Value of conventional CT signs combined with histogram parameters in diagnosis of different pathological subtypes of lung adenocarcinoma
LU Chuanwen
WANG Qiong
MA Yuping
SU Sheng
ZHU Jianguo
Abstract：Objective To investigate the value of conventional CT signs combined with HA parameters in diagnosing acinar type of lung adenocarcinoma.Methods A total of 300 pulmonary nodules were retrospectively collected from 283 patients oper-ated,including 170 acinar types and 130 non-acinar types.They were divided into training set and validation set according to 7∶3 ratio.The combined model of conventional CT signs and histogram(HA)parameters was established by using single factor analysis,LASSO regression analysis and multifactor analysis.The area under the curve(AUC)was used to compare the efficacy of the combined model in differentiating acinar and non-acinar types of lung adenocarcinoma,and the calibration curve and clini-cal decision curve(DCA)were used to evaluate the calibration degree and clinical practicability of the model.Results Five characteristics and parameters were selected by single factor analysis and LASSO regression analysis.Binary Logistic regression showed that pure ground glass nodule,sphericity and entropy were independent predictors of the diagnosis of acinar lung adeno-carcinoma.The AUC of the combined model in the training set and validation set were 0.737 and 0.790,respectively.The calibra-tion curve showed that the calibration degree of the combined model was good.When the threshold was>0.30 in the training set and>0.28 in the validation set,the combined model had a higher clinical net benefit.Conclusion The combined model of con-ventional CT signs and HA parameters can effectively diagnose acinar type of lung adenocarcinoma.
Keywords：Lung adenocarcinomapathological subtypeHistogram parameterTomographyX-ray computed
Publication Date：2025-08-30
Online Publishing Date：2025-09-28(First online date of this platform, not the publication date of the document)
Pages：5( 69-73 )