Boundary-Sensitive Loss Function With Location Constraint for Hard Region Segmentation
Boundary-Sensitive Loss Function With Location Constraint for Hard Region Segmentation
复制标题
DOI：
10.1109/jbhi.2022.3222390
复制
发表时间：
2022-11
影响因子：
7.7
通讯作者：
Jie Du;K. Guan;Peng Liu;Yuanman Li;Tianfu Wang
中科院分区：
文献类型：
--
作者：
Jie Du;K. Guan;Peng Liu;Yuanman Li;Tianfu Wang
在计算机辅助诊断和治疗规划中，医学图像的准确分割起着至关重要的作用，特别是对于边界、小目标和背景干扰等困难区域。然而，现有的分割损失函数，包括基于分布、基于区域和基于边界的损失函数，在这些硬区域上不能达到令人满意的性能。本文提出了一种带位置约束的边界敏感损失函数用于医学图像的硬区域分割，它具有三个优点：(1)边界敏感损失(BS-Loss)可以自动关注难以分割的边界(如薄结构和模糊边界)，从而获得更精细的目标边界；(2)BS-Loss还可以在训练过程中调整对小目标的关注，以便更准确地分割它们；以及(Iii)位置约束通过预测和地面真实(GT)像素在每个轴上的分布匹配来缓解背景干扰的负面影响。借助于所提出的BS-Loss和位置约束，可以同时考虑前景和背景中的硬区域。在三个公开数据集上的实验结果证明了该方法的优越性。具体地说，与本研究中测试的次佳方法相比，我们的方法在硬区域上的性能得到了提高，骰子相似系数(DSC)和95%Hausdorff距离(95%HD)分别高达4.17%和73%。此外，它还获得了最好的整体分割性能。因此，我们可以得出结论，我们的方法能够准确地分割这些硬区域，提高了医学图像的整体分割性能。
In computer-aided diagnosis and treatment planning, accurate segmentation of medical images plays an essential role, especially for some hard regions including boundaries, small objects and background interference. However, existing segmentation loss functions including distribution-, region- and boundary-based losses cannot achieve satisfactory performances on these hard regions. In this paper, a boundary-sensitive loss function with location constraint is proposed for hard region segmentation in medical images, which provides three advantages: i) our Boundary-Sensitive loss (BS-loss) can automatically pay more attention to the hard-to-segment boundaries (e.g., thin structures and blurred boundaries), thus obtaining finer object boundaries; ii) BS-loss also can adjust its attention to small objects during training to segment them more accurately; and iii) our location constraint can alleviate the negative impact of the background interference, through the distribution matching of pixels between prediction and Ground Truth (GT) along each axis. By resorting to the proposed BS-loss and location constraint, the hard regions in both foreground and background are considered. Experimental results on three public datasets demonstrate the superiority of our method. Specifically, compared to the second-best method tested in this study, our method improves performance on hard regions in terms of Dice similarity coefficient (DSC) and 95% Hausdorff distance (95%HD) of up to 4.17% and 73% respectively. In addition, it also achieves the best overall segmentation performance. Hence, we can conclude that our method can accurately segment these hard regions and improve the overall segmentation performance in medical images.