基于乘性梯度的医学超声图像边缘检测算法

Multiplicative gradient based edge detection method for medical ultrasound image

通过改进传统乘性梯度(MG)算子,并结合Canny算子的处理结果,准确、快速地提取了医学超声图像的边缘.通过提升乘性梯度算子模板的维度,提高对弱边缘的检测能力;综合考虑乘性梯度算子和Canny算子的运算结果,提高边缘检测的准确度.为了验证该算法的有效性,对仿真及在体超声图像进行边缘提取实验,将结果与其他抗噪性较好的边缘检测方法进行对比.实验结果表明:对于含有不同强度斑点噪声的超声图像,该算法的边缘检测准确度可达75%以上,具有较好的实时性,适用于对医学超声图像进行快速、准确的边缘检测.

Abstract. An accurate and fast edge detection method for medical ultrasound images was proposed based on a modified multiplicative gradient （MG） operator and the traditional Canny. The dimension of the template of the MG operator was increased to improve the performance in weak Canny and MG operators were combined to improve the accuracy of the edge detecting. edge detection. The results of The proposed method was evaluated based on simulated and in vivo ultrasound images. Experimental results showed that the accuracy of the proposed method was more than 75% for different speckle noise level. The results of the edge detection can be obtained in real-time by using the proposed method.