Predictive value of CT radiomics analysis on the curative effect of extracorporeal shock wave lithotripsy in ureteral calculus patients
10.3969/j.issn.1002-1671.2025.08.019
- VernacularTitle:CT影像组学对输尿管结石体外震波碎石术的疗效预测价值
- Author:
Zhicheng DONG
1
;
Weiling PAN
;
Xiaoyang ZHAO
;
Dongxue YIN
;
Zhibo WANG
;
Shuai ZHAO
Author Information
1. 中国融通医疗健康集团淄博一四八医院医学影像中心,山东 淄博 255300
- Publication Type:Journal Article
- Keywords:
computed tomography;
radiomics;
ureteral calculus;
extracorporeal shock wave lithotripsy
- From:
Journal of Practical Radiology
2025;41(8):1343-1347
- CountryChina
- Language:Chinese
-
Abstract:
Objective To explore the value of CT radiomics analysis in predicting the curative effect of extracorporeal shock wave lithotripsy(ESWL)in ureteral calculus(UC)patients.Methods A total of 126 UC patients who underwent ESWL from January 2018 to December 2023 were selected,and randomly divided into training group and validation group at a ratio of 7∶3.Forty-five UC patients from January 2024 to September 2024 were selected as external validation group and divided into two groups according to whether the residual stones were less than 4 mm after operation.There were 81 cases in the successful lithotripsy group and 45 cases in the failed lithotripsy group.The 3D Slicer software was used to outline the stone layer by layer to obtain region of interest(ROI),and 851 radiomics features were extracted.After the observer consistency test,maximum relevance and minimum redundancy(mRMR)algorithm and least absolute shrinkage and selection operator(LASSO),the radiomics features were selected,and the logistic regression model was established.The diagnostic efficiency of the model was analyzed by receiver operating characteristic(ROC)curve.Results The six optimal features were obtained from the radiomics features.The combined clinical-radiomics model showed the best prediction efficiency with area under the curve(AUC)of 0.908,0.906 and 0.908 in the training,validation and external validation groups respectively.Conclusion CT radiomics model can be used to predict the curative effect of UC patients after ESWL,and provide a basis for assisting UC patients in individualized treatment.
