Zhu Wenhao, Tang Yongxiang, Qi Lin, Gao Xiaomei, Hu Shuo, Chen Min-Feng, Cai Yi
Department of Urology, Disorders of Prostate Cancer Multidisciplinary Team, National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, PR China.
Department of Nuclear Medicine, National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, PR China.
Eur J Radiol. 2025 May;186:112063. doi: 10.1016/j.ejrad.2025.112063. Epub 2025 Mar 19.
Prostate cancer (PCa) is highly heterogeneous, making early detection of adverse pathological features crucial for improving patient outcomes. This study aims to predict PCa aggressiveness and identify radiomic and protein biomarkers associated with poor pathology, ultimately developing a multi-omics marker model for better clinical risk stratification.
In this retrospective study, 191 patients with PCa or benign prostatic hyperplasia confirmed via Ga-PSMA-617 PET/CT scans were analyzed. Radiomic features were extracted from scan contours, and six machine learning algorithms were used to predict malignancy and adverse pathological features like Gleason score, ISUP group, tumor stage, lymph node infiltration, and perineural invasion. Feature selection and dimensionality reduction were performed using minimum redundancy maximum relevance and least absolute shrinkage and selection operator methods. Proteomics analysis on 39 patients identified protein biomarkers, followed by correlation analysis between radiomic features and identified proteins.
The radiomics model showed an AUC of 0.938 for predicting malignant prostate lesions and 0.916 for adverse pathological features in the test set, with validation set AUCs of 0.918 and 0.855, respectively. Three quantitative radiomic features and ten protein molecules associated with adverse pathology were identified, with significant correlations observed between radiomic features and protein biomarkers. Radioproteomic analysis revealed that molecular changes in protein molecules could influence imaging biomarkers.
The machine learning models based on 68 Ga-PSMA-617 PET/CT radiomic features performed well in stratifying patients, supporting clinical risk stratification and highlighting connections between radiomic characteristics and protein biomarkers.
前列腺癌（PCa）具有高度异质性，因此早期检测不良病理特征对于改善患者预后至关重要。本研究旨在预测PCa的侵袭性，识别与不良病理相关的放射组学和蛋白质生物标志物，最终开发一种多组学标志物模型以实现更好的临床风险分层。
在这项回顾性研究中，分析了191例经Ga-PSMA-617 PET/CT扫描确诊为PCa或良性前列腺增生的患者。从扫描轮廓中提取放射组学特征，并使用六种机器学习算法预测恶性肿瘤以及诸如Gleason评分、ISUP分组、肿瘤分期、淋巴结浸润和神经周围浸润等不良病理特征。使用最小冗余最大相关性和最小绝对收缩与选择算子方法进行特征选择和降维。对39例患者进行蛋白质组学分析以识别蛋白质生物标志物，随后进行放射组学特征与已识别蛋白质之间的相关性分析。
放射组学模型在测试集中预测恶性前列腺病变的AUC为0.938，预测不良病理特征的AUC为0.916，验证集的AUC分别为0.918和0.855。识别出三个与不良病理相关的定量放射组学特征和十个蛋白质分子，放射组学特征与蛋白质生物标志物之间存在显著相关性。放射蛋白质组学分析表明蛋白质分子的分子变化可能影响成像生物标志物。
基于68Ga-PSMA-617 PET/CT放射组学特征的机器学习模型在患者分层方面表现良好，支持临床风险分层，并突出了放射组学特征与蛋白质生物标志物之间的联系。
