基于PST和多尺度高斯滤波的视网膜血管的分割

为辅助眼科医生进行眼底疾病的诊断,提出了一种基于相位拉伸变换(PST)和多尺度高斯滤波的视网膜血管分割方法。首先将彩色眼底影像的绿色通道分量图进行增强预处理;然后采用不同尺度的高斯滤波器对预处理增强后的视网膜血管进行降噪处理,再结合PST边缘检测算法初步获得视网膜血管分割图;最后整合初步获得的视网膜血管分割图并进行形态学去噪,获得最终的视网膜血管分割图。通过在视网膜图像库DRIVE上进行实验,其平均准确率为93%,平均灵敏度达77%,平均特异性为95%,实验结果验证了该方法的有效性。

Retinal Vessel Segmentation Based on PST and Multi-scale Gaussian Filter

Retinal vessel segmentation is the basis of ophthalmic computer-aided diagnosis and large-scale ophthalmic disease screening systems. In order to assist ophthalmologists in the diagnosis of fundus diseases, this paper presents a retinal vessel segmentation method based on PST and multi-scale Gaussian filter. Firstly, the green channel of color fundus image is enhanced; then, Gaussian filters with different scales are used to reduce the noise of retinal vessels with different diameters after preconditioning, and combined with the gaussian filters ,the edge detection algorithm of the PST(Phase Stretch Transform) is used to obtain preliminary retinal vascular segmentation map; finally, we integrate the initial retinal vessel segmentation maps and denoise the result based on morphology to obtain the final retinal vessel segmentation map. The experiments on DRIVE retinal image database showed that the average accuracy was 93%, the average sensitivity was 77%, and the average specificity was 95%. The experimental results verify the effectiveness of the method proposed in the paper.