多参数MRI生境成像无创定量可视化预测前列腺癌危险度的研究  

Non-invasive quantitative visualization of multi-parametric MRI habitat imaging for predicting prostate cancer risk degree

作　　者：袁蕾 张景良 马丽娜 韩晔 侯国瑞 秦卫军 张静 宦怡 任静 Yuan Lei;Zhang Jingliang;Ma Lina;Han Ye;Hou Guorui;Qin Weijun;Zhang Jing;Huan Yi;Ren Jing(Department of Radiology,Xijing Hospital,Air Force Medical University,Xi′an 710032,China;Department of Urology,Xijing Hospital,Air Force Medical University,Xi′an 710032,China;Department of Pathology,Xijing Hospital,Air Force Medical University,Xi′an 710032,China)

机构地区：[1]空军军医大学西京医院放射科,西安710032 [2]空军军医大学西京医院泌尿外科,西安710032 [3]空军军医大学西京医院病理科,西安710032

出　　处：《中华放射学杂志》2025年第4期393-400,共8页Chinese Journal of Radiology

基　　金：国家自然科学基金(82220108004,82302244);西京医院助推项目创新医学专项研究(XJZT25CX07)。

摘　　要：目的探讨生境成像(HI)预测前列腺癌(PCa)危险度的价值。方法本研究为横断面研究,回顾性收集2018年1月至2024年5月空军军医大学西京医院行多参数MRI(mpMRI)扫描,并经根治性前列腺切除术(RP)证实的PCa患者220例,通过简单随机抽样法以7∶3的比例分为训练集154例和测试集66例。基于mpMRI成像,整合每体素表观扩散系数(ADC)、灌注分数(f)和平均峰度(MK),使用K-means聚类算法将PCa靶病灶划分为k个生境亚区,生成生境地图,计算各生境亚区在整个病灶的占比。根据2019版国际泌尿病理协会(ISUP)指南,将患者分为低危组(ISUP≤2,65例)和高危组(ISUP≥3,155例)。将RP标本切片与生境地图匹配,识别对应的生境亚区,分别评估每个亚区的ISUP分级,计算各亚区中高危PCa患者的检出率。采用logistic回归分析PCa危险度的独立危险因素并构建HI-临床影像模型和临床影像模型,绘制受试者工作特征曲线评估模型效能。结果按照最佳聚类簇数划分为3个生境亚区,生境1的ADC、f值更低,MK值更高,生境2与其相反,生境3介于两者之间。高危组的生境1占比为28.8%,低危组为8.9%。生境亚区与病理对照示训练集中生境1、生境2和生境3中高危PCa病灶的检出率为66.9%(103/154)、25.3%(39/154)和47.4%(73/154)。Logistic回归分析示生境1占比(OR=3.03,95%CI 1.77~5.18,P<0.001)、前列腺特异性抗原(OR=1.66,95%CI 1.04~2.66,P=0.034)和前列腺影像报告与数据系统评分(OR=1.65,95%CI 1.00~2.70,P=0.048)是高危PCa的独立危险因素。训练集中,HI-临床影像模型和临床影像模型预测PCa危险度的曲线下面积分别为0.854(95%CI 0.789~0.920)和0.779(95%CI 0.701~0.856);测试集中,二者分别为0.809(95%CI 0.693~0.895)和0.738(95%CI 0.619~0.856)。结论基于mpMRI的HI可有效预测PCa危险度。ObjectiveTo explore the value of non-invasive habitat imaging(HI)multi-parametric MRI(mpMRI)in predicting the risk of prostate cancer(PCa).MethodsIn this cross-sectional study,220 patients with PCa confirmed by radical prostatectomy(RP)who underwent multi-parametric MRI(mpMRI)scanning at Xijing Hospital,Air Force Military Medical University from January 2018 to May 2024 were retrospectively collected.Patients were divided into a training set(154 cases)and a test set(66 cases)by simple random sampling in a 7∶3 ratio.Based on mpMRI imaging,the apparent diffusion coefficient(ADC),perfusion fraction(f),and mean kurtosis(MK)of each voxel were integrated.The K-means clustering algorithm was used to divide the PCa target lesions into habitat subregions,generate habitat maps,and calculate the proportion of each habitat subregion in the entire lesion.According to the 2019 International Society of Urological Pathology(ISUP)guidelines,patients were categorized into a low-risk group(ISUP≤2,65 cases)and a high-risk group(ISUP≥3,155 cases).The RP specimens were matched with the habitat map to identify corresponding habitat subregions,and the ISUP grade of each subregion was individually evaluated to calculate the detection rate of high-risk PCa patients.The logistic regression analysis was applied to identify the independent risk factors associated with PCa risk,and the HI-clinical imaging model and clinical imaging model were constructed.The efficacy of the models was assessed using receiver operating characteristic curve.ResultsBased on the optimal cluster number,the habitat was divided into three subregions.Habitat 1 had lower ADC and f values and higher MK values,while habitat 2 had the opposite characteristics,and habitat 3 was intermediate.The proportion of habitat 1 in the high-risk group was 28.8%,in the low-risk group was 8.9%.In the training set,the comparison of habitat subregions with pathological results showed that the detection rate of high-risk lesions was 66.9%(103/154)in habitat 1,25.3%(39/154)in habita

关 键 词：前列腺肿瘤 磁共振成像 生境成像 危险度 

分 类 号：R737.25[医药卫生—肿瘤]