Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers

dc.contributor.author	Μαυροφοράκης, Μιχαήλ Ε.	el
dc.contributor.author	Γεωργίου, Χάρης	el
dc.contributor.author	Δημητρόπουλος, Νικόλαος	el
dc.contributor.author	Κάβουρας, Διονύσης Α.	el
dc.contributor.author	Θεοδωρίδης, Σέργιος	el
dc.date.accessioned	2015-04-30T09:41:05Z
dc.date.available	2015-04-30T09:41:05Z
dc.date.issued	2015-04-30
dc.identifier.uri	http://hdl.handle.net/11400/9310
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.aiimjournal.com/article/S0933-3657(06)00038-8/abstract	en
dc.source	http://www.sciencedirect.com/science/article/pii/S093336570600038	en
dc.subject	Texture analysis
dc.subject	Mammography
dc.subject	Ανάλυση υφής
dc.subject	Μαστογραφία
dc.title	Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers	en
heal.type	journalArticle
heal.classification	Medicine
heal.classification	Biomedical engineering
heal.classification	Ιατρική
heal.classification	Βιοϊατρική τεχνολογία
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh00006614
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh85014237
heal.classificationURI	N/A-Ιατρική
heal.classificationURI	N/A-Βιοϊατρική τεχνολογία
heal.identifier.secondary	doi:10.1016/j.artmed.2006.03.002
heal.language	en
heal.access	campus
heal.recordProvider	Τ.Ε.Ι. Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Βιοϊατρικής Τεχνολογίας Τ.Ε.	el
heal.publicationDate	2006
heal.bibliographicCitation	Mavroforakis, M., Georgiou, H., Dimitropoulos, N., Cavouras, D. and Theodoridis, S. (June 2006). Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers. Artificial Intelligence in Medicine. 37(2). pp. 145-162. Elsevier B.V: 2006. Available from: http://www.sciencedirect.com/science/article/pii/S0933365706000388 [Accessed 23/05/2006]	en
heal.abstract	Objective Localized texture analysis of breast tissue on mammograms is an issue of major importance in mass characterization. However, in contrast to other mammographic diagnostic approaches, it has not been investigated in depth, due to its inherent difficulty and fuzziness. This work aims to the establishment of a quantitative approach of mammographic masses texture classification, based on advanced classifier architectures and supported by fractal analysis of the dataset of the extracted textural features. Additionally, a comparison of the information content of the proposed feature set with that of the qualitative characteristics used in clinical practice by expert radiologists is presented. Methods and material An extensive set of textural feature functions was applied to a set of 130 digitized mammograms, in multiple configurations and scales, constructing compact datasets of textural “signatures” for benign and malignant cases of tumors. These quantitative textural datasets were subsequently studied against a set of a thorough and compact list of qualitative texture descriptions of breast mass tissue, normally considered under a typical clinical assessment, in order to investigate the discriminating value and the statistical correlation between the two sets. Fractal analysis was employed to compare the information content and dimensionality of the textural features datasets with the qualitative information provided through medical diagnosis. A wide range of linear and non-linear classification architectures was employed, including linear discriminant analysis (LDA), least-squares minimum distance (LSMD), K-nearest-neighbors (K-nn), radial basis function (RBF) and multi-layer perceptron (MLP) artificial neural network (ANN), as well as support vector machine (SVM) classifiers. The classification process was used as the means to evaluate the inherent quality and informational content of each of the datasets, as well as the objective performance of each of the classifiers themselves in real classification of mammographic breast tumors against verified diagnosis. Results Textural features extracted at larger scales and sampling box sizes proved to be more content-rich than their equivalents at smaller scales and sizes. Fractal analysis on the dimensionality of the textural datasets verified that reduced subsets of optimal feature combinations can describe the original feature space adequately for classification purposes and at least the same detail and quality as the list of qualitative texture descriptions provided by a human expert. Non-linear classifiers, especially SVMs, have been proven superior to any linear equivalent. Breast mass classification of mammograms, based only on textural features, achieved an optimal score of 83.9%, through SVM classifiers.	en
heal.publisher	Elsevier B.V.	en
heal.journalName	Artificial Intelligence in Medicine	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true