通过频域分解与模型融合，提升儿科脑肿瘤分割精度。
Frequency-Aware Ensemble Learning for BraTS 2025 Pediatric Brain Tumor Segmentation
- 三模型集成：nnU-Net、Swin UNETR、HFF-Net，各具优化策略。
- 在未见测试集上，总体分割准确率达92.6%（WT），排名首位。
- 适合医学影像分割研究者，尤其关注儿科罕见病建模。
儿科脑肿瘤分割因肿瘤稀有性和异质性而面临挑战，但对临床诊断与治疗规划至关重要。本文针对BraTS-PED 2025挑战提出一种集成方法，融合nnU-Net、Swin UNETR与HFF-Net。关键改进包括：调整nnU-Net的初始化尺度以控制复杂度；利用BraTS 2021预训练模型进行迁移学习，增强Swin UNETR在儿科数据上的泛化能力；在HFF-Net中引入频域分解，分离低频组织轮廓与高频纹理细节。最终集成框架结合nnU-Net（γ=0.7）、微调后的Swin UNETR与HFF-Net，于未见测试集上取得Dice分数：62.7%（CC）、83.2%（ED）、72.9%（ET）、85.7%（NET）、91.8%（TC）和92.6%（WT）。该方法在BraTS 2025儿科脑肿瘤分割挑战赛中排名第一。
原文摘要 · Abstract (English)
Pediatric brain tumor segmentation presents unique challenges due to the rarity and heterogeneity of these malignancies, yet remains critical for clinical diagnosis and treatment planning. We propose an ensemble approach integrating nnU-Net, Swin UNETR, and HFF-Net for the BraTS-PED 2025 challenge. Our method incorporates three key extensions: adjustable initialization scales for optimal nnU-Net complexity control, transfer learning from BraTS 2021 pre-trained models to enhance Swin UNETR's generalization on pediatric dataset, and frequency domain decomposition for HFF-Net to separate low-frequency tissue contours from high-frequency texture details. Our final ensemble framework combines nnU-Net ($γ=0.7$), fine-tuned Swin UNETR, and HFF-Net, achieving Dice scores of 62.7% (CC), 83.2% (ED), 72.9% (ET), 85.7% (NET), 91.8% (TC), and 92.6% (WT) on the unseen test dataset, respectively. Our proposed method achieves first place (rank 1st) in the BraTS 2025 Pediatric Brain Tumor Segmentation Challenge.
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。