Quantitative image analysis in sonograms of the thyroid gland

dc.contributor.author	Λύρα, Μαρία	el
dc.contributor.author	Σκουρολιάκου, Αικατερίνη	el
dc.contributor.author	Αντωνίου, Αριστείδης	el
dc.contributor.author	Βλάχος, Λάμπρος	el
dc.date.accessioned	2015-04-23T18:12:55Z
dc.date.available	2015-04-23T18:12:55Z
dc.date.issued	2015-04-23
dc.identifier.uri	http://hdl.handle.net/11400/8788
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.source	http://www.sciencedirect.com/science/article/pii/S0168900206015440	en
dc.subject	Υπέρηχος
dc.subject	θυρεοειδής αδένας
dc.subject	Πίνακες στατιστικής συσχέτισης
dc.subject	χαρακτηριστικά υφής
dc.subject	ultrasonography
dc.subject	Thyroid gland
dc.subject	Co-occurrence matrix
dc.subject	Texture features
dc.title	Quantitative image analysis in sonograms of the thyroid gland	en
heal.type	journalArticle
heal.classification	Ιατρική
heal.classification	Ραδιολογία
heal.classification	Medicine
heal.classification	Radiology
heal.classificationURI	N/A-Ιατρική
heal.classificationURI	N/A-Ραδιολογία
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh00006614
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh85110774
heal.keywordURI	http://lod.nal.usda.gov/35666
heal.identifier.secondary	DOI:10.1016/j.nima.2006.08.162
heal.language	en
heal.access	campus
heal.recordProvider	Τεχνολογικό Εκπαιδευτικό Ίδρυμα Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Ενεργειακής Τεχνολογίας Τ.Ε	el
heal.publicationDate	2006-12-20
heal.bibliographicCitation	Skouroliakou, C., Lyra, M., Antoniou, A. and Vlahos, L. (2006) Quantitative image analysis in sonograms of the thyroid gland. Nuclear Instruments and Methods in Physics Research A. Elsevier. 569 (2), pp.606-609. Available from: http://www.sciencedirect.com [Accessed 23/04/2015]	en
heal.abstract	High-resolution, real-time ultrasound is a routine examination for assessing the disorders of the thyroid gland. However, the current diagnosis practice is based mainly on qualitative evaluation of the resulting sonograms, therefore depending on the physician's experience. Computerized texture analysis is widely employed in sonographic images of various organs (liver, breast), and it has been proven to increase the sensitivity of diagnosis by providing a better tissue characterization. The present study attempts to characterize thyroid tissue by automatic texture analysis. The texture features that are calculated are based on co-occurrence matrices as they have been proposed by Haralick. The sample consists of 40 patients. For each patient two sonographic images (one for each lobe) are recorded in DICOM format. The lobe is manually delineated in each sonogram, and the co-occurrence matrices for 52 separation vectors are calculated. The texture features extracted from each one of these matrices are: contrast, correlation, energy and homogeneity. Primary component analysis is used to select the optimal set of features. The statistical analysis resulted in the extraction of 21 optimal descriptors. The optimal descriptors are all co-occurrence parameters as the first-order statistics did not prove to be representative of the images characteristics. The bigger number of components depends mainly on correlation for very close or very far distances. The results indicate that quantitative analysis of thyroid sonograms can provide an objective characterization of thyroid tissue.	en
heal.journalName	Proceedings of the 3rd International Conference on Imaging Technologies in Biomedical Sciences	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true