计算机科学与探索 ›› 2024, Vol. 18 ›› Issue (4): 978-989.DOI: 10.3778/j.issn.1673-9418.2303122

• 图形·图像 • 上一篇    下一篇

王龙业,肖越,曾晓莉,张凯信,马傲

王龙业,肖越,曾晓莉,张凯信,马傲   

  1. 1. 西南石油大学 电气信息学院,成都 610500
    2. 西藏大学 信息科学技术学院,拉萨 850000
  • 出版日期:2024-04-01 发布日期:2024-04-01

Skin Disease Segmentation Method Combining Dense Encoder and Dual-Path Attention

WANG Longye, XIAO Yue, ZENG Xiaoli, ZHANG Kaixin, MA Ao   

  1. 1. School of Electronics and Information Engineering, Southwest Petroleum University, Chengdu 610500, China
    2. School of Information Science and Technology, Tibet University, Lhasa 850000, China
  • Online:2024-04-01 Published:2024-04-01

摘要: 针对皮肤镜图像病变区域存在形状大小各异、边界不连续且模糊、病灶区域与背景相似度高的问题,提出了一种融合密集编码器与双路径注意力的皮肤病变分割网络(DEDA-Net)。首先,运用密集编码模块进行多尺度信息融合增强网络特征提取能力,缓解皮肤镜图像中边缘模糊的问题,并采用跳跃连接与残差路径减少网络编解码之间的语义鸿沟;其次,根据特征图内每个特征点关联性程度大小进行加权提出了全局正态池化层,设计了在空间与通道两个维度提取特征信息的双路径注意力模块,避免因全局信息获取不足导致难以区分病灶区域与背景的问题;最后,利用辅助损失函数思想,在网络中间与最后的输出层两侧使用加权损失函数来提升网络泛化能力。实验结果表明,该算法在ISIC2017数据集上分割精度为96.45%,特异性为97.82%,Dice系数为93.16%,IoU为86.61%,比基线U-Net分别提高了5.93个百分点、6.45个百分点、6.53个百分点和5.63个百分点,能够有效分割皮肤病变区域。

关键词: 皮肤病分割, 多尺度融合, 密集编码, 注意力机制, 全局正态池化

Abstract: Aiming at the problems of different shapes and sizes, discontinuous and blurred boundaries, and high similarity between the lesion area and the background in dermoscopic image lesion areas, a skin lesion segmentation network integrating dense encoder and dual-path attention (DEDA-Net) is proposed. Firstly, the network employs a dense coding module for multi-scale information fusion to enhance network feature extraction capabilities, alleviating blurred edges in dermoscopic images. Skip connection and residual path are used to reduce the semantic gap in the network coding and decoding parts. Secondly, a global normal pooling layer is proposed that weights feature points in the feature map based on their degree of relevance, and a dual-path attention module that extracts feature information in two dimensions, space and channel, is designed to avoid the problem that it is difficult to distinguish the lesion area from the background due to insufficient global information acquisition. Finally, using the idea of an auxiliary loss function, a weighted loss function is employed on both sides of the middle of the network and the final output layer to improve generalization ability of the network. Experimental results show that the algorithm achieves a segmentation accuracy of 96.45%, a specificity of 97.82%, a Dice coefficient of 93.16%, and an IoU of 86.61% on the ISIC2017 dataset, which are 5.93 percentage points, 6.45 percentage points, 6.53 percentage points, and 5.63 percentage points higher than the baseline U-Net, demonstrating the effectiveness of the proposed algorithm in accurately segmenting skin lesion areas.

Key words: dermatology segmentation, multi-scale fusion, dense coding, attention mechanism, global normal pooling