摘要
目的基于双参数MRI图像纹理构建一个影像组学模型,并探讨其对临床显著性前列腺癌(clinically significant prostate cancer,csPCa)的诊断价值。材料与方法回顾性分析381例(非csPCa组239例,csPCa组142例)患者临床、病理及影像资料。通过图像预处理与分割,特征提取与选择,建立影像组学模型,评估模型对csPCa的诊断价值。结果基于双参数MRI图像所提取的影像组学特征在观察者内及观察者间均具有良好的一致性,构建的影像组学模型对csPCa具有较高的诊断价值,训练组和测试组的曲线下面积(area under the curve,AUC)值分别为0.991、0.983。结论双参数MRI是检出csPCa的有效方法,经训练并测试所构建的影像组学模型对csPCa具有较高的诊断价值,且相对客观、准确,可作为临床诊断csPCa的辅助方法,为临床制订患者诊疗决策提供重要参考依据。
Objective:To evaluate the radiomics model constructed based on biparametric MRI for predicting clinically significant prostate cancer(csPCa).Materials and Methods:The clinical,pathological and imaging data of 381 patients(non-csPCa group 239,csPCa group 142)were analyzed retrospectively.Through image preprocessing and segmentation,feature extraction and selection,the radiomics model was established and its diagnostic value was evaluated.Results:The radiomics model based on biparametric MRI showed good intra-observer and inter-observer consistency,and the constructed radiomics model had high diagnostic value for csPCa.The area under the curve(AUC)values of the training group and the test group were 0.991 and 0.983,respectively.Conclusions:The biparametric MRI is an effective method to detect csPCa.The radiomics model constructed by training and testing has high diagnostic value for csPCa,which is relatively objective and accurate.It can be used as an auxiliary method for clinical diagnosis of csPCa,and provide an important reference for clinical decision-making of patient diagnosis and treatment.
作者
李梦娟
张彩元
赵文露
魏超刚
张跃跃
丁宁
王成成
计一丁
沈钧康
LI Mengjuan;ZHANG Caiyuan;ZHAO Wenlu;WEI Chaogang;ZHANG Yueyue;DING Ning;WANG Chengcheng;JI Yiding;SHEN Junkang(Department of Imaging,Suzhou Ninth People's Hospital,Suzhou 215004,China;Department of Imaging,Second Affiliated Hospital of Soochow University,Suzhou 215004,China)
出处
《磁共振成像》
CAS
CSCD
北大核心
2022年第11期76-81,共6页
Chinese Journal of Magnetic Resonance Imaging
基金
国家自然科学基金青年科学基金(编号:81801754)
苏州市科技发展计划(编号:SS2019012)
苏州市第九人民医院院级科研项目(编号:YK202020)。
关键词
前列腺癌
磁共振成像
影像组学
诊断效能
prostate cancer
magnetic resonance imaging
radiomics
diagnostic efficacy
