Characterization of CT Liver Lesions Based on Texture Features and a Multiple Neural Network Classification Scheme

Mougiakakou, SGr; Valavanis, I; Nikita, KS; Nikita, A; Kelekis, D

dc.contributor.author	Mougiakakou, SGr	en
dc.contributor.author	Valavanis, I	en
dc.contributor.author	Nikita, KS	en
dc.contributor.author	Nikita, A	en
dc.contributor.author	Kelekis, D	en
dc.date.accessioned	2014-03-01T02:42:12Z
dc.date.available	2014-03-01T02:42:12Z
dc.date.issued	2003	en
dc.identifier.issn	05891019	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30863
dc.subject	Genetic algorithm	en
dc.subject	Liver CT images	en
dc.subject	Multiple neural network classification	en
dc.subject	Texture features	en
dc.subject	Voting scheme	en
dc.subject.other	Backpropagation	en
dc.subject.other	Biological organs	en
dc.subject.other	Computer aided diagnosis	en
dc.subject.other	Computerized tomography	en
dc.subject.other	Genetic algorithms	en
dc.subject.other	Learning systems	en
dc.subject.other	Neural networks	en
dc.subject.other	Statistics	en
dc.subject.other	Textures	en
dc.subject.other	Multiple neural network classification	en
dc.subject.other	Texture features	en
dc.subject.other	Medical imaging	en
dc.title	Characterization of CT Liver Lesions Based on Texture Features and a Multiple Neural Network Classification Scheme	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IEMBS.2003.1279504	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IEMBS.2003.1279504	en
heal.publicationDate	2003	en
heal.abstract	In this paper, a Computer Aided Diagnosis (CAD) system for the characterization of hepatic tissue from Computed Tomography (CT) images is presented. Regions of Interest (ROI's) corresponding to normal liver, cyst, hemangioma, and hepatocellular carcinoma, are drawn by an experienced radiologist on abdominal non-enhanced CT images. For each ROI, five distinct sets of texture features are extracted using the following methods: first order statistics, spatial gray level dependence matrix, gray level difference method, Laws' texture energy measures, and fractal dimension measurements. If the dimensionality of a feature set is greater than a predefined threshold, feature selection based on a Genetic Algorithm (GA) is applied. Classification of the ROI is then carried out by a system of five neural networks (NNs), each using as input one of the above feature sets. The members of the NN system (primary classifiers) are 4-class NNs trained by the backpropagation algorithm with adaptive learning rate and momentum. The final decision of the CAD system is based on the application of a voting scheme across the outputs of the individual NNs. The multiple classification scheme using the five sets of texture features results in significantly enhanced performance, as compared to the classification performance of the individual primary classifiers.	en
heal.journalName	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings	en
dc.identifier.doi	10.1109/IEMBS.2003.1279504	en
dc.identifier.volume	2	en
dc.identifier.spage	1287	en
dc.identifier.epage	1290	en