Shen Xian-hua, Li De-yu, Lin Jiang-li, Wang Tian-fu, Wen Xiao-hui, Zheng Chang-qiong, Rao Li, Tang Hong
Biomedical Engineering Center, Sichuan University, Chengdu Sichuan.
Space Med Med Eng (Beijing). 2005 Aug;18(4):246-50.
To improve the precision of the traditional segmentation of echocardiogram, by suppressing the influence from inherent speckle noises in medical ultrasonic images.
An automatic segmentation method based on reconstructed morphology was proposed in this paper. First, the opening and closing operations by reconstruction were imposed to the ultrasonic image. Second, the top-hat operation was used to extract the bright and/or dark features and to find out the boundaries corresponding to these features, whereby implemented the automatic segmentation.
The segmented echocardiogram had less artificial boundaries resulted from speckle noise, and could accurately be extracted the artery and ventricle.
The presented method can detect both dark and bright objects accurately, and the boundary has a fine continuity. In addition, the algorithm is also applicable to the extraction of sole bright/dark features, accordingly to reduce the complexity and time needed and to improve the accuracy.
通过抑制医学超声图像中固有斑点噪声的影响，提高传统超声心动图分割的精度。
本文提出了一种基于形态学重建的自动分割方法。首先，对超声图像进行重建开运算和重建闭运算。其次，利用顶帽变换提取亮和/或暗特征，并找出对应这些特征的边界，从而实现自动分割。
分割后的超声心动图中由斑点噪声产生的人工边界较少，能够准确提取动脉和心室。
所提方法能够准确检测亮暗目标，边界具有良好的连续性。此外，该算法也适用于单独亮/暗特征的提取，从而降低复杂度和所需时间，提高准确性。
