脑转移瘤分割：BraTS 2026 任务 1 的多架构比较
Brain Metastases Segmentation for BraTS 2026 Task 1: A Multi-Architecture Comparison
- Independent University, Bangladesh（孟加拉国独立大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究比较多种分割架构处理脑转移瘤，Primus模型在DSC/NSD上最优，ResEncL在病灶级F1上更佳，集成可部分结合优势。
AI中文摘要：
脑转移瘤是最常见的颅内恶性肿瘤，约30%的原发性实体瘤患者会发生脑转移，其中位生存期接近5.9个月。自动化分割对于治疗计划和体积监测至关重要，但转移瘤通常体积小、数量多，且在同一患者体内大小异质。我们比较了普通nnU-Net基线、残差编码器大型（ResEncL）变体、基于区域的训练以及Primus transformer模型在BraTS-METS 2026任务1上的表现，采用患者分组交叉验证以防止来自纵向UCSD子集的数据泄漏。Primus（基于标签）是我们最强的个体模型，按聚合DSC/NSD衡量，达到ET：0.710/0.761，TC：0.742/0.785，WT：0.683/0.689，RC：0.531/0.436。ResEncL在聚合DSC/NSD上落后于Primus，但在病灶级F1上显著更高（例如ET：0.452对比0.052）；两者的概率平均集成仅部分保留了ResEncL的F1优势（ET病灶级F1：0.064）。我们进一步报告了我们认为超越本次挑战具有普适性的三个后处理和标签重建陷阱。代码可在该https URL获取。
英文摘要：
Brain metastases are the most common intracranial malignancy, occurring in roughly 30% of patients with primary solid tumors and carrying a median survival near 5.9 months. Automated segmentation is critical for treatment planning and volumetric monitoring, but metastases are frequently small, numerous, and heterogeneous in size within a single patient. We compare a plain nnU-Net baseline, a Residual Encoder Large (ResEncL) variant, region-based training, and a Primus transformer model for BraTS-METS 2026 Task 1, using patient-grouped cross-validation to prevent leakage from the longitudinal UCSD subset. Primus (label-based) is our strongest individual model by aggregate DSC/NSD, achieving 0.710/0.761 (ET), 0.742/0.785 (TC), 0.683/0.689 (WT), and 0.531/0.436 (RC). ResEncL trails Primus on aggregate DSC/NSD but achieves substantially higher lesion-wise F1 (e.g. ET: 0.452 vs. 0.052); a probability-averaging ensemble of the two only partially preserves ResEncL's F1 advantage (ET lesion-wise F1: 0.064). We further report three postprocessing and label-reconstruction pitfalls we believe generalize beyond this challenge. Code is available at https://github.com/mahdiislam79/BraTS_METS_2026.
