Clinical value of a nomogram based on biparametric MRI radiomics combined with apparent diffusion coefficient values in Gleason score of prostate cancer
10.3969/j.issn.1002-1671.2025.06.021
- VernacularTitle:基于双参数MRI影像组学联合表观扩散系数值的诺模图在前列腺癌Gleason评分中的临床价值研究
- Author:
Lei SHEN
1
;
Wei SONG
1
;
Qian ZHANG
1
;
Xiangwei LUO
1
;
Yu ZHANG
1
Author Information
1. 中国人民解放军联勤保障部队第九○一医院放射诊断科,安徽 合肥 230031
- Publication Type:Journal Article
- Keywords:
prostate cancer;
magnetic resonance imaging;
radiomics;
Gleason score
- From:
Journal of Practical Radiology
2025;41(6):994-998
- CountryChina
- Language:Chinese
-
Abstract:
Objective To evaluate the clinical value of a nomogram based on biparametric MRI radiomics combined with apparent diffusion coefficient(ADC)values in predicting Gleason score(GS)of prostate cancer(PCa).Methods A retrospective analysis was conducted on MRI data of 105 PCa patients.The radiomics features were extracted from region of interest(ROI)delineated on ADC and T2WI images,and after screening features,the radiomics model was established and the Radiomics score(Radscore)was calculated.Clinical factors and Radscore were analyzed using logistic regression to identify independent predictors of GS,which were used to construct a combined model and plot nomogram.The area under the curve(AUC),decision curve analysis(DCA),and calibration curves were used to evaluate the performance of combined model,and compare it with radiomics model.Results A total of 214 radiomics features were extracted,and three features were selected to establish a radiomics model and calculate the Radscore.Radscore and ADC values were independent predictors for assessing GS,and a combined model was constructed based on these two factors.The AUC of the radiomics model and the combined model in the training set were 0.801 and 0.866,respectively;and the AUC in the test set were 0.767 and 0.838,respectively.The combined model had better predictive value,calibration,and clinical application value,and its predictive performance was better than that of the radiomics model.Conclusion The nomogram constructed based on biparametric MRI radiomics combined with ADC values can noninvasively distinguish PCa in Gleason low-middle-risk from high-risk.
