Ding Yuhan, Yi Zhenglin, Xiao Jiatong, Hu Minghui, Guo Yu, Liao Zhifang, Wang Yongjie
School of Computer Science and Engineering, Central South University, Changsha 410083, China.
Departments of Urology, Xiangya Hospital, Central South University, Changsha 410008, China.
iScience. 2024 Mar 6;27(4):109442. doi: 10.1016/j.isci.2024.109442. eCollection 2024 Apr 19.
Automatically and accurately segmenting skin lesions can be challenging, due to factors such as low contrast and fuzzy boundaries. This paper proposes a hybrid encoder-decoder model (CTH-Net) based on convolutional neural network (CNN) and Transformer, capitalizing on the advantages of these approaches. We propose three modules for skin lesion segmentation and seamlessly connect them with carefully designed model architecture. Better segmentation performance is achieved by introducing SoftPool in the CNN branch and sandglass block in the bottleneck layer. Extensive experiments were conducted on four publicly accessible skin lesion datasets, ISIC 2016, ISIC 2017, ISIC 2018, and PH to confirm the efficacy and benefits of the proposed strategy. Experimental results show that the proposed CTH-Net provides better skin lesion segmentation performance in both quantitative and qualitative testing when compared with state-of-the-art approaches. We believe the CTH-Net design is inspiring and can be extended to other applications/frameworks.
由于对比度低和边界模糊等因素，自动且准确地分割皮肤病变可能具有挑战性。本文提出了一种基于卷积神经网络（CNN）和Transformer的混合编码器-解码器模型（CTH-Net），利用这些方法的优势。我们提出了三个用于皮肤病变分割的模块，并将它们与精心设计的模型架构无缝连接。通过在CNN分支中引入SoftPool和在瓶颈层中引入沙漏块，实现了更好的分割性能。在四个可公开访问的皮肤病变数据集ISIC 2016、ISIC 2017、ISIC 2018和PH上进行了广泛的实验，以证实所提出策略的有效性和优势。实验结果表明，与现有最先进的方法相比，所提出的CTH-Net在定量和定性测试中都提供了更好的皮肤病变分割性能。我们相信CTH-Net的设计具有启发性，并且可以扩展到其他应用/框架。
