文献速递肿瘤 PET/CT

用于结外自然杀伤/T细胞淋巴瘤预后分层的稳健且可解释的深度学习系统

Robust and interpretable deep learning system for prognostic stratification of extranodal natural killer/T-cell lymphoma.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2024-12-23

研究纳入四个中心共562例结外自然杀伤/T细胞淋巴瘤(ENKTCL)患者,构建并验证可解释深度学习系统DeepENKTCL进行预后风险分层。该系统整合肿瘤分割模型、PET/CT融合模型和预后预测模型,构建RadScore与TopoScore并以SHAP分析增强可解释性,最终形成预测无进展生存(PFS)和总生存(OS)的FusionScore。FusionScore显示出显著的预后性能,较高FusionScore与较差PFS和OS相关。

要点

  • DeepENKTCL整合肿瘤分割、PET/CT融合与预后预测模型,用于ENKTCL预后风险分层。
  • 验证队列中RadScore预测PFS的AUC为0.908、预测OS的AUC为0.922;测试队列分别为0.822和0.867。
  • FusionScore的 time-dependent C-index 在验证队列PFS为0.897、OS为0.928,测试队列PFS为0.894、OS为0.868。

核心结论

  • DeepENKTCL为ENKTCL预后提供了稳健且可解释的框架,有潜力改善患者结局并指导个体化治疗。

研究设计与样本

  • 来自四个中心的562例患者被分为训练队列、验证队列和测试队列。
  • DeepENKTCL整合了肿瘤分割模型、PET/CT融合模型和预后预测模型。
  • RadScore与TopoScore基于融合图像的影像组学和拓扑特征构建,并以SHAP分析增强可解释性。
  • 最终预后模型FusionScore用于预测无进展生存(PFS)和总生存(OS)。
  • 性能评估采用AUC、time-dependent C-index、临床决策曲线(DCA)和Kaplan-Meier(KM)曲线。

主要发现

  • 肿瘤分割模型能准确勾画肿瘤病灶。
  • RadScore在验证队列预测PFS的AUC为0.908、预测OS的AUC为0.922,在测试队列预测PFS的AUC为0.822、预测OS的AUC为0.867。
  • TopoScore在验证队列预测PFS的AUC为0.756、预测OS的AUC为0.805,在测试队列预测PFS的AUC为0.689、预测OS的AUC为0.769。
  • FusionScore的time-dependent C-index在验证队列PFS为0.897、OS为0.928,在测试队列PFS为0.894、OS为0.868。
  • DCA提示FusionScore较现有模型提供显著的预后性能和更优的净临床获益。

关键数值与推荐

  • RadScore预测PFS的AUC:验证队列0.908,测试队列0.822。
  • RadScore预测OS的AUC:验证队列0.922,测试队列0.867。
  • TopoScore预测PFS的AUC:验证队列0.756,测试队列0.689。
  • TopoScore预测OS的AUC:验证队列0.805,测试队列0.769。
  • FusionScore的time-dependent C-index:验证队列PFS 0.897、OS 0.928;测试队列PFS 0.894、OS 0.868。

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: Extranodal natural killer/T-cell lymphoma (ENKTCL) is an hematologic malignancy with prognostic heterogeneity. We aimed to develop and validate DeepENKTCL, an interpretable deep learning prediction system for prognosis risk stratification in ENKTCL. METHODS: A total of 562 patients from four centers were divided into the training cohort, validation cohort and test cohort. DeepENKTCL combined a tumor segmentation model, a PET/CT fusion model, and prognostic prediction models. RadScore and TopoScore were constructed using radiomics and topological features derived from fused images, with SHapley Additive exPlanations (SHAP) analysis enhancing interpretability. The final prognostic models, termed FusionScore, were developed for predicting progression-free survival (PFS) and overall survival (OS). Performance was assessed using area under the receiver operator characteristic curve (AUC), time-dependent C-index, clinical decision curves (DCA), and Kaplan-Meier (KM) curves. RESULTS: The tumor segmentation model accurately delineated the tumor lesions. RadScore (AUC: 0.908 for PFS, 0.922 for OS in validation; 0.822 for PFS, 0.867 for OS in test) and TopoScore (AUC: 0.756 for PFS, 0.805 for OS in validation; 0.689 for PFS, 0.769 for OS in test) both exhibited potential prognostic capability. The time-dependent C-index (0.897 for PFS, 0.928 for OS in validation; 0.894 for PFS, 0.868 for OS in test) and DCA indicated that FusionScore offers significant prognostic performance and superior net clinical benefits compared to existing models. KM survival analysis showed that higher FusionScores correlated with poorer PFS and OS across all cohorts. CONCLUSION: DeepENKTCL provided a robust and interpretable framework for ENKTCL prognosis, with the potential to improve patient outcomes and guide personalized treatment.

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

引用

  1. Jiang C, Jiang Z, Zhang X, et al. Robust and interpretable deep learning system for prognostic stratification of extranodal natural killer/T-cell lymphoma. Eur J Nucl Med Mol Imaging. 2024. PMID: 39714634. doi:10.1007/s00259-024-07024-x

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。