arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16320eess.IVcs.CVcs.LG
收藏

RefineFormer3D:通过自适应多尺度Transformer与交叉注意力融合实现高效的3D医学图像分割

RefineFormer3D: Efficient 3D Medical Image Segmentation via Adaptive Multi-Scale Transformer with Cross Attention Fusion

National Institute of Technology Kurukshetra(库鲁克谢特拉国家技术学院);Indian Institute of Technology Ropar(罗帕尔印度理工学院)

Kavyansh Tyagi, Vishwas Rathi, Puneet Goyal

AI总结:

RefineFormer3D通过自适应多尺度Transformer与交叉注意力融合,实现高效且准确的3D医学图像分割。

摘要:

准确且计算效率高的3D医学图像分割仍然是临床工作流程中的关键挑战。基于Transformer的架构通常在全局上下文建模方面表现优异,但以牺牲过多的参数数量和内存需求为代价,限制了其在临床中的应用。我们提出了RefineFormer3D,一种轻量级的分层Transformer架构,旨在平衡分割精度和计算效率以用于体积医学影像。该架构集成了三个关键组件:(i)基于GhostConv3D的补丁嵌入用于高效的特征提取且冗余极少,(ii)MixFFN3D模块结合低秩投影和深度卷积以实现参数高效的特征提取,(iii)交叉注意力融合解码器,能够实现自适应多尺度跳跃连接整合。RefineFormer3D仅包含2.94M个参数,远少于当前的Transformer基于方法。在ACDC和BraTS基准上的广泛实验表明,RefineFormer3D分别实现了93.44%和85.9%的平均Dice分数,优于或匹配了最先进的方法,同时需要显著更少的参数。此外,该模型在GPU上实现了快速推理(每体积8.35毫秒)且内存需求低,支持在资源受限的临床环境中部署。这些结果确立了RefineFormer3D作为实际3D医学图像分割的有效且可扩展的解决方案。

英文摘要:

Accurate and computationally efficient 3D medical image segmentation remains a critical challenge in clinical workflows. Transformer-based architectures often demonstrate superior global contextual modeling but at the expense of excessive parameter counts and memory demands, restricting their clinical deployment. We propose RefineFormer3D, a lightweight hierarchical transformer architecture that balances segmentation accuracy and computational efficiency for volumetric medical imaging. The architecture integrates three key components: (i) GhostConv3D-based patch embedding for efficient feature extraction with minimal redundancy, (ii) MixFFN3D module with low-rank projections and depthwise convolutions for parameter-efficient feature extraction, and (iii) a cross-attention fusion decoder enabling adaptive multi-scale skip connection integration. RefineFormer3D contains only 2.94M parameters, substantially fewer than contemporary transformer-based methods. Extensive experiments on ACDC and BraTS benchmarks demonstrate that RefineFormer3D achieves 93.44\% and 85.9\% average Dice scores respectively, outperforming or matching state-of-the-art methods while requiring significantly fewer parameters. Furthermore, the model achieves fast inference (8.35 ms per volume on GPU) with low memory requirements, supporting deployment in resource-constrained clinical environments. These results establish RefineFormer3D as an effective and scalable solution for practical 3D medical image segmentation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑