Lu Yangbai, Yuan Runqiang, Su Yun, Liang Zhiying, Huang Hongxing, Leng Qu, Yang Ang, Xiao Xuehong, Lai Zhaoqi, Zhang Yongxin
Department of Urology, Zhongshan City People's Hospital, Shiqi District, No. 2, Sunwen East Road, Zhongshan, 528403, Guangdong, China.
Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, NO.107, Yanjiang West Road, Guangzhou, 510120, China.
Sci Rep. 2025 Jan 3;15(1):654. doi: 10.1038/s41598-024-84908-w.
To investigate the potential of an MRI-based radiomic model in distinguishing malignant prostate cancer (PCa) nodules from benign prostatic hyperplasia (BPH)-, as well as determining the incremental value of radiomic features to clinical variables, such as prostate-specific antigen (PSA) level and Prostate Imaging Reporting and Data System (PI-RADS) score. A restrospective analysis was performed on a total of 251 patients (training cohort, n = 119; internal validation cohort, n = 52; and external validation cohort, n = 80) with prostatic nodules who underwent biparametric MRI at two hospitals between January 2018 and December 2020. A total of 1130 radiomic features were extracted from each MRI sequence, including shape-based features, gray-level histogram-based features, texture features, and wavelet features. The clinical model was constructed using logistic regression analysis. Radiomic models were created by comparing seven machine learning classifiers. The useful clinical variables and radiomic signature were integrated to develop the combined model. Model performance was assessed by receiver operating characteristic curve, calibration curve, decision curve, and clinical impact curve. The ratio of free PSA to total PSA, PSA density, peripheral zone volume, and PI-RADS score were independent determinants of malignancy. The clinical model based on these factors achieved an AUC of 0.814 (95% CI: 0.763-0.865) and 0.791 (95% CI: 0.742-840) in the internal and external validation cohorts, respectively. The clinical-radiomic nomogram yielded the highest accuracy, with an AUC of 0.925 (95% CI: 0.894-0.956) and 0.872 (95% CI: 0.837-0.907) in the internal and external validation cohorts, respectively. DCA and CIC further confirmed the clinical usefulness of the nomogram. Biparametric MRI-based radiomics has the potential to noninvasively discriminate between-BPH and malignant PCa nodules, which outperforms screening strategies based on PSA and PI-RADS.
为了研究基于磁共振成像（MRI）的放射组学模型在鉴别恶性前列腺癌（PCa）结节与良性前列腺增生（BPH）结节方面的潜力，以及确定放射组学特征对临床变量（如前列腺特异性抗原（PSA）水平和前列腺影像报告和数据系统（PI-RADS）评分）的增量价值。对2018年1月至2020年12月期间在两家医院接受双参数MRI检查的251例前列腺结节患者（训练队列，n = 119；内部验证队列，n = 52；外部验证队列，n = 80）进行了回顾性分析。从每个MRI序列中提取了总共1130个放射组学特征，包括基于形状的特征、基于灰度直方图的特征、纹理特征和小波特征。使用逻辑回归分析构建临床模型。通过比较七个机器学习分类器创建放射组学模型。整合有用的临床变量和放射组学特征以开发联合模型。通过受试者操作特征曲线、校准曲线、决策曲线和临床影响曲线评估模型性能。游离PSA与总PSA的比值、PSA密度、外周带体积和PI-RADS评分是恶性肿瘤的独立决定因素。基于这些因素的临床模型在内部和外部验证队列中的AUC分别为0.814（95%CI：0.763 - 0.865）和0.791（95%CI：0.742 - 840）。临床-放射组学列线图的准确性最高，在内部和外部验证队列中的AUC分别为0.925（95%CI：0.894 - 0.956）和0.872（95%CI：0.837 - 0.907）。决策曲线分析（DCA）和临床影响曲线（CIC）进一步证实了列线图的临床实用性。基于双参数MRI的放射组学有潜力无创地区分BPH和恶性PCa结节，其性能优于基于PSA和PI-RADS的筛查策略。
