融合模糊连通图和区域生长的MRI脑组织图像分割算法

An Algorithm for MRI Brain Image Segmentation Based on Region Growing and Fuzzy Connective Map

针对磁共振脑组织图像中存在灰度不均匀,不利于分割的问题,提出了一种应用模糊连通图和区域生长的MRI(Magnetic Resonance Imaging)脑组织图像分割算法。首先用大津法对脑组织进行粗分割,得到脑白质部分的大致轮廓,。然后计算粗分割结构的中心点,根据中心点得到图像的模糊连通图。最后用区域生长算法对模糊连通图中的脑白质进行更精确的分割。试验结果表明,此方法能够精确的得到脑白质轮廓的边缘,并且大大降低了区域生长种子点位置和阈值选取对分割结果的影响。

In order to solve the problem that Magnetic resonance brain tissue image grayscale uneven and not easy to segment. This paper presents an efficient algorithm for brain segmentation in MRI using region growing on fuzzy connective map. At first, using OTSU method to derive the foreground region, get the alba part of the outline, Secondly searching the center point of the alba part, according to the center of the image to get the fuzzy connected graph. Lastly, the region growing algorithm is applied on the fuzzy connectivity map to get edges of inner component. Experimental results show that the proposed method can detect the edge of alba, and greatly reduced the affect that the seed position and threshold value on the result of segmentation.