Information Office, Chongqing University of Science and Technology, Chongqing, 401331, China.
College of Intelligent Technology and Engineering, Chongqing University of Science and Technology, Chongqing, 401331, China.
Sci Rep. 2023 Apr 25;13(1):6762. doi: 10.1038/s41598-023-33357-y.
In recent years, there have been several solutions to medical image segmentation, such as U-shaped structure, transformer-based network, and multi-scale feature learning method. However, their network parameters and real-time performance are often neglected and cannot segment boundary regions well. The main reason is that such networks have deep encoders, a large number of channels, and excessive attention to local information rather than global information, which is crucial to the accuracy of image segmentation. Therefore, we propose a novel multi-branch medical image segmentation network MBSNet. We first design two branches using a parallel residual mixer (PRM) module and dilate convolution block to capture the local and global information of the image. At the same time, a SE-Block and a new spatial attention module enhance the output features. Considering the different output features of the two branches, we adopt a cross-fusion method to effectively combine and complement the features between different layers. MBSNet was tested on five datasets ISIC2018, Kvasir, BUSI, COVID-19, and LGG. The combined results show that MBSNet is lighter, faster, and more accurate. Specifically, for a [Formula: see text] input, MBSNet's FLOPs is 10.68G, with an F1-Score of [Formula: see text] on the Kvasir test dataset, well above [Formula: see text] for UNet++ with FLOPs of 216.55G. We also use the multi-criteria decision making method TOPSIS based on F1-Score, IOU and Geometric-Mean (G-mean) for overall analysis. The proposed MBSNet model performs better than other competitive methods. Code is available at https://github.com/YuLionel/MBSNet .
近年来，已经有几种医学图像分割的解决方案，如 U 形结构、基于变形器的网络和多尺度特征学习方法。然而，它们的网络参数和实时性能往往被忽视，无法很好地分割边界区域。主要原因是这些网络具有深层编码器、大量通道，并且过于关注局部信息而不是全局信息，这对图像分割的准确性至关重要。因此，我们提出了一种新的多分支医学图像分割网络 MBSNet。我们首先使用并行残差混合器 (PRM) 模块和扩张卷积块设计两个分支，以捕获图像的局部和全局信息。同时，使用 SE-Block 和新的空间注意力模块增强输出特征。考虑到两个分支的不同输出特征，我们采用交叉融合方法有效地结合和补充不同层之间的特征。MBSNet 在五个数据集 ISIC2018、Kvasir、BUSI、COVID-19 和 LGG 上进行了测试。综合结果表明，MBSNet 更轻、更快、更准确。具体来说，对于 [Formula: see text] 的输入，MBSNet 的 FLOPs 为 10.68G，在 Kvasir 测试数据集上的 F1-Score 为 [Formula: see text]，远高于 FLOPs 为 216.55G 的 UNet++。我们还使用基于 F1-Score、IOU 和几何平均值 (G-mean) 的多准则决策方法 TOPSIS 进行整体分析。所提出的 MBSNet 模型的性能优于其他竞争方法。代码可在 https://github.com/YuLionel/MBSNet 获得。
