Diagnostic value of lumbar spine CT radiomics nomogram in osteoporosis
10.3969/j.issn.1002-1671.2024.07.022
- VernacularTitle:基于腰椎CT影像组学列线图对骨质疏松的诊断价值
- Author:
Zhai LIU
1
;
Ting GAO
;
Hui XU
;
Qingyun REN
Author Information
1. 河北医科大学第一医院放射科,河北 石家庄 050000
- Keywords:
osteoporosis;
bone mineral density;
lumbar spine;
computed tomography;
radiomics
- From:
Journal of Practical Radiology
2024;40(7):1133-1137
- CountryChina
- Language:Chinese
-
Abstract:
Objective To investigate the diagnostic value of lumbar spine CT radiomics nomogram for osteoporosis(OP).Methods A total of 414 patients who underwent abdominal CT and quantitative computed tomography(QCT)examinations were retrospectively selected.The patients were randomly divided into a training group(n=290)and a validation group(n=124)at a ratio of 7∶3.Radiomics features were extracted from lumbar spine CT images.The least absolute shrinkage and selection operator(LASSO)algorithm was used for dimen-sion reduction and feature selection.Multivariable logisitic regression was used to build the radiomics signature and the radiomics nomo-gram.The area under the curve(AUC)of receiver operating characteristic(ROC)curve was used to analyze the diagnostic performance of the Radiomics score(Radscore)and radiomics nomogram in diagnosing OP.The DeLong test was used to compare the diagnostic performance between the two models.Results Eight radiomics features were selected to establish the Radscore.The AUC of the Radscore and radiomics nomograms in the validation group for distinguishing normal bone mass from reduced bone mass and OP,reduced bone mass from OP,and OP from reduced bone mass and normal bone mass were 0.891 and 0.976,0.866 and 0.976,0.897 and 0.982,respectively.According to the DeLong test,the AUC of the radiomics nomograms was significantly higher than that of the Radscore(P＜0.05).Conclusion The radiomics nomogram model based on lumbar spine CT can serve as a novel method for individualized assess-ment of OP and provide assistance to clinical decision-making.
