Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers

Mougiakakou, SG; Valavanis, IK; Nikita, A; Nikita, KS

dc.contributor.author	Mougiakakou, SG	en
dc.contributor.author	Valavanis, IK	en
dc.contributor.author	Nikita, A	en
dc.contributor.author	Nikita, KS	en
dc.date.accessioned	2014-03-01T01:26:08Z
dc.date.available	2014-03-01T01:26:08Z
dc.date.issued	2007	en
dc.identifier.issn	0933-3657	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/17939
dc.subject	Bootstrap	en
dc.subject	Computer-aided diagnosis	en
dc.subject	Ensembles of classifiers	en
dc.subject	Feature selection	en
dc.subject	Genetic algorithms	en
dc.subject	Liver CT images	en
dc.subject	Texture features	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Engineering, Biomedical	en
dc.subject.classification	Medical Informatics	en
dc.subject.other	Computer aided design	en
dc.subject.other	Feature extraction	en
dc.subject.other	Genetic algorithms	en
dc.subject.other	Image reconstruction	en
dc.subject.other	Medical imaging	en
dc.subject.other	Multilayer neural networks	en
dc.subject.other	Radiology	en
dc.subject.other	Bootstrap	en
dc.subject.other	Gray level difference methods	en
dc.subject.other	Spatial gray level dependence matrix	en
dc.subject.other	Texture features	en
dc.subject.other	Computerized tomography	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	clinical feature	en
dc.subject.other	computer assisted diagnosis	en
dc.subject.other	computer assisted tomography	en
dc.subject.other	differential diagnosis	en
dc.subject.other	fractal analysis	en
dc.subject.other	genetic algorithm	en
dc.subject.other	hemangioma	en
dc.subject.other	liver cell carcinoma	en
dc.subject.other	liver cyst	en
dc.subject.other	liver injury	en
dc.subject.other	perceptron	en
dc.subject.other	priority journal	en
dc.subject.other	radiologist	en
dc.subject.other	Algorithms	en
dc.subject.other	Diagnosis, Differential	en
dc.subject.other	Humans	en
dc.subject.other	Liver Diseases	en
dc.subject.other	Mathematical Computing	en
dc.subject.other	Neural Networks (Computer)	en
dc.subject.other	Radiographic Image Interpretation, Computer-Assisted	en
dc.subject.other	Reproducibility of Results	en
dc.subject.other	Tomography, X-Ray Computed	en
dc.title	Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.artmed.2007.05.002	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.artmed.2007.05.002	en
heal.language	English	en
heal.publicationDate	2007	en
heal.abstract	Objectives: The aim of the present study is to define an optimally performing computer-aided diagnosis (CAD) architecture for the classification of liver tissue from non-enhanced computed tomography (CT) images into normal liver (C1), hepatic cyst (C2), hemangioma (C3), and hepatocellular carcinoma (C4). To this end, various CAD architectures, based on texture features and ensembles of classifiers (ECs), are comparatively assessed. Materials and methods: Number of regions of interests (ROIs) corresponding to C1-C4 have been defined by experienced radiologists in non-enhanced liver CT images. For each ROI, five distinct sets of texture features were extracted using first order statistics, spatial gray level dependence matrix, gray level difference method, Laws' texture energy measures, and fractal dimension measurements. Two different ECs were constructed and compared. The first one consists of five multilayer perceptron neural networks (NNs), each using as input one of the computed texture feature sets or its reduced version after genetic algorithm-based feature selection. The second EC comprised five different primary classifiers, namely one multilayer perceptron NN, one probabilistic NN, and three k-nearest neighbor classifiers, each fed with the combination of the five texture feature sets or their reduced versions. The final decision of each EC was extracted by using appropriate voting schemes, while bootstrap re-sampling was utilized in order to estimate the generalization ability of the CAD architectures based on the available relatively small-sized data set. Results: The best mean classification accuracy (84.96%) is achieved by the second EC using a fused feature set, and the weighted voting scheme. The fused feature set was obtained after appropriate feature selection applied to specific subsets of the original feature set. Conclusions: The comparative assessment of the various CAD architectures shows that combining three types of classifiers with a voting scheme, fed with identical feature sets obtained after appropriate feature selection and fusion, may result in an accurate system able to assist differential diagnosis of focal liver lesions from non-enhanced CT images. (c) 2007 Elsevier B.V. All rights reserved.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	Artificial Intelligence in Medicine	en
dc.identifier.doi	10.1016/j.artmed.2007.05.002	en
dc.identifier.isi	ISI:000249821200003	en
dc.identifier.volume	41	en
dc.identifier.issue	1	en
dc.identifier.spage	25	en
dc.identifier.epage	37	en