摘要
针对传统深度神经网络在对血管壁图像分割中难以提取具有针对性有效特征的问题,提出一种融合密度连接与自适应加权损失的血管壁图像分割方法。首先通过构建密集连接的分割网络学习更多的边界和轮廓表征以促进特征复用融合;然后设计了改进的自适应加权损失和边界紧凑性损失约束训练网络,利用自适应加权损失自动调整不同区域分割产生的损失比例来引导网络向最佳方向学习;同时引入边界紧凑性损失约束以充分利用边界信息,提升对血管壁图像的分割精度;最后对包含2544张MRI的MERGE血管壁数据集进行了验证实验。结果表明,提出的改进方法能够有效提取血管壁图像的特征信息,在管腔和外壁轮廓分割中的Dice分别达到了93.65%和95.81%,设计的消融实验也充分证明了所提各个模块和网络的有效性,能够更好地实现高精度的图像分割。
Aiming at the traditional deep neural network is difficult to extract effective features from vessel wall image segmentation,this paper proposed a vascular wall image segmentation method combining dense connection and adaptive weighted loss.Firstly,it constructed a densely connected segmentation network to learn more boundary and contour representations to promote feature reuse and fusion,and then designed an improved adaptive weight loss and boundary compactness loss constraint trai-ning network.It used the adaptive weighted loss to automatically adjust the loss ratio of different regions to guide the network to learn in the best direction.At the same time,it introduced the boundary compactness loss constraint to make full use of the boundary information and improve the segmentation accuracy of the blood vessel wall image.Finally,this paper performed vali-dation experiments using the MERGE blood vessel wall dataset containing 2544 MRI.The results show that the proposed improved method can effectively extract the feature information of the vessel wall image,segmentation Dice reaches 93.65%and 95.81%in the segmentation of the lumen contour and the outer wall contour,respectively.The ablation experiment also fully proves the effectiveness of the various module,which can better achieve high-precision image segmentation.
作者
高红霞
郜伟
Gao Hongxia;Gao Wei(School of Software,Henan University of Engineering,Zhengzhou 451191,China;Institute of Sciences,Information Engineering Univer-sity,Zhengzhou 450001,China)
出处
《计算机应用研究》
CSCD
北大核心
2022年第6期1905-1910,共6页
Application Research of Computers
基金
河南省高等学校青年骨干教师培养计划资助项目。
关键词
血管壁图像分割
深度神经网络
密集连接结构
自适应加权损失
边界紧凑性约束
vessel wall image segmentation
deep neural network
dense connection module
adaptive weighted loss
boun-dary compactness constraint
