基于时/空滤波噪声抑制算法和活动轮廓模型的血管内超声图像边缘提取

Edge detection of IVUS images based on a temporal/spatial filtering noise suppressing algorithm and the active contour model

为解决血管内超声(IVUS)图像中严重的血液斑点噪声影响边缘提取方法的有效性问题,采用一种时/空滤波方法对IVUS图像进行降噪预处理,基于活动轮廓模型(Snake模型)和IVUS图像的边缘对比度特征量,利用Hopfield神经网络并结合模拟退火算法自动提取IVUS图像的冠脉血管壁内、外膜边缘.实验结果表明,该方法对序列IVUS图像处理有较好的可重复性和鲁棒性.

Blood speckle noise in the IVUS image would affect： the validity of edge detection badly. A temporal/spatial filtering method was used to preprocess the IVUS image to restrain the noise. Then a method to automatically detect the intima and ectoblastic edge of IVUS image was presented. This method is based on the active contour model （Snakes model） and the contrast properties of 1VUS image, which makes use of the Hopfield NN and simulated annealing algorithm. Experiments show that the method is accurate, repeatable and robust for sequential IVUS frames.