基于[18F]PSMA-1007 PET的影像组学模型预测根治性前列腺切除术后生化复发无生存期的开发与验证
本研究回顾性分析236例经组织学确诊前列腺癌并接受根治性前列腺切除术的患者,所有患者术前均行[18F]PSMA-1007 PET/CT,从PET图像原发肿瘤区域提取影像组学特征,采用LASSO Cox回归构建影像组学标签,并在98例独立队列中外部验证。影像组学标签由三个特征组成,训练队列C指数0.76(95%CI 0.60-0.91),验证队列0.71(95%CI 0.63-0.79),多变量分析中为BRFS的独立预测因子(HR 2.48,95%CI 1.47-4.17,p<0.001)。临床-影像组学列线图在训练队列C指数0.81(95%CI 0.66-0.95,p=0.007)、验证队列0.78(95%CI 0.63-0.89,p<0.001),预测性能显著提高。
要点
- 基于术前[18F]PSMA-1007 PET的影像组学标签由三个特征组成,可预测根治性前列腺切除术后的生化复发无生存期。
- 影像组学标签在多变量分析中是BRFS的独立预测因子(HR 2.48,95%CI 1.47-4.17,p<0.001)。
- 临床-影像组学列线图较影像组学标签显著提高预测性能,训练队列C指数0.81,验证队列0.78。
核心结论
- 研究开发并验证了一种基于[18F]PSMA-1007 PET的新型临床-影像组学模型,可预测前列腺癌患者根治性前列腺切除术后的BRFS。
- 作者认为该模型可能有助于识别BCR风险较高的患者,从而实现个性化风险分层和定制化管理策略。
研究设计与样本
- 回顾性分析236例经组织学确诊前列腺癌并接受根治性前列腺切除术的患者,所有患者术前均行[18F]PSMA-1007 PET/CT。
- 从PET图像原发肿瘤区域提取影像组学特征,采用LASSO Cox回归模型构建影像组学标签。
- 采用Harrell一致性指数(C-index)评估影像组学标签预测BRFS的性能,并利用影像组学标签与临床特征构建临床-影像组学列线图。
- 模型在98例独立队列中进行外部验证。
主要发现
- 影像组学标签由三个特征组成,训练队列C指数为0.76(95%CI 0.60-0.91),验证队列为0.71(95%CI 0.63-0.79)。
- 影像组学标签在多变量分析中仍是BRFS的独立预测因子(HR 2.48,95%CI 1.47-4.17,p<0.001)。
- 临床-影像组学列线图在训练队列中C指数为0.81(95%CI 0.66-0.95,p=0.007),在验证队列中C指数为0.78(95%CI 0.63-0.89,p<0.001),预测性能显著提高。
关键数值与推荐
- 影像组学标签训练队列C指数0.76(95%CI 0.60-0.91),验证队列C指数0.71(95%CI 0.63-0.79)。
- 影像组学标签多变量分析HR 2.48(95%CI 1.47-4.17,p<0.001)。
- 临床-影像组学列线图训练队列C指数0.81(95%CI 0.66-0.95,p=0.007),验证队列C指数0.78(95%CI 0.63-0.89,p<0.001)。
临床怎么用
- 作者认为该模型可能有助于识别BCR风险较高的患者,从而实现个性化风险分层和定制化管理策略。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: Biochemical recurrence (BCR) following radical prostatectomy (RP) is a significant concern for patients with prostate cancer. Reliable prediction models are needed to identify patients at risk for BCR and facilitate appropriate management. This study aimed to develop and validate a clinical-radiomics model based on preoperative [18 F]PSMA-1007 PET for predicting BCR-free survival (BRFS) in patients who underwent RP for prostate cancer. MATERIALS AND METHODS: A total of 236 patients with histologically confirmed prostate cancer who underwent RP were retrospectively analyzed. All patients had a preoperative [18 F]PSMA-1007 PET/CT scan. Radiomics features were extracted from the primary tumor region on PET images. A radiomics signature was developed using the least absolute shrinkage and selection operator (LASSO) Cox regression model. The performance of the radiomics signature in predicting BRFS was assessed using Harrell's concordance index (C-index). The clinical-radiomics nomogram was constructed using the radiomics signature and clinical features. The model was externally validated in an independent cohort of 98 patients. RESULTS: The radiomics signature comprised three features and demonstrated a C-index of 0.76 (95% CI: 0.60-0.91) in the training cohort and 0.71 (95% CI: 0.63-0.79) in the validation cohort. The radiomics signature remained an independent predictor of BRFS in multivariable analysis (HR: 2.48, 95% CI: 1.47-4.17, p < 0.001). The clinical-radiomics nomogram significantly improved the prediction performance (C-index: 0.81, 95% CI: 0.66-0.95, p = 0.007) in the training cohort and (C-index: 0.78 95% CI: 0.63-0.89, p < 0.001) in the validation cohort. CONCLUSION: We developed and validated a novel [18 F]PSMA-1007 PET-based clinical-radiomics model that can predict BRFS following RP in prostate cancer patients. This model may be useful in identifying patients with a higher risk of BCR, thus enabling personalized risk stratification and tailored management strategies.
引用
- Li T, Xu M, Yang S, et al. Development and validation of [18 F]-PSMA-1007 PET-based radiomics model to predict biochemical recurrence-free survival following radical prostatectomy. Eur J Nucl Med Mol Imaging. 2024. PMID: 38691111. doi:10.1007/s00259-024-06734-6
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。