文献速递肿瘤 PET/CT

基于[18F]PSMA-1007 PET/CT与多参数MRI的多模态深度学习预测前列腺癌不良病理

Prediction of adverse pathology in prostate cancer using a multimodal deep learning approach based on [18F]PSMA-1007 PET/CT and multiparametric MRI.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-02-19

回顾性分析341例接受根治性前列腺切除术且术前行mpMRI与[18F]PSMA-1007 PET/CT的前列腺癌患者,构建基于卷积神经网络与Transformer的多模态深度学习模型(MPC)并联合临床特征形成整合模型(MPCC)。MPCC预测不良病理的AUC为0.955(95%CI 0.932-0.975),高于MPC的0.930(95%CI 0.901-0.955),MPC优于单PET/CT(AUC 0.813)或单mpMRI(AUC 0.865)。

要点

  • MPCC预测不良病理AUC 0.955(95%CI 0.932-0.975),高于MPC的0.930(95%CI 0.901-0.955)。
  • MPC预测不良病理优于单PET/CT(AUC 0.813,95%CI 0.780-0.845)或单mpMRI(AUC 0.865,95%CI 0.829-0.901)。
  • MPCC对单一不良病理特征同样具有预测效能。

核心结论

  • 整合mpMRI与[18F]PSMA-1007 PET/CT的深度学习模型提升了预测前列腺癌患者不良病理存在的能力,有助于医生做出术前决策并最终改善患者预后。

研究设计与样本

  • 回顾性分析341例接受根治性前列腺切除术且术前行mpMRI与PET/CT扫描的前列腺癌患者。
  • 基于卷积神经网络与Transformer构建多模态深度学习模型(MPC)生成mpMRI与PET/CT的深度学习签名,并联合临床特征构建整合模型(MPCC)。
  • 将MPC与MPCC同临床模型及单mpMRI或单PET/CT模型进行比较。

主要发现

  • MPCC预测不良病理的AUC为0.955(95%CI 0.932-0.975),高于MPC的AUC 0.930(95%CI 0.901-0.955)。
  • MPC预测不良病理的AUC为0.930(95%CI 0.901-0.955),优于单PET/CT的AUC 0.813(95%CI 0.780-0.845)和单mpMRI的AUC 0.865(95%CI 0.829-0.901)。
  • MPCC对单一不良病理特征同样具有预测效能。

关键数值与推荐

  • MPCC预测不良病理AUC 0.955(95%CI 0.932-0.975)。
  • MPC预测不良病理AUC 0.930(95%CI 0.901-0.955)。
  • 单PET/CT模型预测不良病理AUC 0.813(95%CI 0.780-0.845)。
  • 单mpMRI模型预测不良病理AUC 0.865(95%CI 0.829-0.901)。

临床怎么用

  • 原文未据此给出推荐。

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: Accurate prediction of adverse pathology (AP) in prostate cancer (PCa) patients is crucial for formulating effective treatment strategies. This study aims to develop and evaluate a multimodal deep learning model based on [18F]PSMA-1007 PET/CT and multiparametric MRI (mpMRI) to predict the presence of AP, and investigate whether the model that integrates [18F]PSMA-1007 PET/CT and mpMRI outperforms the individual PET/CT or mpMRI models in predicting AP. METHODS: 341 PCa patients who underwent radical prostatectomy (RP) with mpMRI and PET/CT scans were retrospectively analyzed. We generated deep learning signature from mpMRI and PET/CT with a multimodal deep learning model (MPC) based on convolutional neural networks and transformer, which was subsequently incorporated with clinical characteristics to construct an integrated model (MPCC). These models were compared with clinical models and single mpMRI or PET/CT models. RESULTS: The MPCC model showed the best performance in predicting AP (AUC, 0.955 [95% CI: 0.932-0.975]), which is higher than MPC model (AUC, 0.930 [95% CI: 0.901-0.955]). The performance of the MPC model is better than that of single PET/CT (AUC, 0.813 [95% CI: 0.780-0.845]) or mpMRI (AUC, 0.865 [95% CI: 0.829-0.901]). Additionally, MPCC model is also effective in predicting single adverse pathological features. CONCLUSION: The deep learning model that integrates mpMRI and [18F]PSMA-1007 PET/CT enhances the predictive capabilities for the presence of AP in PCa patients. This improvement aids physicians in making informed preoperative decisions, ultimately enhancing patient prognosis.

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

引用

  1. Lin H, Yao F, Yi X, et al. Prediction of adverse pathology in prostate cancer using a multimodal deep learning approach based on [18F]PSMA-1007 PET/CT and multiparametric MRI. Eur J Nucl Med Mol Imaging. 2025. PMID: 39969539. doi:10.1007/s00259-025-07134-0

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。