Skip to main content
QUICK REVIEW

[论文解读] SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography

Jinke Wang, Peiqing Lv|arXiv (Cornell University)|Mar 11, 2021
Advanced Neural Network Applications参考文献 32被引用 4
一句话总结

本文提出SAR-U-Net,一种在2D U-Net基础上引入挤压-激励(SE)模块、空洞空间金字塔池化(ASPP)和残差学习的变体,用于在CT扫描中实现精确的肝脏分割。该模型在LiTS17和SLiver07数据集上达到最先进性能,Dice分数分别为95.71%和97.31%,展现出对复杂肝脏边界及小块/碎片化区域的卓越鲁棒性。

ABSTRACT

Background and objective: In this paper, a modified U-Net based framework is presented, which leverages techniques from Squeeze-and-Excitation (SE) block, Atrous Spatial Pyramid Pooling (ASPP) and residual learning for accurate and robust liver CT segmentation, and the effectiveness of the proposed method was tested on two public datasets LiTS17 and SLiver07. Methods: A new network architecture called SAR-U-Net was designed. Firstly, the SE block is introduced to adaptively extract image features after each convolution in the U-Net encoder, while suppressing irrelevant regions, and highlighting features of specific segmentation task; Secondly, ASPP was employed to replace the transition layer and the output layer, and acquire multi-scale image information via different receptive fields. Thirdly, to alleviate the degradation problem, the traditional convolution block was replaced with the residual block and thus prompt the network to gain accuracy from considerably increased depth. Results: In the LiTS17 experiment, the mean values of Dice, VOE, RVD, ASD and MSD were 95.71, 9.52, -0.84, 1.54 and 29.14, respectively. Compared with other closely related 2D-based models, the proposed method achieved the highest accuracy. In the experiment of the SLiver07, the mean values of Dice, VOE, RVD, ASD and MSD were 97.31, 5.37, -1.08, 1.85 and 27.45, respectively. Compared with other closely related models, the proposed method achieved the highest segmentation accuracy except for the RVD. Conclusion: The proposed model enables a great improvement on the accuracy compared to 2D-based models, and its robustness in circumvent challenging problems, such as small liver regions, discontinuous liver regions, and fuzzy liver boundaries, is also well demonstrated and validated.

研究动机与目标

  • 为解决由于小肝脏区域、不连续结构和模糊边界导致的CT扫描中肝脏分割不准确问题。
  • 提升2D U-Net架构中的特征表示与多尺度上下文建模能力,以提高分割精度。
  • 通过在U-Net编码器和解码器中集成残差学习,减少深层网络中的性能退化。
  • 验证在U-Net框架中结合SE模块与ASPP的有效性,用于医学图像分割。
  • 在公开肝脏分割基准数据集LiTS17和SLiver07上实现最先进性能。

提出的方法

  • 在U-Net编码器的每个卷积层后集成SE模块,基于全局上下文重新校准通道维度的特征响应,突出相关特征并抑制无关特征。
  • 使用空洞空间金字塔池化(ASPP)替代原有的过渡层和输出层,通过不同空洞率的空洞卷积捕捉多尺度上下文信息。
  • 使用残差块替代标准卷积块,以缓解梯度消失问题,支持更深网络的训练,提升学习效率与精度。
  • 保留U-Net的编码器-解码器架构,通过跳跃连接实现编码路径与解码路径之间的特征融合。
  • 采用二元交叉熵损失与Dice损失联合训练网络,端到端优化分割性能。
  • 在两个公开数据集(LiTS17和SLiver07)上评估模型,采用标准指标包括Dice、VOE、RVD、ASD和MSD。

实验结果

研究问题

  • RQ1在U-Net中集成挤压-激励模块是否能提升肝脏CT分割的特征表示能力?
  • RQ2在2D U-Net架构中引入空洞空间金字塔池化是否能增强多尺度上下文建模并提高分割精度?
  • RQ3残差学习在U-Net基肝脏分割模型中在多大程度上提升了网络深度与性能?
  • RQ4所提出的SAR-U-Net与最先进2D模型相比,在肝脏分割基准数据集上的表现如何?
  • RQ5该模型能否稳健处理小块、不连续或边界不清晰的肝脏区域等挑战性情况?

主要发现

  • 在LiTS17数据集上,SAR-U-Net取得95.71%的Dice分数,优于比较中的其他2D模型。
  • 在LiTS17上,模型的VOE为9.52%,RVD为-0.84%,ASD为1.54 mm,MSD为29.14 mm,表明分割精度与一致性均较高。
  • 在SLiver07数据集上,模型取得97.31%的Dice分数,为可比模型中的最高值,VOE为5.37%,RVD为-1.08%,ASD为1.85 mm,MSD为27.45 mm。
  • 模型在分割小块、不连续及边界模糊的肝脏区域方面表现出强鲁棒性,优于基线U-Net及相关架构。
  • 消融实验表明,SE模块、ASPP与残差学习的组合显著优于单一组件。
  • 结果验证了所提出的SAR-U-Net架构能有效捕捉多尺度上下文信息并增强特征判别能力,从而实现最先进水平的分割精度。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。