用剪枝图注意力模型，实现快速精准脑肿瘤分割
EfficientGFormer: Multimodal Brain Tumor Segmentation via Pruned Graph-Augmented Transformer
- 构建双边图结构，融合空间与语义关系进行推理
- 在MSD和BraTS数据集上精度领先，内存占用减少40%
- 适合临床实时应用，兼顾效率与可解释性
准确且高效的脑肿瘤分割在神经影像中仍具挑战，源于肿瘤亚区异质性及体积分割的高计算成本。本文提出EfficientGFormer，一种融合预训练基础模型、图式推理与轻量效率机制的新型3D脑肿瘤分割架构。该框架采用nnFormer作为模态感知编码器，将多模态MRI体积转换为片段级嵌入，并将其组织成包含空间邻接与语义相似性的双边图。通过剪枝的、边类型感知的图注意力网络（GAT）实现对肿瘤亚区间的高效关系推理，同时引入知识蒸馏模块，将全容量教师模型的知识迁移至紧凑的学生模型，以支持实时部署。在MSD Task01和BraTS 2021数据集上的实验表明，EfficientGFormer在保持显著降低的内存占用和推理时间的同时，达到当前最优精度，优于近期基于Transformer与图的方法。本工作为快速、精准的体积分割提供了具备可扩展性、可解释性与泛化能力的临床可行方案。
原文摘要 · Abstract (English)
Accurate and efficient brain tumor segmentation remains a critical challenge in neuroimaging due to the heterogeneous nature of tumor subregions and the high computational cost of volumetric inference. In this paper, we propose EfficientGFormer, a novel architecture that integrates pretrained foundation models with graph-based reasoning and lightweight efficiency mechanisms for robust 3D brain tumor segmentation. Our framework leverages nnFormer as a modality-aware encoder, transforming multi-modal MRI volumes into patch-level embeddings. These features are structured into a dual-edge graph that captures both spatial adjacency and semantic similarity. A pruned, edge-type-aware Graph Attention Network (GAT) enables efficient relational reasoning across tumor subregions, while a distillation module transfers knowledge from a full-capacity teacher to a compact student model for real-time deployment. Experiments on the MSD Task01 and BraTS 2021 datasets demonstrate that EfficientGFormer achieves state-of-the-art accuracy with significantly reduced memory and inference time, outperforming recent transformer-based and graph-based baselines. This work offers a clinically viable solution for fast and accurate volumetric tumor delineation, combining scalability, interpretability, and generalization.
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。