Morphological and wavelet features towards sonographic thyroid nodules evaluation

dc.contributor.author	Τσαντής, Σταύρος	el
dc.contributor.author	Δημητρόπουλος, Νίκος Δ.	el
dc.contributor.author	Κάβουρας, Διονύσης	el
dc.contributor.author	Νικηφορίδης, Γεώργιος Κ.	el
dc.date.accessioned	2015-06-07T16:15:45Z
dc.date.available	2015-06-07T16:15:45Z
dc.date.issued	2015-06-07
dc.identifier.uri	http://hdl.handle.net/11400/15483
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	www.sciencedirect.com/science/journal/08956111	en
dc.subject	Morphological features
dc.subject	Probabilistic neural networks
dc.subject	Support vector machines
dc.subject	Thyroid ultrasound
dc.subject	Wavelet local maxima features
dc.subject	Μορφολογικά χαρακτηριστικά
dc.subject	Πιθανοτικά νευρωνικά δίκτυα
dc.subject	Μηχανές διανυσμάτων
dc.subject	Υπέρηχος θυρεοειδούς
dc.title	Morphological and wavelet features towards sonographic thyroid nodules evaluation	en
heal.type	journalArticle
heal.classification	Medicine
heal.classification	Technology
heal.classification	Ιατρική
heal.classification	Τεχνολογία
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh00006614
heal.classificationURI	http://zbw.eu/stw/descriptor/10470-6
heal.classificationURI	N/A-Ιατρική
heal.classificationURI	N/A-Τεχνολογία
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh2008009003
heal.identifier.secondary	DOI: 10.1016/j.compmedimag.2008.10.010
heal.language	en
heal.access	campus
heal.recordProvider	Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Βιοϊατρικής Τεχνολογίας Τ.Ε.	el
heal.publicationDate	2009
heal.bibliographicCitation	Tsantis, S., Dimitropoulos, N., Cavouras, D. and Nikiforidis, G. (2009) Morphological and wavelet features towards sonographic thyroid nodules evaluation. "Computerized Medical Imaging and Graphics", 33 (2), p. 91-99. Available from: http://www.sciencedirect.com/science/article/pii/S0895611108001055 [Accessed: 07/06/2015].	en
heal.abstract	This paper presents a computer-based classification scheme that utilized various morphological and novel wavelet-based features towards malignancy risk evaluation of thyroid nodules in ultrasonography. The study comprised 85 ultrasound images-patients that were cytological confirmed (54 low-risk and 31 high-risk). A set of 20 features (12 based on nodules boundary shape and 8 based on wavelet local maxima located within each nodule) has been generated. Two powerful pattern recognition algorithms (support vector machines and probabilistic neural networks) have been designed and developed in order to quantify the power of differentiation of the introduced features. A comparative study has also been held, in order to estimate the impact speckle had onto the classification procedure. The diagnostic sensitivity and specificity of both classifiers was made by means of receiver operating characteristics (ROC) analysis. In the speckle-free feature set, the area under the ROC curve was 0.96 for the support vector machines classifier whereas for the probabilistic neural networks was 0.91. In the feature set with speckle, the corresponding areas under the ROC curves were 0.88 and 0.86 respectively for the two classifiers. The proposed features can increase the classification accuracy and decrease the rate of missing and misdiagnosis in thyroid cancer control.	en
heal.publisher	Wong, Stephen	en
heal.journalName	Computerized Medical Imaging and Graphics	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true