	human	en
dc.subject.other	image processing	en
dc.subject.other	inhalation	en
dc.subject.other	lung non small cell cancer	en
dc.subject.other	priority journal	en
dc.subject.other	qualitative analysis	en
dc.subject.other	quantitative analysis	en
dc.subject.other	radiological procedures	en
dc.subject.other	rib	en
dc.subject.other	scapula	en
dc.subject.other	thorax radiography	en
dc.subject.other	treatment planning	en
dc.subject.other	tumor volume	en
dc.subject.other	validation process	en
dc.subject.other	vertebra	en
dc.subject.other	visual information	en
dc.subject.other	Adult	en
dc.subject.other	Algorithms	en
dc.subject.other	Artificial Intelligence	en
dc.subject.other	Carcinoma, Non-Small-Cell Lung	en
dc.subject.other	Female	en
dc.subject.other	Humans	en
dc.subject.other	Imaging, Three-Dimensional	en
dc.subject.other	Information Storage and Retrieval	en
dc.subject.other	Lung Neoplasms	en
dc.subject.other	Male	en
dc.subject.other	Middle Aged	en
dc.subject.other	Pattern Recognition, Automated	en
dc.subject.other	Radiographic Image Enhancement	en
dc.subject.other	Radiographic Image Interpretation, Computer-Assisted	en
dc.subject.other	Radiography, Thoracic	en
dc.subject.other	Reproducibility of Results	en
dc.subject.other	Sensitivity and Specificity	en
dc.subject.other	Subtraction Technique	en
dc.title	Thoracic non-rigid registration combining self-organizing maps and radial basis functions	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.media.2004.09.002	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.media.2004.09.002	en
heal.language	English	en
heal.publicationDate	2005	en
heal.abstract	An automatic three-dimensional non-rigid registration scheme is proposed in this paper and applied to thoracic computed tomography (CT) data of patients with stage III non-small cell lung cancer (NSCLC). According to the registration scheme, initially anatomical set of points such as the vertebral spine, the ribs, and shoulder blades are automatically segmented slice by slice from the two CT scans of the same patient in order to serve as interpolant points. Based on these extracted features, a rigid-body transformation is then applied to provide a pre-registration of the data. To establish correspondence between the feature points, the novel application of the self-organizing maps (SOMs) is adopted. In particular, the automatic correspondence of the interpolant points is based on the initialization of the Kohonen neural network model capable to identify 500 corresponding pairs of points approximately in the two CT sets. Then, radial basis functions (RBFs) using the shifted log function is subsequently employed for elastic warping of the image volume, using the correspondence between the interpolant points, as obtained in the previous phase. Quantitative and qualitative results are also presented to validate the performance of the proposed elastic registration scheme resulting in an alignment error of 6 mm, on average, over 15 CT paired datasets. Finally, changes of the tumor volume in respect to each reference dataset are estimated for all patients, which indicate inspiration and/or movement of the patient during acquisition of the data. Thus, the practical implementation of this scheme could provide estimations of lung tumor volumes during radiotherapy treatment planning. (c) 2004 Elsevier B.V. All rights reserved.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	Medical Image Analysis	en
dc.identifier.doi	10.1016/j.media.2004.09.002	en
dc.identifier.isi	ISI:000229376600005	en
dc.identifier.volume	9	en
dc.identifier.issue	3	en
dc.identifier.spage	237	en
dc.identifier.epage	254	en