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.

中文翻译：

---

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

 目的

结外自然杀伤/T 细胞淋巴瘤 （ENKTCL） 是一种具有预后异质性的血液系统恶性肿瘤。我们旨在开发和验证 DeepENKTCL，这是一种用于 ENKTCL 预后风险分层的可解释深度学习预测系统。

 方法

来自 4 个中心的 562 名患者被分为训练队列、验证队列和测试队列。DeepENKTCL 结合了肿瘤分割模型、 PET/CT 融合模型和预后预测模型。RadScore 和 TopoScore 是使用来自融合图像的放射组学和拓扑特征构建的，SHapley 加法解释 （SHAP） 分析增强了可解释性。最终的预后模型称为 FusionScore，用于预测无进展生存期 （PFS） 和总生存期 （OS）。使用受试者操作员特征曲线下面积 （AUC） 、时间依赖性 C 指数、临床决策曲线 （DCA） 和 Kaplan-Meier （KM） 曲线评估性能。

 结果

肿瘤分割模型准确描绘了肿瘤病灶。RadScore（AUC：PFS 为 0.908，验证 OS 为 0.922;PFS 为 0.822，受试 OS 为 0.867）和 TopoScore（AUC：PFS 为 0.756，验证 OS 为 0.805;PFS 为 0.689，受试 OS 为 0.769）均表现出潜在的预后能力。时间依赖性 C 指数 （PFS 为 0.897，验证 OS 为 0.928;PFS 为 0.894，测试中 OS 为 0.868）和 DCA 表明，与现有模型相比，FusionScore 提供了显著的预后性能和卓越的净临床获益。KM 生存分析显示，在所有队列中，较高的 FusionScores 与较差的 PFS 和 OS 相关。

 结论

DeepENKTCL 为 ENKTCL 预后提供了一个稳健且可解释的框架，有可能改善患者预后并指导个性化治疗。