Investigating the image features landscape for the classification of breast microcalcifications

Andreadis, I; Nikita, K; Antaraki, A; Ligomenides, P; Spyrou, G

dc.contributor.author	Andreadis, I	en
dc.contributor.author	Nikita, K	en
dc.contributor.author	Antaraki, A	en
dc.contributor.author	Ligomenides, P	en
dc.contributor.author	Spyrou, G	en
dc.date.accessioned	2014-03-01T02:46:51Z
dc.date.available	2014-03-01T02:46:51Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32892
dc.subject	CAD	en
dc.subject	Feature extraction	en
dc.subject	Feature selection	en
dc.subject	Microcalcification	en
dc.subject.other	Benign lesion	en
dc.subject.other	Breast microcalcifications	en
dc.subject.other	CAD	en
dc.subject.other	Classification of data	en
dc.subject.other	Computer aided diagnosis systems	en
dc.subject.other	Feature selection	en
dc.subject.other	Feature selection methods	en
dc.subject.other	Image features	en
dc.subject.other	Inherent limitations	en
dc.subject.other	Machine learning techniques	en
dc.subject.other	Mammography database	en
dc.subject.other	Microcalcifications	en
dc.subject.other	Pre-processing step	en
dc.subject.other	Ranking and selection	en
dc.subject.other	Classification (of information)	en
dc.subject.other	Computer aided diagnosis	en
dc.subject.other	Image processing	en
dc.subject.other	Imaging systems	en
dc.subject.other	Mammography	en
dc.subject.other	Feature extraction	en
dc.title	Investigating the image features landscape for the classification of breast microcalcifications	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IST.2010.5548502	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IST.2010.5548502	en
heal.identifier.secondary	5548502	en
heal.publicationDate	2010	en
heal.abstract	Computer aided diagnosis systems using machine learning techniques have been developed in order to assist radiologists' diagnosis and overcome inherent limitations of conventional mammography. Such systems base their diagnosis on image features extracted from mammograms, which are mainly related to the shape, the morphology, the texture and the position of the suspicious abnormality. Since the discrimination of malignant and benign lesions is a classification problem, a feature selection preprocessing step is needed in order to minimize the dimensionality of the features set by keeping the most significant between them. In this paper, we compare four feature selection methods all based on different approaches on ranking and selection and perform classification of data. Experiments were performed on cases containing clusters of microcalcifications, extracted from a large public mammography database. Our findings indicate that there are subsets of very small number of features that can provide a proper baseline classification. © 2010 IEEE.	en
heal.journalName	2010 IEEE International Conference on Imaging Systems and Techniques, IST 2010 - Proceedings	en
dc.identifier.doi	10.1109/IST.2010.5548502	en
dc.identifier.spage	139	en
dc.identifier.epage	143	en