文献速递肿瘤 PET/CT核素与放射性配体治疗

基于PSMA PET/CT的多模态深度学习模型用于准确预测术前列线图判定为扩大盆腔淋巴结清扫候选者的前列腺癌患者盆腔淋巴结转移

PSMA PET/CT based multimodal deep learning model for accurate prediction of pelvic lymph-node metastases in prostate cancer patients identified as candidates for extended pelvic lymph node dissection by preoperative nomograms.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-01-27

本研究纳入116例接受根治性前列腺切除术联合扩大盆腔淋巴结清扫的前列腺癌患者(训练队列82例、测试队列34例),构建结合临床信息、SUVmax及PET/CT深度学习特征的多模态模型预测病理淋巴结侵犯。最终模型预测淋巴结侵犯的AUC为0.89(95%CI 0.81-0.97),在测试队列中优于PET/CT视觉评估、MSKCC列线图和Briganti-2017列线图。

要点

  • 多模态模型整合临床信息、SUVmax和PET/CT深度学习特征预测淋巴结侵犯。
  • 最终模型预测淋巴结侵犯的AUC为0.89(95%CI 0.81-0.97)。
  • 测试队列中模型AUC 0.85优于PET/CT视觉评估0.80、MSKCC 0.79和Briganti-2017 0.69。

核心结论

  • 结合术前PSMA PET/CT影像的多模态深度学习模型对临床局限性前列腺癌淋巴结侵犯的预测能力优于PSMA PET/CT视觉评估及MSKCC和Briganti-2017列线图。
  • 该模型有潜力减少不必要的扩大盆腔淋巴结清扫,同时降低遗漏淋巴结侵犯病例的风险。

研究设计与样本

  • 研究纳入116例符合条件的前列腺癌患者,均接受[68Ga]Ga-PSMA-617 PET/CT扫描及根治性前列腺切除术联合扩大盆腔淋巴结清扫,其中训练队列82例、测试队列34例。
  • 采用Med3D深度学习网络从PET/CT图像整个前列腺感兴趣体积中提取判别特征,并构建多核支持向量机多模态模型整合PET/CT深度学习特征、定量PET参数和临床参数。
  • 以最终组织病理学为参考标准,采用AUC、校准曲线、决策曲线分析评估模型性能,并与现有列线图及PET/CT视觉评估结果比较。

主要发现

  • 最终多模态模型纳入临床信息、最大标准化摄取值(SUVmax)和PET/CT深度学习特征。
  • 最终模型预测淋巴结侵犯的AUC为0.89(95%CI 0.81-0.97)。
  • 测试队列中,所提出模型AUC为0.85(95%CI 0.69-1.00),PET/CT视觉评估结果为0.80(95%CI 0.64-0.95),MSKCC列线图为0.79(95%CI 0.61-0.97),Briganti-2017列线图为0.69(95%CI 0.50-0.88)。
  • 与传统列线图相比,所提出模型显示相似的校准和更高的净获益。

关键数值与推荐

  • 最终模型预测淋巴结侵犯的AUC为0.89(95%CI 0.81-0.97)。
  • 测试队列中模型AUC 0.85(95%CI 0.69-1.00)vs PET/CT视觉评估0.80(95%CI 0.64-0.95)vs MSKCC列线图0.79(95%CI 0.61-0.97)vs Briganti-2017列线图0.69(95%CI 0.50-0.88)。

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: To develop and validate a prostate-specific membrane antigen (PSMA) PET/CT based multimodal deep learning model for predicting pathological lymph node invasion (LNI) in prostate cancer (PCa) patients identified as candidates for extended pelvic lymph node dissection (ePLND) by preoperative nomograms. METHODS: [68Ga]Ga-PSMA-617 PET/CT scan of 116 eligible PCa patients (82 in the training cohort and 34 in the test cohort) who underwent radical prostatectomy with ePLND were analyzed in our study. The Med3D deep learning network was utilized to extract discriminative features from the entire prostate volume of interest on the PET/CT images. Subsequently, a multimodal model i.e., Multi kernel Support Vector Machine was constructed to combine the PET/CT deep learning features, quantitative PET and clinical parameters. The performance of the multimodal models was assessed using final histopathology as the reference standard, with evaluation metrics including area under the receiver operating characteristic curve (AUC), calibration curve, decision curve analysis, and compared with available nomograms and PET/CT visual evaluation result. RESULTS: Our multimodal model incorporated clinical information, maximum standardized uptake value (SUVmax), and PET/CT deep learning features. The AUC for predicting LNI was 0.89 (95% confidence interval [CI] 0.81-0.97) for the final model. The proposed model demonstrated superior predictive accuracy in the test cohort compared to PET/CT visual evaluation result, the Memorial Sloan Kettering Cancer Center (MSKCC) and the Briganti-2017 nomograms (AUC 0.85 [95% CI 0.69-1.00] vs. 0.80 [95% CI 0.64-0.95] vs. 0.79 [95% CI 0.61-0.97] and 0.69 [95% CI 0.50-0.88], respectively). The proposed model showed similar calibration and higher net benefit as compared to the traditional nomograms. CONCLUSION: Our multimodal deep learning model, which incorporates preoperative PSMA PET/CT imaging, shows enhanced predictive capabilities for LNI in clinically localized PCa compared to PSMA PET/CT visual evaluation result and existing nomograms like the MSKCC and Briganti-2017 nomograms. This model has the potential to reduce unnecessary ePLND procedures while minimizing the risk of missing cases of LNI.

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

引用

  1. Ma Q, Chen B, Seifert R, et al. PSMA PET/CT based multimodal deep learning model for accurate prediction of pelvic lymph-node metastases in prostate cancer patients identified as candidates for extended pelvic lymph node dissection by preoperative nomograms. Eur J Nucl Med Mol Imaging. 2025. PMID: 39865180. doi:10.1007/s00259-024-07065-2

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。