中文摘要：

针对现有的血管内超声（intravascularu ltrasound,IVUS）图像边缘提取存在的不足,提出一种改进的IVUS序列图像内外膜边缘自动提取的方法。该方法首先在Contourlet变换域对图像的斑点噪声进行有效去除;然后根据序列图像的物理特征和结构信息,自动确定图像内外膜边缘的初始轮廓;最后采用活动轮廓模型和去噪后图像灰阶梯度特征量,通过动态规划技术自动提取图像的内外膜边缘。实验结果表明,该方法算法简单,准确性较高,具有一定的临床应用价值。

英文摘要：

Because of shortcomings of the existing contour detection of the intravascular ultrasound（IVUS） image,an improved method used for automatically detecting the lumen and media-adventitia contours of sequential IVUS images was presented.First,the speckle noise of the image was effectively removed in the contourlet transform domain.Then,the initial lumen and media-adventitia contours of the image were estimated according to physical properties and structural information of sequential images.Finally,using the active contour model and the grey level gradient of the de-noised image,and according to the dynamic programming technique,the lumen and media-adventitia contours of the image were automatically detected.Experimental results showed that the proposed method is algorithmically simple,statistically accurate,and has clinical value.