Predictive value of diffusion weighted imaging radiomic features combined with apparent diffusion coefficient values for p53 gene mutation status in endometrial cancer
10.3969/j.issn.1002-1671.2024.12.014
- VernacularTitle:扩散加权成像影像组学特征联合表观扩散系数值对子宫内膜癌p53基因突变状态的预测价值
- Author:
Fang ZHOU
1
;
Dandan ZHAO
;
Zhen GUO
;
Jikai ZHENG
;
Yongchao NIU
Author Information
1. 新乡市中心医院磁共振科 新乡市医学影像工程技术研究中心,河南 新乡 453000
- Keywords:
endometrial cancer;
diffusion weighted imaging;
radiomics;
p53 gene mutation
- From:
Journal of Practical Radiology
2024;40(12):1998-2001
- CountryChina
- Language:Chinese
-
Abstract:
Objective To explore the value of the prediction model based on diffusion weighted imaging(DWI)radiomic features and apparent diffusion coefficient(ADC)values in the assessment of p53 gene mutation status in endometrial cancer(EC).Methods The DWI data of 22 p53 wild-type and 60 p53 mutant EC patients were analyzed retrospectively.The DWI radiomic features of the primary lesions were extracted,and the ADC values were calculated.The prediction model was constructed based on support vector machine(SVM)algorithm.The area under the curve(AUC)of the receiver operating characteristic(ROC)curve was used to evaluate the performance of the prediction model.Internal validation was conducted using Bootstrap.Results The ADC value of p53 mutant EC was significantly lower than that of p53 wild-type EC(P=0.002).When comparing the ADC value and radiomics model,the combined ADC-radiomics model demonstrated the highest diagnostic efficacy,achieving an AUC of 0.924,sensitivity of 86.67％,and specificity of 90.91％.In Bootstrap-based validation,the combined ADC-radiomics model also showed high performance with an AUC of 0.904.The calibration curve and clinical decision curve analysis(DCA)showed that the combined ADC-radiomics model not only had better agreement between predicted and actual observed values but also provided better net benefits for the patients concerned.Conclusion The combined ADC-radiomics model achieved a more efficient assessment of p53 status in EC patients.
