蚁群算法在全方向M型心动图检测中的应用与研究

为了解决传统边缘检测算法对全方向M型心动图检测效果差的问题,根据基于蚁群算法边缘检测的思想,提出一种基于改进的蚁群算法的边缘检测算法。根据心动图间接来源于CT图的原理,一幅心动图中包含目标、背景、边界和噪声等内容,因此采用传统的边缘检测算法的效果并不理想。这里在传统蚁群算法边缘检测的基础上,根据心动图的特点,采取改进的转移规则和信息素更新策略,以提高检测精度和适应性。再逐步细化,使用蚂蚁算法进行详细的检测,得到最佳的运动曲线。实验结果表明,该算法可以获得精确的运动曲线,其结果能够比传统的方法获得更丰富更真实的心动图运动细节信息,为医生的诊断提供更多信息。

Application of ant colony algorithm in omni-directional M-mode echocardiography

In order to solve the problem that the traditional edge detection algorithm has poor detection effect of omni-di-rectional M-mode echocardiography,an edge detection algorithm based on the improved ant colony algorithm is presented according to the idea of edge detection based on the ant colony algorithm. According to the principle that the echocardiography comes indirect-ly from CT figure,that is,an echocardiography contains the contents of target,background,boundary,noise,etc.,it is point-ed out that the detection effect of traditional edge detection algorithm for omni-directional M-mode echocardiography is not ex-pected. According to the characteristics of echocardiography,the improved transition rule and pheromone update strategy was taken to improve the detection precision and adaptability. The best motion curves were obtained by gradually thinning and de-tailed edge detection with the ant algorithm. The experimental results show that the algorithm can get the more accurate motion curve and more actual and detail information than the traditional method. Therefore,the algorithm can provide more information for the doctor’s diagnosis.