|本期目录/Table of Contents|

[1]王卓英,童基均,蒋路茸,等.基于U Dense net网络的DSA图像冠状动脉血管分割[J].浙江理工大学学报,2021,45-46(自科三):390-399.
 WANG Zhuoying,TONG Jijun,JIANG Lurong,et al.Coronary artery segmentation of DSA images based on UDensenet network[J].Journal of Zhejiang Sci-Tech University,2021,45-46(自科三):390-399.
点击复制

基于U Dense net网络的DSA图像冠状动脉血管分割()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第45-46卷
期数:
2021年自科第三期
页码:
390-399
栏目:
出版日期:
2021-04-28

文章信息/Info

Title:
Coronary artery segmentation of DSA images based on UDensenet network
文章编号:
1673-3851 (2021) 05-0390-10
作者:
王卓英童基均蒋路茸潘哲毅
1. 浙江理工大学信息学院,杭州 310018;2. 武警海警总队医院信息科,浙江嘉兴 314000
Author(s):
WANG Zhuoying1 TONG Jijun1 JIANG Lurong1 PAN Zheyi2
1. School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China; 2. Information Office, Hospital of Coast Guard Corps of Chinese People′s Armed Police Forces, Jiaxing 314000, China
关键词:
冠状动脉血管图像分割UDensenet密集残差块注意力机制深度神经网络DSA
分类号:
TS391-4
文献标志码:
A
摘要:
冠状动脉血管是研究心血管疾病的重要基础,为准确分割DSA(Digital subtraction angiography)图像冠状动脉血管,提高训练过程中血管特征的有效利用率,提出了一种基于UDensenet网络的分割方法。该方法首先对数据集进行限制对比度直方图均衡化预处理;然后对预处理结果进行图像粗分割,基于UDensenet网络,在解码器部分融合密集残差块和注意力机制实现深度神经网络模型,加强特征映射,充分提取局部特征,实现血管与背景的分类;最后利用形态学处理、阈值分割、基于多点区域生长的连通域分析进行图像细分割,实现血管的提取。将测试结果和3位专家手工标注的标准图进行对比分析,结果表明:该数据集的分割结果精确率、召回率、F1分数分别为8322%、8981%、8604%,3种特性曲线下的平均面积为09923。与其他方法比较,该方法提取到的血管信息较为完整,为精确分割冠状动脉血管提供了一种解决方案。

参考文献/References:

[1] Woodruffe S, Neubeck L, Clark R A, et al. Australian cardiovascular health and rehabilitation association (ACRA) core components of cardiovascular disease secondary prevention and cardiac rehabilitation 2014[J]. Heart, Lung and Circulation, 2015, 24(5): 430-441.
[2] Kirili H A, Schaap M, Metz C T, et al. Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography[J]. Medical Image Analysis, 2013, 17(8): 859-876.
[3] 康文炜. 冠状动脉造影图像的分割方法研究[D]. 长春: 吉林大学, 2010: 11.
[4] Kerkeni A, Benabdallah A, Manzanera A, et al. A coronary artery segmentation method based on multiscale analysis and region growing[J]. Computerized Medical Imaging and Graphics, 2016, 48: 49-61.
[5] CervantesSanchez F, CruzAceves I, HernandezAguirre A, et al. Coronary artery segmentation in Xray angiograms using Gabor filters and differential evolution[J]. Applied Radiation and Isotopes, 2018, 138: 18-24.
[6] Mabrouk S, Oueslati C, Ghorbel F. Multiscale graph cuts based method for coronary artery segmentation in angiograms[J]. Innovation and Research in BioMedical Engineering, 2017, 38(3): 167-175.
[7] Zhao B, Feng J S, Wu X, et al. A Survey on deep learningbased finegrained object classification and semantic segmentation[J]. International Journal of Automation and Computing, 2017, 14(2): 119-135.
[8] 杨少戈. 基于深度学习的冠脉造影图像分割[D]. 北京: 北京邮电大学, 2019: 44-49.
[9] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.
[10] He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.

相似文献/References:

[1]孙麒. 基于极大似然估计的织物图像分割[J].浙江理工大学学报,2013,30(01):12.
 SUN Qi. Textile Image Segmentation Based on theMaximum Likelihood Algorithm[J].Journal of Zhejiang Sci-Tech University,2013,30(自科三):12.
[2]娄翔飞,吕文涛,叶冬,等.基于计算机视觉的行人检测方法研究进展[J].浙江理工大学学报,2023,49-50(自科三):318.
 LOU Xiangfei,L  Wentao,YE Dong,et al.Research progress of pedestrian detection methods  based on computer vision[J].Journal of Zhejiang Sci-Tech University,2023,49-50(自科三):318.
[3]祝鹏烜,黄体仁,李旭.MSAG-TransNet:肺部CT图像中新冠肺炎感染新型冠状病毒感染区域的分割模型[J].浙江理工大学学报,2023,49-50(自科六):734.
 ZHU Pengxuan,HUANG Tiren,LI Xu.MSAG-TransNet: Segmentation model of COVID-19 infected areas in lung CT images[J].Journal of Zhejiang Sci-Tech University,2023,49-50(自科三):734.

备注/Memo

备注/Memo:
收稿日期:2020-09-02
网络出版日期:2021-02-04
基金项目:国家自然科学基金项目(61602417);浙江理工大学基础研究项目(2019Q042);浙江理工大学“521人才培养计划”
作者简介:王卓英(1996-),女,山西吕梁人,硕士研究生,主要从事智能医学图像处理方面的研究
通信作者:潘哲毅,E-mail:panzheyi@sina.com
更新日期/Last Update: 2021-06-29