基于边缘引导的多尺度医学影像分割方法  

Medical Image Segmentation Based on Multi-scale Edge Guidance

作　　者：姜灏天 王琦智 黄扬林 章雅琴[2] 胡凯[1] JIANG Haotian;WANG Qizhi;HUANG Yanglin;ZHANG Yaqin;HU Kai(School of Computer Science&School of Cyberspace Science,Xiangtan University,Xiangtan,Hunan 411105,China;Department of Radiology,The Third Xiangya Hospital,Central South University,Changsha 410013,China)

机构地区：[1]湘潭大学计算机学院·网络空间安全学院,湖南湘潭411105 [2]中南大学湘雅三医院放射科,长沙410013

出　　处：《计算机科学》2023年第S02期1026-1032,共7页Computer Science

基　　金：国家自然科学基金(61802328);中国大学生创新创业项目(S202110530024)。

摘　　要：医学影像的灰阶变化小,分割目标与背景不易区分,因此,进行影像分割是充满挑战性的问题。现有网络模型大多将高频的分割边缘与低频的主体部分统一学习,忽视了高频与低频信息的差异性和两者在图像中占比不同的差别。针对这一问题,提出了基于边缘引导的多尺度卷积神经网络Edge Guided V-Shape Network(EGV-Net),从低频分割主体和高频分割边缘两个特征角度进行针对性学习。其中,低频特征通过编码-解码方式进行特征传递,学习分割目标的主体部分;高频特征则通过边缘提取方法,首先将高频语义信息从分割图谱中提取出来,再将分割边缘过滤分离。高频边缘通过边缘引导模块指导模型对低频特征做出精准的分割,并恢复边缘细节精度。在肝脏影像与ISIC2016数据集上进行的实验结果表明,所提算法对整体分割的把控能力更强,在边缘细节处有更好的分割效果,优于其他模型。Medical images have small gray-scale changes,and segmentation targets and backgrounds are not easy to distinguish,thus image segmentation is full of challenging problems.Most of the existing models unify the segmented high-frequency edges with the low-frequency subjects for learning,ignoring the difference between high-frequency information and low-frequency information and the difference in the proportion of both in the image.To address this problem,edge guided V-shape network(EGV-Net),a multi-scale convolutional neural network based on edge guidance,is proposed to perform targeted learning from two feature perspectives:low-frequency segmented subjects and high-frequency segmented edges.Among them,the low-frequency features are passed through the feature transfer by the encoder-decoder connection method to learn the main part of the segmentation target.The high-frequency features are firstly extracted from the segmentation mapping by edge extraction method,and then the segmentation edges are filtered and separated from it.The segmented edges of high frequency are guided by edge guidance module to make accurate segmentation of low frequency segmented edges and recover edge detail accuracy.Experimental results in liver images and ISIC2016 show that the proposed algorithm has better control over the overall segmentation and better segmentation effect at the edge details than other models.

关 键 词：深度学习 医学影像分割 多尺度特征 边缘提取 边缘引导 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]