中文摘要：

为了在噪声环境下尽量多地检测出MRI（magnetic resonance imaging）图像的边缘细节，以满足医学临床诊断的特殊需求，提出一种基于形态学的医学图像自适应边缘检测算法。根据医学磁共振图像噪声的特点构造了一种基于形态学滤波特性的边缘算子，使用多方向结构元素实现了边缘的精确检测，并根据图像的灰度特征自适应地调整各方向结构元素检测结果的权值，最后合理地调整结构元素的尺寸大小。仿真实验结果表明，与经典微分边缘算子及常用形态学算法相比，该算法不仅具有很强的抗噪性能，而且能更有效地提取图像中不同方向的边缘信息。

英文摘要：

To meet the special needs of clinical diagnosis, extracting more edge details of magnetic resonance imaging （MRI） image in noise jamming situation is required. An adaptive edge detection algorithm of medical image based on morphology is proposed in this paper. The algorithm structures an edge detection operator based on morphological filtering, uses multi-direction structure elements to detect edge information accurately, adaptively adjusts the weights of different structure elements. And finally, the size of the structure is reasonably adjusted. The results of simulation demonstrate that the adaptive edge detection algorithm gets better effect than classical differential operator and common morphological methods. The theory proposed suppresses the interference of noise effectively, performs better in extracting the edge information of different directions.