Guo Yanhui, Du Guo-Qing, Xue Jing-Yi, Xia Rong, Wang Yu-Hang
Department of Computer Science, University of Illinois at Springfield, Springfield, IL USA.
Department of Ultrasound, Second Affiliated Hospital of Harbin Medical University, Harbin, China.
Comput Methods Programs Biomed. 2017 Apr;142:109-116. doi: 10.1016/j.cmpb.2017.02.020. Epub 2017 Feb 22.
Automatic 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.
The 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.
Echocardiographic 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 ± 1.12mm and 0.79 ± 0.28mm using EPSO method, 7.12 ± 0.98mm and 0.82 ± 0.32mm using ACMWE method, and 4.55 ± 0.9mm and 0.58 ± 0.18mm using NACM method, respectively. The improvement on epicardium is much more significant, and two metrics are decreased from 7.45 ± 1.24mm, and 1.47 ± 0.34mm using EPSO method, and 8.21±0.43mm, and 1.73±0.47mm using ACMWE method, to 4.94 ± 0.82mm, and 0.84 ± 0.22mm using NACM method, respectively.
The proposed method can automatically detect myocardium accurately, and is helpful for clinical therapeutics to measure myocardial perfusion and infarct size.
超声心动图中心肌的自动勾勒有助于放射科医生诊断心脏问题。然而，由于信噪比低、对比度低、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。本研究的目的是自动检测左心室心肌对比超声心动图（LVMCE）图像中的心肌区域，以帮助放射科医生进行诊断并进一步测量梗死面积。
首先利用强度和均匀性特征将LVMCE图像映射到中智相似性（NS）域。然后，提出了一种中智活动轮廓模型（NACM），并通过NS值定义能量函数。最后，利用曲线演化结果检测心室。心室边界被确定为心内膜。为了加快演化过程并提高检测精度，采用聚类算法获得初始心室区域。再次利用NACM中的曲线演化过程获得心包，其中初始轮廓使用检测到的心内膜和心肌厚度的解剖学知识。
使用Vivid 7系统对10只雄性Sprague-Dawley大鼠进行超声心动图研究，包括5例正常病例和5例心肌梗死大鼠。由经验丰富的放射科医生手动勾勒的心内膜边界用作性能评估的参考标准。采用Hdist和AvgDist两个指标来评估检测结果。将NACM方法与消除粒子群优化（EPSO）方法和无边缘活动轮廓模型（ACMWE）方法的结果进行比较。使用EPSO方法时，心内膜上Hdist和AvgDist的平均值和标准差分别为6.83±1.12mm和0.79±0.28mm；使用ACMWE方法时，分别为7.12±0.98mm和0.82±0.32mm；使用NACM方法时，分别为4.55±0.9mm和0.58±0.18mm。在心包方面的改善更为显著，使用EPSO方法时，两个指标分别从7.45±1.24mm和1.47±0.34mm降至4.94±0.82mm和0.84±0.22mm；使用ACMWE方法时，分别从8.21±0.43mm和1.73±0.47mm降至4.94±0.82mm和0.84±0.22mm。
所提出的方法能够准确自动检测心肌，有助于临床治疗中测量心肌灌注和梗死面积。
