用自适应连接提升脑肿瘤分割精度，效果显著且几乎不增加参数量。
Hyper-Connections for Adaptive Multi-Modal MRI Brain Tumor Segmentation
- 引入动态超连接替代固定残差连接，实现模态间自适应特征融合。
- 在BraTS 2021上平均Dice提升1.03%，增强肿瘤区域分割更精准。
- 适用于多种3D模型，尤其对临床关键序列敏感度更高，适合医学影像研究者。
我们首次将超连接（Hyper-Connections, HC）应用于三维多模态脑肿瘤分割，作为nnU-Net、SwinUNETR、VT-UNet、U-Net和U-Netpp五种架构的即插即用替代方案。在BraTS 2021数据集上，动态超连接一致提升了所有3D模型性能，最大平均Dice增益达+1.03%，参数开销可忽略不计。增益在增强肿瘤子区域最明显，表明边界划分能力显著改善。模态消融分析显示，配备超连接的模型对临床主导序列敏感度更高：T1ce对肿瘤核心与增强部分，FLAIR对全肿瘤，此特性在固定连接基线中缺失，且在所有架构中保持一致。二维设置下提升较小且依赖配置，说明体积空间上下文增强了自适应聚合的优势。结果确立了超连接作为简单、高效、通用的多模态特征融合机制。
原文摘要 · Abstract (English)
We present the first study of Hyper-Connections (HC) for volumetric multi-modal brain tumor segmentation, integrating them as a drop-in replacement for fixed residual connections across five architectures: nnU-Net, SwinUNETR, VT-UNet, U-Net, and U-Netpp. Dynamic HC consistently improves all 3D models on the BraTS 2021 dataset, yielding up to +1.03 percent mean Dice gain with negligible parameter overhead. Gains are most pronounced in the Enhancing Tumor sub-region, reflecting improved fine-grained boundary delineation. Modality ablation further reveals that HC-equipped models develop sharper sensitivity toward clinically dominant sequences, specifically T1ce for Tumor Core and Enhancing Tumor, and FLAIR for Whole Tumor, a behavior absent in fixed-connection baselines and consistent across all architectures. In 2D settings, improvements are smaller and configuration-sensitive, suggesting that volumetric spatial context amplifies the benefit of adaptive aggregation. These results establish HC as a simple, efficient, and broadly applicable mechanism for multi-modal feature fusion in medical image segmentation.
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。