文献速递心血管MR

兼顾高性能与轻量化:HL-UNet用于3D心脏医学图像分割

Balancing High-performance and Lightweight: HL-UNet for 3D Cardiac Medical Image Segmentation.
PubMed 文献 · Acad Radiol · 2024-06-20

研究提出轻量化3D心脏图像分割网络HL-UNet,融合残差增强自适应注意力模块与Visual Mamba模块。与TransUNet等大模型相比,右心室腔、左心室心肌、左心室腔Dice分别提高1.61%、5.03%、0.19%,参数量和FLOPs分别减少41.3 M和31.05 G。与MISSFormer等轻量模型相比,参数量与计算复杂度接近或更低时,上述三个Dice分别提高4.11%、3.82%、4.33%。

要点

  • HL-UNet在参数量减少41.3 M、FLOPs减少31.05 G的同时,右心室腔、左心室心肌、左心室腔Dice较大模型分别提高1.61%、5.03%、0.19%。
  • 与轻量模型参数量与计算复杂度接近或更低时,右心室腔、左心室心肌、左心室腔Dice分别提高4.11%、3.82%、4.33%。
  • 模型通过残差增强自适应注意力模块与Visual Mamba模块兼顾局部细节与边缘信息。

核心结论

  • HL-UNet在保持轻量化的同时捕捉图像局部细节与边缘信息;较大模型显著降低参数量与计算复杂度并维持性能、提高每秒帧数,较轻量模型在多项关键指标上大幅提升且参数量与计算复杂度接近或更低。

研究设计与样本

  • 提出并评估3D高性能轻量化医学图像分割网络HL-UNet,用于心脏图像分割,对比大模型TransUNet与轻量模型MISSFormer。

诊断标准与关键数值

  • 较大模型TransUNet,HL-UNet的右心室腔、左心室心肌、左心室腔Dice分别提高1.61%、5.03%、0.19%,参数量减少41.3 M,FLOPs减少31.05 G。
  • 较MISSFormer,HL-UNet的右心室腔、左心室心肌、左心室腔Dice分别提高4.11%、3.82%、4.33%,参数量与计算复杂度接近或更低。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: Cardiac magnetic resonance imaging is a crucial tool for analyzing, diagnosing, and formulating treatment plans for cardiovascular diseases. Currently, there is very little research focused on balancing cardiac segmentation performance with lightweight methods. Despite the existence of numerous efficient image segmentation algorithms, they primarily rely on complex and computationally intensive network models, making it challenging to implement them on resource-constrained medical devices. Furthermore, simplified models designed to meet the requirements of device lightweighting may have limitations in comprehending and utilizing both global and local information for cardiac segmentation.

MATERIALS AND METHODS: We propose a novel 3D high-performance lightweight medical image segmentation network, HL-UNet, for application in cardiac image segmentation. Specifically, in HL-UNet, we propose a novel residual-enhanced Adaptive attention (REAA) module that combines residual-enhanced connectivity with an adaptive attention mechanism to efficiently capture key features of input images and optimize their representation capabilities, and integrates the Visual Mamba (VSS) module to enhance the performance of HL-UNet.

RESULTS: Compared to large-scale models such as TransUNet, HL-UNet increased the Dice of the right ventricular cavity (RV), left ventricular myocardia (MYO), and left ventricular cavity (LV), the key indicators of cardiac image segmentation, by 1.61%, 5.03% and 0.19%, respectively. At the same time, the Params and FLOPs of the model decreased by 41.3 M and 31.05 G, respectively. Furthermore, compared to lightweight models such as the MISSFormer, the HL-UNet improves the Dice of RV, MYO, and LV by 4.11%, 3.82%, and 4.33%, respectively, when the number of parameters and computational complexity are close to or even lower.

CONCLUSION: The proposed HL-UNet model captures local details and edge information in images while being lightweight. Experimental results show that compared with large-scale models, HL-UNet significantly reduces the number of parameters and computational complexity while maintaining performance, thereby increasing frames per second (FPS). Compared to lightweight models, HL-UNet shows substantial improvements across various key metrics, with parameter count and computational complexity approaching or even lower.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Zhou H, Hu B, Yi N, et al. Balancing High-performance and Lightweight: HL-UNet for 3D Cardiac Medical Image Segmentation. Acad Radiol. 2024. PMID: 38902109. doi:10.1016/j.acra.2024.06.008

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。