改进nnU-Net的脑肿瘤分割模型，提升特征提取与多尺度感知能力。
Multiscale Encoder and Omni-Dimensional Dynamic Convolution Enrichment in nnU-Net for Brain Tumor Segmentation
- 用全维动态卷积替代传统卷积，增强特征表达能力
- 引入多尺度注意力机制，融合不同层级视觉信息
- 在BraTS-Africa数据集上表现优异，适合医学图像分割研究者
脑肿瘤分割在计算机辅助诊断中至关重要。本研究提出一种基于改进nnU-Net架构的新分割算法。在nnU-Net编码器部分，通过引入全维动态卷积（ODConv）层替代传统卷积层，显著提升了特征表示能力；同时提出一种多尺度注意力策略，有效整合来自不同尺度的现代视觉洞察。该模型在BraTS-2023挑战赛的多个数据集上验证了有效性。结合ODConv层与多尺度特征的改进方案，在多个脑肿瘤分割数据集上均带来显著性能提升。尤其值得注意的是，该模型在BraTS Africa数据集的验证阶段展现出良好准确率。相关ODConv源码及完整训练代码已开源至GitHub。
原文摘要 · Abstract (English)
Brain tumor segmentation plays a crucial role in computer-aided diagnosis. This study introduces a novel segmentation algorithm utilizing a modified nnU-Net architecture. Within the nnU-Net architecture's encoder section, we enhance conventional convolution layers by incorporating omni-dimensional dynamic convolution layers, resulting in improved feature representation. Simultaneously, we propose a multi-scale attention strategy that harnesses contemporary insights from various scales. Our model's efficacy is demonstrated on diverse datasets from the BraTS-2023 challenge. Integrating omni-dimensional dynamic convolution (ODConv) layers and multi-scale features yields substantial improvement in the nnU-Net architecture's performance across multiple tumor segmentation datasets. Remarkably, our proposed model attains good accuracy during validation for the BraTS Africa dataset. The ODconv source code along with full training code is available on GitHub.
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。