文献速递前列腺癌

深度学习算法基于[18F]PSMA-1007 PET/CT与多参数MRI辅助诊断前列腺癌包膜外侵犯:多中心研究

Deep learning algorithm assisting diagnosis of prostate cancer extracapsular extension based on [18F]PSMA-1007 PET/CT and multiparametric MRI: A multicenter study.
PubMed 文献 · Prostate Cancer Prostatic Dis · 2025-12-08

本研究开发并验证基于多参数MRI和[18F]PSMA-1007 PET/CT的深度学习模型预测前列腺癌包膜外侵犯(ECE),并构建整合深度学习与人工模型的简易模型。共纳入388例根治性前列腺切除术患者,MPC-M模型在内外部验证中AUC分别为0.907和0.849,简易模型E-MPC-M的AUC分别为0.862和0.775。结论认为MPC-M模型预测性能强,E-MPC-M保留较多性能且临床实用性增强,但需更大前瞻性多中心研究验证。

要点

  • MPC-M模型预测ECE的内部AUC为0.907,外部为0.849。
  • 简易模型E-MPC-M内部AUC为0.862,外部为0.775。
  • Grad-CAM显示模型关注肿瘤相关区域,学习有效。

核心结论

  • MPC-M模型在内外部队列中对前列腺癌ECE表现出强预测性能,E-MPC-M模型保留较多性能且临床实用性更佳。
  • 模型应视为初步结果,需更大前瞻性多中心研究确认稳健性和泛化性。

研究设计与样本

  • 多中心研究,纳入388例接受根治性前列腺切除术的患者,来自中心A、B和C。
  • 开发了基于mpMRI、PET/CT及联合的MPC三种深度学习模型,并与基于ECE分级系统的人工模型比较。
  • 构建整合深度学习与人工模型的mpMRI-M、PET/CT-M和MPC-M三种联合模型,并开发简易模型E-MPC-M。
  • 使用AUC和混淆矩阵指标评估性能,采用Grad-CAM可视化模型可解释性。

主要发现

  • 内部队列中,人工模型、MPC和MPC-M的AUC分别为0.752、0.897和0.907;敏感度分别为0.616、0.896和0.915;特异度分别为0.791、0.740和0.802。
  • 外部验证队列中,上述模型AUC分别为0.665、0.824和0.849;敏感度分别为0.318、0.955和0.955;特异度分别为0.960、0.600和0.640。
  • E-MPC-M模型内部队列AUC为0.862,外部队列AUC为0.775。
  • Grad-CAM可视化显示模型关注肿瘤相关区域,确认有效学习肿瘤特征。

临床怎么用

  • MPC-M模型可用于辅助预测前列腺癌包膜外侵犯,E-MPC-M模型在保持一定性能的同时提升临床易用性。
  • 模型输出应结合临床判断,目前视为初步工具,需进一步验证后用于临床决策。

局限性

  • 模型为初步结果,需更大前瞻性多中心研究确认稳健性和泛化性。

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

BACKGROUND: This study aimed to develop and validate deep learning (DL) models based on multiparametric MRI (mpMRI) and [18F]PSMA-1007 PET/CT to predict extracapsular extension (ECE) in prostate cancer (PCa), and to explore easy models integrating DL with clinical expertise. METHODS: A total of 388 patients who underwent radical prostatectomy were enrolled from centers A, B and C. Three DL models based on mpMRI, PET/CT, and a combined MPC model were developed and compared with a manual model based on the ECE grading system. Additionally, three combined models (mpMRI-M, PET/CT-M, and MPC-M) were constructed by integrating the DL models with the Manual model. To enhance clinical applicability, an easy model (E-MPC-M) was developed. Model performance was evaluated using the area under the receiver-operating-characteristic curve (AUC) and metrics derived from the confusion matrix. Gradient-weighted class-activation-mapping (Grad-CAM) was employed to visualize model interpretability. RESULTS: In the internal cohort, the Manual, MPC, and MPC-M models achieved AUCs of 0.752, 0.897, and 0.907, respectively; corresponding sensitivities were 0.616, 0.896, and 0.915, and specificities were 0.791, 0.740, and 0.802. In the external validation cohort, these models achieved AUCs of 0.665, 0.824, and 0.849; sensitivities of 0.318, 0.955, and 0.955; and specificities of 0.960, 0.600, and 0.640, respectively. The E-MPC-M model also showed robust performance, with an AUC of 0.862 in the internal cohort and 0.775 in the external cohort. Grad-CAM visualizations highlighted the model's focus on tumor-relevant regions, confirming effective learning of tumor features. CONCLUSIONS: The MPC-M model demonstrated strong predictive performance for PCa ECE across internal and external cohorts, while the E-MPC-M model retained much of this performance with enhanced clinical practicality. However, these models should be considered as preliminary, and larger prospective multicenter studies are required to confirm their robustness and generalizability.

来源:Prostate Cancer Prostatic Dis,查看原文。版权归原作者所有。

引用

  1. Yao F, Zhu D, Lin H, et al. Deep learning algorithm assisting diagnosis of prostate cancer extracapsular extension based on [18F]PSMA-1007 PET/CT and multiparametric MRI: A multicenter study. Prostate Cancer Prostatic Dis. 2025. PMID: 41361534. doi:10.1038/s41391-025-01063-7

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。