轻量级脑肿瘤分割模型，参数减少98%仍保持高精度
Graph-Based Multi-Modal Light-weight Network for Adaptive Brain Tumor Segmentation
- 用图结构建模多模态互补关系，提升跨模态融合效率
- 仅458万参数，比主流3D Transformer少98%且性能领先
- 适合临床部署的低资源医学图像分割场景
多模态脑肿瘤分割因主流模型计算成本过高而难以实际应用。本文提出GMLN-BTS，一种基于图的多模态轻量级网络用于脑肿瘤分割。通过三个核心组件实现高精度、低资源分割：首先，模态感知自适应编码器（M2AE）实现高效多尺度语义提取；其次，基于图的多模态协同交互模块（G2MCIM）利用图结构建模跨模态互补关系；最后，体素细化上采样模块（VRUM）结合线性插值与多尺度转置卷积，抑制伪影并保留边界细节。在BraTS 2017、2019和2021基准上的实验表明，GMLN-BTS在轻量级模型中达到领先性能。仅需458万参数，相比主流3D Transformer减少98%参数量，同时显著优于现有紧凑方法。
原文摘要 · Abstract (English)
Multi-modal brain tumor segmentation remains challenging for practical deployment due to the high computational costs of mainstream models. In this work, we propose GMLN-BTS, a Graph-based Multi-modal interaction Lightweight Network for brain tumor segmentation. Our architecture achieves high-precision, resource-efficient segmentation through three key components. First, a Modality-Aware Adaptive Encoder (M2AE) facilitates efficient multi-scale semantic extraction. Second, a Graph-based Multi-Modal Collaborative Interaction Module (G2MCIM) leverages graph structures to model complementary cross-modal relationships. Finally, a Voxel Refinement UpSampling Module (VRUM) integrates linear interpolation with multi-scale transposed convolutions to suppress artifacts and preserve boundary details. Experimental results on BraTS 2017, 2019, and 2021 benchmarks demonstrate that GMLN-BTS achieves state-of-the-art performance among lightweight models. With only 4.58M parameters, our method reduces parameter count by 98% compared to mainstream 3D Transformers while significantly outperforming existing compact approaches.
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。