基于空频结合的图像增强的脑肿瘤分割

针对脑部核磁共振图像中含有噪音、对比度低及肿瘤边界不连续模糊等造成肿瘤难以准确分割的问题,提出了一种基于空频域图像增强的脑肿瘤分割算法.首先,采用空频域相结合的增强方法对图像进行增强处理.该方法利用基于邻域的方法,结合了空间域增强算法与基于方向滤波器组的频率域增强算法,具有它们优点的同时,克服了前者导致的图像细节模糊的缺陷及后者带来的对比度降低的缺陷.然后,利用液体向量流的分割方法,对增强后的图像进行分割,得到脑肿瘤区域.实验结果表明,本文的增强方法在增强肿瘤边界特征的同时改善了图像的对比度和清晰度,提高了脑肿瘤分割的准确性.

Brain Tumor Segmentation Based on Spatial-frequency Domain Image Enhancement

In view of the problems that the target border always appears too fuzzy to be detected, a novel method of brain tumor segmentation is proposed based on spatial frequency domain image enhancement. The method is composed of the spatial and frequency domain enhancing process and the detecting process. In the enhancing process, the directional filter band, neighborhood and histogram equalization are combined to overcome the defect of contrast reduction caused by directional filter and the defect of details vagueness caused by histogram equalization. Then in the detecting process, a method of image segmentation is applied to find the area of the brain tumor. The experiment results show that the enhancing process strengthens the features of tumor greatly, and improves the contrast and definition of the image.