一套统一模型，同时完成头颈癌肿瘤分割、分期和生存预测。
HERMES: A Hybrid Ensemble for Head-and-Neck Tumor Segmentation, TN Staging, and Recurrence-Free Survival on PET/CT
- 用10个小型网络集成做肿瘤和淋巴结分割，驱动后续任务。
- 通过几何特征提升分期准确率，平衡精度提高3个百分点。
- 融合深度学习与临床数据，适合放疗精准治疗场景使用。
我们提出HERMES（混合集成用于放疗靶区分割、恶性程度分期及无事件生存预测），一个基于配对FDG-PET/CT扫描和电子健康记录的单容器算法，解决HECKTOR 2026三项任务：原发肿瘤（GTVp）和病理淋巴结（GTVn）分割、影像学T/N分期及无复发生存（RFS）预测。采用10折小型STU-Net网络集成生成分割结果，其掩码用于下游任务。不使用通用放射组学特征，而是从分割结果提取与AJCC/UICC第7版影像学分期中大小和数量维度对齐的紧凑几何特征，使N期平衡准确率从0.691提升至0.720（+0.030），为最大单一改进，且特征维度更低。预后预测中，将互补的深度与临床风险专家以等权重集成，并训练一个自定义的协同追踪生存损失函数的深度专家，其值在训练中近似于一致性指数。所有组件均基于正交折叠预测选择，遵循正则化导向协议，未在公开验证集上调参，部署为两个去相关提交。在HECKTOR 2026验证排行榜上，HERMES取得加权得分0.6454（平均Dice 0.641，T期平衡准确率0.580，N期平衡准确率0.642，RFS一致性指数0.679），进入测试阶段。团队：AMC_HNC。
原文摘要 · Abstract (English)
We present HERMES (Hybrid Ensemble for Radiotherapy-target segmentation, Malignancy staging, and Event-free Survival), a single containerized algorithm for the three HECKTOR 2026 subtasks: segmentation of the primary tumor (GTVp) and pathological lymph nodes (GTVn), radiological T/N staging, and recurrence-free survival (RFS), computed from a paired FDG-PET/CT scan and an electronic health record. A 10-fold ensemble of STU-Net Small networks produces the segmentation; the predicted mask then drives two downstream tasks. Rather than pass a generic radiomics vector to the staging models, we derive from the predicted masks a compact set of geometry features aligned with the size and number axes of AJCC/UICC 7th-edition radiological N/T staging. On internal cross-validation these features raise N-stage balanced accuracy from 0.691 to 0.720 (+0.030), our largest single design gain, at lower feature dimensionality. For prognosis we combine complementary deep and clinical risk experts in an equal-weight ensemble, and train one deep expert with a concordance-tracking survival loss of our own, whose value approximates the concordance index during training. Every component was selected on honest out-of-fold predictions under a regularization-oriented protocol, with no tuning on the public validation set, and deployed as two decorrelated submissions. On the HECKTOR 2026 validation leaderboard, HERMES achieved a weighted score of 0.6454 (Mean Dice 0.641, T balanced accuracy 0.580, N balanced accuracy 0.642, RFS C-index 0.679) and qualified for the testing phase. Team: AMC_HNC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。