基于小波变换的脑部医学Demons图像配准

非刚性配准是医学图像处理的一个重要研究方向。针对Demons衍生出的一系列经典的配准算法在医学图像应用上计算复杂、方向信息不足问题进行了研究。基于光流场模型的Demons算法依赖图像灰度梯度是图像发生变形,当缺乏梯度信息时,力不能确定,因而容易造成误差,并且该算法仅适合于单模态图像配准。为此本文提出了一种基于小波变换理论的频域Demons配准处理方法(B-Demons)。该方法利用小波变换能够对各个尺度、方向和位置实现较好定位的优势,通过高频、低频的图像变换反映出图像的特征信息。实验结果证明了算法的有效性和鲁棒性。

Demons Brain- medical image registration based on wavelet transform

Non-rigid registration is an important research direction of medical image processing. For Demons derived from a series of classic registration algorithms on the computational complexity of medical imaging applications, the direction of the problem of lack of information were studied. Demons algorithm based on optical flow field model is dependent on the image gray gradient image is deformed when the lack of gradient information, the force can not be determined, and thus likely to cause the error, and the algorithm is only suitable for single-mode image registration. Therefore, we propose a frequency-domain Demons registration processing method based on wavelet transform theory(B-Demons). The method uses the wavelet transform can realize the benefits of better positioning on each scale, orientation and location information of the image reflected characteristics by the high frequency, low frequency of image transformation. Experimental results show that the algorithm is effective and robust.