HERMES：用于PET/CT图像上头颈部肿瘤分割、TN分期及无复发生存分析的混合集成模型
HERMES: A Hybrid Ensemble for Head-and-Neck Tumor Segmentation, TN Staging, and Recurrence-Free Survival on PET/CT
浏览论文内容
中文总结 AI 辅助
该研究提出名为HERMES的混合集成算法，用于解决HECKTOR 2026的肿瘤分割、TN分期及无复发生存分析任务，在验证排行榜取得加权分0.6454并晋级测试阶段。
中文摘要 AI 辅助
我们提出HERMES（Hybrid Ensemble for Radiotherapy-target segmentation, Malignancy staging, and Event-free Survival），这是一个单一容器化算法，用于解决HECKTOR 2026的三个子任务：从配对的FDG-PET/CT扫描和电子健康记录中分割原发肿瘤（GTVp）和病理淋巴结（GTVn）、进行放射学T/N分期，以及预测无复发生存（RFS）。采用STU-Net Small网络的10折集成模型生成分割结果，预测的掩码随后驱动两个下游任务。与将通用放射组学向量输入分期模型的做法不同，我们从预测的掩码中提取了一组紧凑的几何特征，这些特征与AJCC/UICC第7版放射学N/T分期的大小和数量轴对齐。在内部交叉验证中，这些特征使N分期的平衡准确率从0.691提升至0.720（+0.030），这是我们最大的单一设计增益，且特征维度更低。对于预后任务，我们采用等权重集成方式结合互补的深度风险专家和临床风险专家，并使用我们自行提出的一致性跟踪生存损失训练其中一个深度专家，该损失值在训练期间近似于一致性指数。所有组件均在面向正则化的协议下基于诚实的折外预测进行选择，未在公共验证集上进行调参，并作为两个去相关的提交部署。在HECKTOR 2026验证排行榜上，HERMES取得了0.6454的加权分数（平均Dice系数0.641、T分期平衡准确率0.580、N分期平衡准确率0.642、RFS一致性指数0.679），并获得了测试阶段的参赛资格。团队：AMC_HNC。
英文摘要
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.
发表机构
- University of Colorado School of Medicine（科罗拉多大学医学院）
机构由 AI 辅助整理，请以论文原文为准。
