弥散张量成像纤维束跟踪中噪声去除方法研究

Noise elimination methods for fibre tracking in diffusion tensor imaging

对弥散张量成像(DTI)中影响纤维束跟踪效果的几种噪声去除方法进行研究。仿真结果表明:高斯平滑滤波、中值滤波和形态学最大最小值滤波对DTI中的噪声都有一定的抑制作用。高斯平滑滤波能够去除高频白噪声,引起图像边缘模糊,影响纤维束跟踪的连续性;中值滤波在去除随机噪声的同时,较好地保存了图像细节,能提高纤维束跟踪效果;最大最小值滤波能抑制较大噪声的影响,提高纤维束跟踪的连续性。此外,提出一种联合运用最大最小值滤波和中值滤波的混合滤波去噪法,该方法能更好地抑制噪声对DTI纤维束跟踪的影响,获得了令人满意的跟踪效果。

Several noise elimination approaches for fibre tracking in diffusion tensor imaging(DTI)are analyzed.The simulation results indicate that Gaussian smoothing filter,median filter,and maximum-minimum filter are able to eliminate the noise in DTI image.Gaussian smoothing filter eliminates high-frequency white noise,but causes fuzzy edges of images and affects the connectivity of DTI fibre tracking.Median filter not only eliminates random noise,but also remains valuable information,which improves the effect of DTI fibre tracking.Maximum-minimum filter inhibits the effects of significant noise and improves the connectivity of DTI fibre tracking.Herein a mixed filtering method by integrating maximum-minimum filter with median filter is proposed for image denoising.The proposed method is proved to be able to effectively reduce the effects of noise on DTI fibre tracking,achieving better DTI fibre tracking results.