针对儿童脑瘤分割难题，改进nnU-Net模型实现高精度分割。
Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements
- 采用注意力机制与深度可分离卷积提升特征提取能力
- 在公开数据集上达0.967（活动病灶）等六项指标领先
- 适合医学影像分析、儿科肿瘤研究者参考
多参数磁共振成像（mpMRI）中精准分割儿童脑瘤对诊断、治疗规划和监测至关重要，但受限于数据少、解剖变异大及机构间成像差异，面临挑战。本文针对BraTS 2025 Task-6（PED）——目前最大的术前儿童高级别胶质瘤公开数据集，提出增强版nnU-Net框架。创新包括：(1) 带有挤压-激励（SE）注意力的加宽残差编码器；(2) 3D深度可分离卷积；(3) 特异性驱动正则化项；(4) 小尺度高斯权重初始化。结合两阶段后处理，模型在任务验证排行榜中排名第一，获得病灶级Dice分数：CC为0.759，ED为0.967，ET为0.826，NET为0.910，TC为0.928，WT为0.928。
原文摘要 · Abstract (English)
Accurate segmentation of pediatric brain tumors in multi-parametric magnetic resonance imaging (mpMRI) is critical for diagnosis, treatment planning, and monitoring, yet faces unique challenges due to limited data, high anatomical variability, and heterogeneous imaging across institutions. In this work, we present an advanced nnU-Net framework tailored for BraTS 2025 Task-6 (PED), the largest public dataset of pre-treatment pediatric high-grade gliomas. Our contributions include: (1) a widened residual encoder with squeeze-and-excitation (SE) attention; (2) 3D depthwise separable convolutions; (3) a specificity-driven regularization term; and (4) small-scale Gaussian weight initialization. We further refine predictions with two postprocessing steps. Our models achieved first place on the Task-6 validation leaderboard, attaining lesion-wise Dice scores of 0.759 (CC), 0.967 (ED), 0.826 (ET), 0.910 (NET), 0.928 (TC) and 0.928 (WT).
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。