Advanced Search

Show simple item record

dc.contributor.authorAyyildiz, Oguzhan
dc.contributor.authorAydin, Zafer
dc.contributor.authorYilmaz, Bulent
dc.contributor.authorKaracavus, Seyhan
dc.contributor.authorenkaya, Kubra
dc.contributor.authorIcer, Semra
dc.contributor.authorTasdemir, Arzu
dc.contributor.authorKaya, Eser
dc.date.accessioned2021-03-01T10:28:25Z
dc.date.available2021-03-01T10:28:25Z
dc.date.issued2020en_US
dc.identifier.issn1300-0632
dc.identifier.issn1303-6203
dc.identifier.urihttps://doi.org/10.3906/elk-1810-154
dc.identifier.urihttps://hdl.handle.net/20.500.12573/565
dc.descriptionThis study was supported by the Scientific and Technological Research Council of Turkey (TUBITAK) under Project No: 113E188.en_US
dc.description.abstractLung cancer is one of the deadly cancer types, and almost 85% of lung cancers are nonsmall cell lung cancer (NSCLC). In the present study we investigated classification and feature selection methods for the differentiation of two subtypes of NSCLC, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). The major advances in understanding the effects of therapy agents suggest that future targeted therapies will be increasingly subtype specific. We obtained positron emission tomography (PET) images of 93 patients with NSCLC, 39 of which had ADC while the rest had SqCC. Random walk segmentation was applied to delineate three-dimensional tumor volume, and 39 texture features were extracted to grade the tumor subtypes. We examined 11 classifiers with two different feature selection methods and the effect of normalization on accuracy. The classifiers we used were the k-nearest-neighbor, logistic regression, support vector machine, Bayesian network, decision tree, radial basis function network, random forest, AdaBoostM1, and three stacking methods. To evaluate the prediction accuracy we performed a leave-one-out cross-validation experiment on the dataset. We also considered optimizing certain hyperparameters of these models by performing 10-fold cross-validation separately on each training set. We found that the stacking ensemble classifier, which combines a decision tree, AdaBoostM1, and logistic regression methods by a metalearner, was the most accurate method for detecting subtypes of NSCLC, and normalization of feature sets improved the accuracy of the classification method.en_US
dc.description.sponsorshipTurkiye Bilimsel ve Teknolojik Arastirma Kurumu (TUBITAK) 113E188en_US
dc.language.isoengen_US
dc.publisherTUBITAK SCIENTIFIC & TECHNICAL RESEARCH COUNCIL TURKEY, ATATURK BULVARI NO 221, KAVAKLIDERE, ANKARA, 00000, TURKEYen_US
dc.relation.isversionof10.3906/elk-1810-154en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjecttexture analysisen_US
dc.subjectlung canceren_US
dc.subjectPETen_US
dc.subjectMachine learningen_US
dc.titleLung cancer subtype differentiation from positron emission tomography imagesen_US
dc.typearticleen_US
dc.contributor.departmentAGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümüen_US
dc.identifier.volumeVolume: 28en_US
dc.identifier.issue1en_US
dc.identifier.startpage262en_US
dc.identifier.endpage274en_US
dc.relation.journalTURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCESen_US
dc.relation.tubitak113E188
dc.relation.publicationcategoryMakale - Uluslararası - Editör Denetimli Dergien_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record