RetrospectiveanalysisofCT manifestationsofsolitarylungcancernodules less th a n 2 c m usin g L o g istic regressio n a n alysis
10.3969/j.issn.1002-1671.2019.05.010
- VernacularTitle:用Logistic回归分析法对直径＜2cm孤立肺癌结节CT征象的回顾性分析
- Author:
Weitian LIN
1
;
Li SHI
;
Zhiyu LIANG
;
Jianwei HUANG
Author Information
1. 广州医科大学附属第三医院放射科
- Keywords:
solitary lung cancer nodules;
L o g istic regression analysis;
co m puted to m ography;
ground-glass sign
- From:
Journal of Practical Radiology
2019;35(5):726-729
- CountryChina
- Language:Chinese
-
Abstract:
Objective ToanalyzethecharacteristicmanifestationsandearlydiagnosticvalueofCTinsolitarypulmonarynodules (SPNs)lessthan2cmusing L o g istic regressionanalysis.Methods 156patientswithSPNlessthan2cmconfirmedbypathology werecollected.Statisticalassignment was performed and binary L o g istic regression wasimplemented for CT manifestations.Those features,whichmightbesignsoflungcancer,wereextractedfromtheCTimagesandtheirrisklevelswerealsoanalyzed.Results SixCTsignsincluding "ground-glasssign"(8.12),"lobulationsign"(6.72),"vascularconvergencesign"(6.02),"spiculesign"(5.07),"necrosis and cavitation "(3.41 ),and "vacuole sign (1.02 )" were enrolled in the L o g istic equation.Conclusion "Ground-glass sign "is associated with the highest risk level for lung cancer nodules.T he L o g istic m odel constructed fro m C T m anifestations is helpful for identifyingsolitarylungcancernodules.
