文献速递肿瘤 PET/CT核素与放射性配体治疗

可解释的18F-PSMA PET/CT-MRI融合模型优化前列腺穿刺决策

An interpretable 1⁸F-PSMA PET/CT-MRI model for optimizing prostate biopsy decisions.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2026-05-23

该多中心回顾性研究基于302例穿刺初治男性,整合18F-PSMA PET/CT、mpMRI影像组学与临床变量构建融合模型预测临床显著前列腺癌(csPCa)。融合模型在内外部验证队列AUC均为0.92,PI-RADS 3亚组AUC达0.97;风险分层可避免三个队列中82.9%、75.0%、72.2%的不必要穿刺,漏诊率分别为4.0%、9.5%、6.1%。

要点

  • 融合模型内外部验证AUC均为0.92,优于临床及单模态模型。
  • PI-RADS 3亚组AUC 0.97,灵敏度95.0%、特异度86.5%。
  • 风险分层可避免多数不必要穿刺,漏诊率维持在较低水平。

核心结论

  • 整合18F-PSMA PET/CT与mpMRI的可解释融合模型对csPCa诊断性能优于标准临床评估。
  • 该模型有望作为无创分诊工具辅助穿刺决策,在维持肿瘤学安全的同时减少不必要穿刺。

研究设计与样本

  • 多中心回顾性研究,分析来自前瞻性多中心队列的302例穿刺初治患者。
  • 从18F-PSMA PET与mpMRI提取影像组学特征,采用病灶与全腺体双层次ROI策略。
  • 影像组学签名取自四种机器学习筛选算法交集,临床特征经逻辑回归筛选,训练八种机器学习模型并采用十折交叉验证。

主要发现

  • 融合模型内部验证AUC为0.92(95%CI:0.85-0.97),外部验证AUC为0.92(95%CI:0.83-0.99)。
  • PI-RADS 3亚组融合模型AUC为0.97,灵敏度95.0%,特异度86.5%。
  • 风险分层在三个队列中分别可避免82.9%、75.0%、72.2%的不必要穿刺,漏诊率分别为4.0%、9.5%、6.1%。
  • SHAP分析显示PET来源的强度与纹理特征为主要预测因子,体现18F-PSMA PET的附加价值。

关键数值与推荐

  • 以AUC、决策曲线分析(DCA)和临床影响曲线(CIC)比较融合模型与临床及单模态模型。

临床怎么用

  • 对穿刺初治男性,可结合18F-PSMA PET/CT与mpMRI的融合模型评估csPCa风险。
  • 依据模型风险分层辅助筛选可安全免于穿刺的患者,降低不必要穿刺。

局限性

  • 为回顾性研究设计。
  • 样本量为302例,来源于单一前瞻性多中心队列。

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: Distinguishing indolent from clinically significant prostate cancer (csPCa) in biopsy-naïve men remains a diagnostic challenge, often leading to unnecessary biopsies. This study aimed to develop and externally validate an interpretable multimodal model integrating 18F-PSMA PET/CT, mpMRI, and clinical variables to predict csPCa and optimize biopsy decision-making. METHODS: This multicenter retrospective study analyzed 302 biopsy-naïve patients derived from a prospective multicenter cohort. Radiomic features were extracted from 18F-PSMA PET and mpMRI. A dual-level region-of-interest (ROI) strategy was used to capture lesion and whole-gland features. To prevent overfitting, the optimal radiomics signature was derived from the intersection of four machine learning (ML) selection algorithms, while clinical features were selected via logistic regression. Eight ML models were trained and tested with ten-fold cross-validation. A Fusion model, combining radiomics and clinical variables, was evaluated against clinical and single-modality models using AUC, decision curve analysis (DCA), and clinical impact curves (CIC). Additionally, SHapley Additive exPlanations (SHAP) values elucidated feature contributions. RESULTS: The Fusion model demonstrated robust diagnostic efficacy, achieving AUCs of 0.92 in both the internal (95% CI: 0.85-0.97) and external (95% CI: 0.83-0.99) validation cohorts. In the PI-RADS 3 subgroup, the model outperformed standard clinical assessments, yielding an excellent AUC of 0.97 (sensitivity 95.0%, specificity 86.5%). Clinically, risk stratification utilizing the Fusion model could avoid 82.9%, 75.0%, and 72.2% of unnecessary biopsies across the three cohorts, while maintaining low missed-diagnosis rates of 4.0%, 9.5%, and 6.1%, respectively. Furthermore, SHAP analysis identified PET-derived intensity and textural features as the dominant predictors, underscoring the indispensable added value of 18F-PSMA PET. CONCLUSION: This interpretable Fusion model integrating 18F-PSMA PET/CT and mpMRI demonstrated superior diagnostic performance for csPCa compared to standard clinical assessment. This approach shows potential as an effective non-invasive triage tool to support biopsy decision-making, with the potential to reduce unnecessary biopsies while maintaining oncological safety.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Xiong S, Ma J, Li H, et al. An interpretable 1⁸F-PSMA PET/CT-MRI model for optimizing prostate biopsy decisions. Eur J Nucl Med Mol Imaging. 2026. PMID: 42176196. doi:10.1007/s00259-026-07947-7

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。