Role of the texture features of images in the diagnosis of solitary pulmonary nodules in different sizes-中国Betway体育网页登陆

摘要 Objective:Toexploretheroleofthetexturefeaturesofimagesinthediagnosisofsolitarypulmonarynodules(SPNs)indifferentsizes.Materialsandmethods:Atotalof379patientswithpathologicallyconfirmedSPNswereenrolledinthisstudy.TheyweredividedintothreegroupsbasedontheSPNsizes:≤10,11-20,and>20mm.Theirtexturefeaturesweresegmentedandextracted.ThedifferencesintheimagefeaturesbetweenbenignandmalignantSPNswerecompared.TheSPNsinthesethreegroupsweredeterminedandanalyzedwiththetexturefeaturesofimages.Results:These379SPNsweresuccessfullysegmentedusingthe2DOtsuthresholdmethodandtheself-adaptivethresholdsegmentationmethod.ThetexturefeaturesoftheseSPNswereobtainedusingthemethodofgreylevelco-occurrencematrix(GLCM).Ofthese379patients,120hadbenignSPNsand259hadmalignantSPNs.Theentropy,contrast,energy,homogeneity,andcorrelationwere3.5597±0.6470,0.5384±0.2561,0.1921±0.1256,0.8281±0.0604,and0.8748±0.0740inthebenignSPNsand3.8007±0.6235,0.6088±0.2961,0.1673±0.1070,0.7980±0.0555,and0.8550±0.0869inthemalignantSPNs(allP<0.05).Thesensitivity,specificity,andaccuracyofthetexturefeaturesofimageswere83.3%,90.0%,and86.8%,respectively,forSPNssized≤10mm,andwere86.6%,88.2%,and87.1%,respectively,forSPNssized11-20mmand94.7%,91.8%,and93.9%,respectively,forSPNssized>20mm.Conclusions:Theentropyandcontrastofmalignantpulmonarynoduleshavebeendemonstratedtobehigherincomparisontothoseofbenignpulmonarynodules,whiletheenergy,homogeneitycorrelationofmalignantpulmonarynodulesarelowerthanthoseofbenignpulmonarynodules.Thetexturefeaturesofimagescanreflectthetissuefeaturesandhavehighsensitivity,specificity,andaccuracyindifferentiatingSPNs.ThesensitivityandaccuracyincreaseforlargerSPNs.更多还原

1FuYusheng DingDongtao HouYinming.STUDY ON THE TECHNIQUE TO DETECT TEXTURE FEATURES IN SAR IMAGES.物理电子学,2004-06.
2Samia Bouteldja;Assia Kourgli.Retrieval of High Resolution Satellite Images Using Texture Features.物理电子学,2014-02.
3Liu Hai-Yang,Zhao Xing-Ru,Chi Meng,Cheng Xiang-Song,Wang Zi-Qi,Xu Zhi-Wei,Li Yong-Li,Yang Rui,Wu Yong-Jun,Zhang Xiao-Ju.Risk assessment of malignancy in solitary pulmonary nodules in lung computed tomography: a multivariable predictive model study.医药卫生,2021-08.
4Paula D. Brown;Kim S. Finch;Cynthia MacGregor.A Comparison of Learning Cultures in Different Sizes and Types.教育学,2012-02.
5Wei Li;Xuexiang Wang;Yuwei Zhang;Xubin Li;Qian Li;Zhaoxiang ye.Radiomic analysis of pulmonary ground-glass opacity nodules fordistinction of preinvasive lesions, invasive pulmonaryadenocarcinoma and minimally invasive adenocarcinoma basedon quantitative texture analysis of CT.肿瘤,2018-04.
6RAMAKRISHNAN S. SELVAN S..Multiwavelets domain singular value features for image texture classification.物理,2007-04.
7Jau-YauLU;Chih-ChiangSU.TRANSPORT OF GRAVELS WITH DIFFERENT RANGES OF GRAIN SIZES IN A STEEP CHANNEL.地球物理学,2005-02.
8Erivaldo Antonio da Silva;Guilherme Pina Cardim;Ruben de Best.Semiautomatic Algorithm to Extraction of Cartographic Features in Digital Images.计算机应用技术,2012-11.
9Wu Yang;Zhang Dengrong;Zhang Hankui;Wu Honggan.Remote Sensing Estimation of Forest Canopy Density Combined with Texture Features.林学,2012-03.
10Y.Q. Feng A.B. Yu.An analysis of the chaotic motion of particles of different sizes in a gas fluidized bed.力学,2008-06.

Role of the texture features of images in the diagnosis of solitary pulmonary nodules in different sizes

来源期刊

相关推荐

同分类资源更多

相关关键词