摘要
目的超声图像是临床医学中应用最广泛的医学图像之一,但左心室超声图像一般具有强噪声、弱边缘和组织结构复杂等问题,其图像分割难度较大。临床上需要一种效率高、质量好的超声图像左心室分割算法。本文提出一种基于深层聚合残差密集网络(deep layer aggregation for residual dense network,DLA-RDNet)的超声图像左心室分割算法。方法对获取的超声图像进行形态学操作,定位目标区域,得到目标图像。构建残差密集网络(residual dense network,RDNet)用于提取图像特征,并将RDNet得到的层次信息通过深层聚合(deep layer aggregation,DLA)的方式紧密融合到一起,得到分割网络DLA-RDNet,用于实现对超声图像左心室的精确分割。通过深监督(deep supervision,DS)方式为网络剪枝,简化网络结构,提升网络运行速度。结果数据测试集的实验结果表明,所提算法平均准确率为95.68%,平均交并比为97.13%,平均相似性系数为97.15%,平均垂直距离为0.31 mm,分割轮廓合格率为99.32%。与6种分割算法相比,所提算法的分割精度更高。在测试阶段,每幅图像仅需不到1 s的时间即可完成分割,远远超出了专业医生的分割速度。结论提出了一种深层聚合残差密集神经网络对超声图像左心室进行分割,通过主、客观对比实验表明本文算法的有效性,能够较对比方法更实时准确地对超声图像左心室进行分割,符合临床医学中超声图像左心室分割的需求。
Objective Ultrasound images are widely used in clinical medicine.Compared with other medical imaging technologies,ultrasound(US)images are noninvasive,emit non-ionizing radiation,and are relatively cheap and simple to operate.To assess whether a heart is healthy,the ejection fraction is measured,and the regional wall motion is assessed on the basis of identifying the endocardial border of the left ventricle.Generally,cardiologists analyze and segment ultrasound images in a manual or semiautomatic manner to identify the endocardial border of the left ventricle on ultrasound images.However,these segmentation methods have some disadvantages.On the one hand,they are cumbersome and time-consuming tasks,and these ultrasound images can only be segmented by the professional clinicians.On the other hand,the images must be resegmented for different heart disease patients.These problems can be solved by automatic segmentation systems.Unfortunately,affected by ultrasound imaging device and complex heart structure,left ventricular segmentation suffers from the fol lowing challenges:first,false edges lead to incorrect segmentation results because the gray scale of the trabecular and mastoid muscles is similar to the myocardial gray scale.Second,the shapes of the left ventricular heart slice are irregular under the influence of the atrium.Third,the accurate positions of the left ventricles are difficult to obtain from ultrasound images because the gray value of the edges is almost the same with that of the myocardium and the tissues surrounding the left heart(such as fats and lungs).Fourth,ultrasound imaging devices produce substantial noise,which affects the quality of ultrasound images;thus,the resolution of ultrasound images is low and thus not conducive to ventricular structure segmentation.In recent years,algorithms for left ventricular segmentation have considerably improved;however,some problems remain.Compared with traditional segmentation methods,deep learning-based methods are more advanced,but some useful original in
作者
吴宣言
缑新科
朱子重
魏域林
王凯
Wu Xuanyan;Gou Xinke;Zhu Zizhong;Wei Yulin;Wang Kai(College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou 730050,China)
出处
《中国图象图形学报》
CSCD
北大核心
2020年第9期1930-1942,共13页
Journal of Image and Graphics
基金
国家自然科学基金项目(61866022,61876161)
甘肃省教育厅科研创新团队项目(2018C-09)。
关键词
超声图像
左心室分割
深层聚合
残差密集网络
网络剪枝
ultrasound(US)image
left ventricular segmentation
deep layer aggregation(DLA)
residual dense network(RDNet)
network pruning
