A novel myocardium segmentation approach based on neutrosophic active contour model
A novel myocardium segmentation approach based on neutrosophic active contour model
复制标题
一种基于中智活动轮廓模型的新型心肌分割方法
DOI：
10.1016/j.cmpb.2017.02.020
复制
发表时间：
2017
影响因子：
6.1
通讯作者：
Wang Yu-hang
中科院分区：
文献类型：
--
作者：
Guo Yanhui;Du Guo-Qing;Xue Jing-Yi;Xia Rong;Wang Yu-hang
背景和目的超声心动图中心肌的自动描绘可以帮助放射科医生诊断心脏问题。然而，由于低信噪比、低对比度、边界模糊和斑点噪声，将心肌与其他组织区分开来仍然具有挑战性。为自动检测左心室心肌造影超声心动图（LVMCE）图像中的心肌区域，以帮助放射科医生诊断和进一步测量梗死面积，本研究首先利用LVMCE图像的强度和均匀性特征将LVMCE图像映射到神经相似性（NS）域。然后，提出了一种新的主动轮廓模型（NACM），并定义了能量函数的NS值。最后利用曲线演化结果检测心室。心室的边界被确定为内膜。为了加快进化过程，提高检测精度，聚类算法被用来获得初始心室区域。再次利用NACM中的曲线演化程序来获得心外膜，其中初始轮廓使用检测到的内膜和解剖学知识上的厚度myocardial.ResultsEchocardiographic研究进行了10个雄性Sprague-Dawley大鼠使用Vivid 7系统，包括5个正常情况下，5只大鼠心肌梗死。由经验丰富的放射科医生手动勾画的心肌边界用作性能评价的参考标准。两个指标，Hdist和AvgDist，被用来评估检测结果。将NACM方法与消除粒子群算法（EPSO）和无边缘主动轮廓模型（ACMWE）方法进行了比较。用EPSO法测得的内径Hdist和AvgDist的平均值和标准差分别为6.83 ± 1.12 mm和0.79 ± 0.28 mm，ACMWE法测得的内径Hdist和AvgDist的平均值和标准差分别为7.12 ± 0.98 mm和0.82 ± 0.32 mm，NACM法测得的内径Hdist和AvgDist的平均值和标准差分别为4.55 ± 0.9 mm和0.58 ± 0.18 mm。心外膜的改善更为显著，两个测量值分别由EPSO法的7.45 ± 1.24 mm和1.47 ± 0.34 mm，ACMWE法的8.21±0.43 mm和1.73±0.47 mm，下降到NACM法的4.94 ± 0.82 mm和0.84 ± 0.22 mm。结论该方法能自动准确地检测心肌，为临床治疗学测量心肌灌注和梗死面积提供了参考。
Background and objectivesAutomatic delineation of the myocardium in echocardiography can assist radiologists to diagnosis heart problems. However, it is still challenging to distinguish myocardium from other tissue due to a low signal-to-noise ratio, low contrast, vague boundary, and speckle noise. The purpose of this study is to automatically detect myocardium region in left ventricle myocardial contrast echocardiography (LVMCE) images to help radiologists’ diagnosis and further measurement on infarction size.MethodsThe LVMCE image is firstly mapped into neutrosophic similarity (NS) domain using the intensity and homogeneity features. Then, a neutrosophic active contour model (NACM) is proposed and the energy function is defined by the NS values. Finally, the ventricle is detected using the curve evolving results. The ventricle's boundary is identified as the endocardium. To speed up the evolution procedure and increase the detection accuracy, a clustering algorithm is employed to obtain the initial ventricle region. The curve evolution procedure in NACM is utilized again to obtain the epicardium, where the initial contour uses the detected endocardium and the anatomy knowledge on the thickness of the myocardium.ResultsEchocardiographic studies are performed on 10 male Sprague-Dawley rats using a Vivid 7 system including 5 normal cases and 5 rats with myocardial infarction. The myocardium boundaries manually outlined by an experienced radiologist are used as the reference standard for the performance evaluation. Two metrics, Hdist and AvgDist, are employed to evaluate the detection results. The NACM method was compared with those from the eliminated particle swarm optimization (EPSO) and active contour model without edges (ACMWE) methods. The mean and standard deviation of the Hdist and AvgDist on endocardium are 6.83 ± 1.12 mm and 0.79 ± 0.28 mm using EPSO method, 7.12 ± 0.98 mm and 0.82 ± 0.32 mm using ACMWE method, and 4.55 ± 0.9 mm and 0.58 ± 0.18 mm using NACM method, respectively. The improvement on epicardium is much more significant, and two metrics are decreased from 7.45 ± 1.24 mm, and 1.47 ± 0.34 mm using EPSO method, and 8.21±0.43 mm, and 1.73±0.47 mm using ACMWE method, to 4.94 ± 0.82 mm, and 0.84 ± 0.22 mm using NACM method, respectively.ConclusionsThe proposed method can automatically detect myocardium accurately, and is helpful for clinical therapeutics to measure myocardial perfusion and infarct size.