The value of a machine learning-based biparametric MRI radiomics model in predicting clinically significant prostate cancer in the transitional zone
10.3969/j.issn.1002-1671.2024.11.019
- VernacularTitle:基于机器学习的双参数MRI影像组学模型在移行带临床显著性前列腺癌预测中的价值
- Author:
Lu LI
1
,
2
;
Xu YAN
;
Ke MA
;
Yuting WANG
;
Qin JIN
;
Yiqi PAN
;
Qi SUN
;
Xiaoli MAI
Author Information
1. 南京医科大学鼓楼临床医学院医学影像科,江苏 南京 210008
2. 宣城市中心医院影像科,安徽 宣城 242000
- Keywords:
prostate cancer;
magnetic resonance imaging;
texture analysis;
radiomics;
machine learning
- From:
Journal of Practical Radiology
2024;40(11):1837-1842
- CountryChina
- Language:Chinese
-
Abstract:
Objective To evaluate the value of a machine learning-based biparametric magnetic resonance imaging(bpMRI)radiomics model in predicting clinically significant prostate cancer(csPCa)in the transitional zone.Methods A retrospective analysis was con-ducted on 507 cases in two medical centers.All patients underwent prostate MRI examinations before surgery,with complete patho-logical data.The case distribution was as follows:256 cases of csPCa,97 cases of clinically insignificant prostate cancer(ciPCa),and 154 cases of benign prostatic hyperplasia(BPH).Using the R language,the data from Center One was randomly divided into training and test groups at a ratio of 7∶3,and the data from Center Two as an independent external validation group.The image features from T2 WI and diffusion weighted imaging(DWI)were extracted,and the least absolute shrinkage and selection operator(LASSO)was used to reduce dimensionality and filter features.Two datasets were constructed based on T2 WI features alone and combined T2 WI and DWI features.Six prediction models were established using random forest(RF),logistic regression(LR),and support vector machine(SVM).The efficacy of six models of T2 WI features and combined T2 WI and DWI features in the diagnosis of prostate dis-eases through receiver operating characteristic(ROC)curve,area under the curve(AUC),and decision curve analysis(DCA)were compared and evaluated.Results In the training group,feature screening identified 7 and 8 features from the T2WI single sequence and the T2WI with DWI dual sequence for csPCa prediction in the transitional zone.The results showed that the T2WI with DWI dual sequence RF model had the highest AUC performance.The AUC of the training,test,and validation groups were 0.950,0.866,and 0.818,respectively.The test group accuracy was 0.805,sensitivity was 0.690,and specificity was 0.920;the validation group accu-racy was 0.726,sensitivity was 0.661,and specificity was 0.793.DCA showed that within a wide probability threshold range,the T2 WI with DWI dual sequence RF model had the greatest net benefit.Conclusion Based on the bpMRI radiomics model,non-invasive prediction of csPCa in the transitional zone can be achieved before surgery,which helps to make clinical diagnosis and treatment decisions.
