一种心肌延迟强化磁共振图像的半自动分割算法

杨聪; 伍卫国; 苏远歧

doi:10.7652/xjtuxb201708002

您当前的位置：

首页 >

文章列表页 >

一种心肌延迟强化磁共振图像的半自动分割算法

更新时间：2025-07-09

- 一种心肌延迟强化磁共振图像的半自动分割算法
- A Semi-Automatic Method for Segmentation of Myocardial DE-MRI
- 西安交通大学学报 2017年51卷第8期页码：6-11
- 作者机构：
  
  西安交通大学电子与信息工程学院,西安,710049
- 作者简介：
- 基金信息：
  
  : 2016-12-16。作者简介: 杨聪(1987—),男,博士生;伍卫国(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(61672423)
- DOI：10.7652/xjtuxb201708002
  中图分类号： TP242.6;TP317.4
- 网络首发：2017-08-10，
  
  纸质出版：2017
- 稿件说明：
移动端阅览
杨聪, 伍卫国, 苏远歧. 一种心肌延迟强化磁共振图像的半自动分割算法[J]. 西安交通大学学报, 2017,51(8):6-11.

A Semi-Automatic Method for Segmentation of Myocardial DE-MRI[J]. 2017, 51(8): 6-11.
杨聪, 伍卫国, 苏远歧. 一种心肌延迟强化磁共振图像的半自动分割算法[J]. 西安交通大学学报, 2017,51(8):6-11. DOI： 10.7652/xjtuxb201708002.

A Semi-Automatic Method for Segmentation of Myocardial DE-MRI[J]. 2017, 51(8): 6-11. DOI： 10.7652/xjtuxb201708002.

摘要

针对心肌延迟强化磁共振图像分割中边界模糊的问题

提出了一种基于水平集的半自动分割算法。该算法通过结合多相水平集算法和Chan-Vese模型

可以同时分割心肌内膜、外膜和心肌梗塞区域的边界。根据心脏左心室的圆形特征

通过增加圆形惩罚项

使得分割心肌内膜的曲线在迭代过程中逐渐接近于圆形

从而解决了心肌内膜边界模糊的问题。根据心肌内膜和外膜之间的距离关系

提出了动态气球力

通过将两条演化曲线之间的距离约束在一定范围内

使得曲线在真实边界附近收敛

从而提高了分割心肌外膜边界的精度。由于正常心肌与发生梗塞的心肌在灰度上存在着明显的差异

采用Chan-Vese模型代替阈值法分割心肌梗塞区域以获取光滑的目标边界。该算法已在STACOM 2012国际竞赛数据集上进行了验证测试

结果表明

算法的平均Dice相似性系数为0.72

较其他算法的平均Dice系数提高了0.07～0.12; 算法具有较好的实验可重复性的同时也具有更好的稳定性。

Abstract

A semiautomatic segmentation method based on level set is proposed to solve the weak boundaries problem in segmentation of myocardial DE-MRI(delayed enhancement magnetic resonance Image). This method uses multiphase level sets and the Chan-Vese model to simultaneously extract the boundaries of endocardium

epicardium and infarction. It relies on the circular shape of the cardiac left ventricle that a circular penalized term is introduced to keep the shape of the evolving contour close to a circle

and thus the difficulty caused by the weak boundaries between the endocardium and trabeculation is overcome. A dynamic balloon force is introduced according to the distance between the myocardial borders to preserve the distance between the two evolving contours within a given range

therefore the segmentation accuracy of the epicardium is improved. Since the gray level of the normal myocardium is significantly different from that of the infarcted myocardium

the Chan-Vese model is used to extract the infarction region of myocardium and to obtain smooth object boundaries. The proposed method is validated on the data set from STACOM 2012 challenge. The average Dice similarity coefficient of the method is 0.72

and is 0.07-0.12 bigger than those of other methods. Experimental results also show that the proposed method obtains better reproducibility

and is more robust than those compared methods.

关键词

Keywords

references

顾晓龙. 急性心肌梗塞合并心力衰竭再灌注后早期应用洋地黄的近期疗效和安全性研究 [D]. 广州: 南方医科大学, 2014: 1-2.

KARIM R, BHAGIRATH P, CLAUS P, et al. Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images [J]. Medical Image Analysis, 2016, 30: 95-107.

UKWATTA E, AREVALO H, LI K, et al. Myocardial infarct segmentation from magnetic resonance images for personalized modeling of cardiac electrophysiology [J]. IEEE Transactions on Medical Imaging, 2016, 35(6): 1408-1419.

RAJCHL M, STIRRAT J, GOUBRAN M, et al. Comparison of semiautomated scar quantification techniques using highresolution, 3-dimensional late-gadolinium-enhancement magnetic resonance imaging [J]. International Journal of Cardiovascular Imaging, 2015, 31(2): 349-357.

ALBA X, FIGUERAS I V R M, LEKADIR K, et al. Healthy and scar myocardial tissue classification in DE-MRI [C]∥Proceedings of the International Conference on Statistical Atlases and Computational Models of the Heart: Imaging and Modelling Challenges. Berlin, Germany: Springer-Verlag, 2012: 62-70.

KOTU L P, ENGAN K, SKRETTING K, et al. Probability mapping of scarred myocardium using texture and intensity features in CMR images [J]. BioMedical Engineering OnLine, 2013, 12(1): 91.

DETSKY J S, PAUL G, DICK A, et al. Reproducible classification of infarct heterogeneity using fuzzy clustering on multicontrast delayed enhancement magnetic resonance images [J]. IEEE Transactions on Medical Imaging, 2009, 28(10): 1606-1614.

KARIM R, CHEN Z, OBOM S, et al. Infarct segmentation of the left ventricle using graph-cuts [C]∥Proceedings of the International Conference on Statistical Atlases and Computational Models of the Heart: Imaging and Modelling Challenges. Berlin, Germany: Springer-Verlag, 2012: 71-79.

RAJCHL M, YUAN J, WHITE J, et al. Interactive hierarchical max-flow segmentation of scar tissue from late-enhancement cardiac MR images [J]. IEEE Transactions on Medical Imaging, 2013, 33(1): 159-172.

LARA L, VERA S, PEREZ F, et al. Supervised learning modelization and segmentation of cardiac scar in delayed enhanced MRI [C]∥Proceedings of the International Conference on Statistical Atlases and Computational Models of the Heart: Imaging and Modelling Challenges. Berlin, Germany: Springer-Verlag, 2012: 53-61.

CHAN T F, VESE L A. Active contour without edges [J]. IEEE Transactions on Image Processing, 2001, 10(2): 266-277.

LI C, XU C, GUI C, et al. Distance regularized level set evolution and its application to image segmentation [J]. IEEE Transactions on Image Processing, 2010, 19(12): 3243-3254.

HENNEMUTH A, FRIMAN O, HUELLEBRAND M, et al. Mixture-model-based segmentation of myocardial delayed enhancement MRI [C]∥Proceedings of the International Conference on Statistical Atlases and Computational Models of the Heart: Imaging and Modelling Challenges. Berlin, Germany: Springer-Verlag, 2012: 87-96.

李莉,冯林,吴俊,等.一种三结构描述子的图像检索方法.2017,51(6):86-91.[doi:10.7652/xjtuxb201706014]

杨源,库涛,查宇飞,等.快速多特征金字塔的尺度目标跟踪方法.2016,50(10):49-56.[doi:10.7652/xjtuxb201610008]

刘凯,张立民,孙永威,等.利用深度玻尔兹曼机与典型相关分析的自动图像标注算法.2015,49(6):33-38.[doi:10.7652/xjtuxb201506006]

吴一全,孟天亮,吴诗婳.人工蜂群优化的非下采样Shearlet域引导滤波图像增强.2015,49(6):39-45.[doi:10.7652/xjtuxb201506007]

唐晓庆,范赐恩,刘鑫,等.基于边缘保持滤波的单幅图像快速去雾.2015,49(3):143-150.[doi:10.7652/xjtuxb201503 022]

贺文骅,刘志镜,屈鉴铭.利用全局约束霍夫模型的目标跟踪算法.2014,48(12):69-73.[doi:10.7652/xjtuxb201412011]

符均,牟轩沁,季文博.亮色分离的饱和图像校正方法.2014,48(10):101-107.[doi:10.7652/xjtuxb201410016]

徐胜军,韩九强,何波,等.融合边缘特征的马尔科夫随机场模型及分割算法.2014,48(2):14-19.[doi:10.7652/xjtuxb 201402003]

王芳梅,范虹,Yi WANG,等.利用改进CV模型连续水平集算法的核磁共振乳腺图像分割.2014,48(2):38-43.[doi:10.7652/xjtuxb201402007]

屠礼芬,仲思东,彭祺.自然场景下运动目标检测与阴影剔除方法.2013,47(12):26-31.[doi:10.7652/xjtuxb201312005]

刘光辉,任庆昌,孟月波,等.自适应先验马尔科夫随机场模型的图像分割算法.2013,47(10):62-67.[doi:10.7652/xjtuxb201310011]

李亚超,周瑞雨,全英汇,等.采用自适应背景窗的舰船目标检测算法.2013,47(6):25-30.[doi:10.7652/xjtuxb201306 005]

姜柯,李艾华,苏延召.结合边缘纹理和抽样推断的自适应阴影检测算法.2013,47(2):39-46.[doi:10.7652/xjtuxb201302 007]

高燕华,刘玉欢,喻罡,等.多尺度非参数花水平集的超声心动图分割.2013,47(2):53-57.[doi:10.7652/xjtuxb201302 009]

赵军,赵继,张雷.焊缝结构光图像处理与特征提取方法.2013,47(1):114-119.[doi:10.7652/xjtuxb201301022]

尹诗白,赵祥模,王卫星等.递推人工蜂群的模糊划分熵多阈值分割算法.2012,46(10):72-77.[doi:10.7652/xjtuxb2012 10013].

穆为磊,高建民,陈富民,等.符合人眼视觉特性的焊缝射线数字图像增强方法.2012,46(3):90-93.[doi:10.7652/xjtuxb201203016]

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

多工况下离心压气机叶轮-机匣一体联合设计优化

三塔合一间接空冷系统结构参数对夏季运行特性的影响研究

扇贝仿生密封腔室内超临界二氧化碳泄漏流湍动能耗散机理研究

超临界水异常区域热力学特性研究

离子液体改性燃料的电流体动力学效应研究