Brain vascular image enhancement based on gradient adjust with split bregman

	Brain vascular image enhancement based on gradient adjust with split bregman
	Liang Xiao(梁潇); Dong Di; Hui Hui; Zhang Liwen; Fang Mengjie; Tian Jie
	2016-04-06
会议名称	Spie Bios
会议录名称	SPIE Proceedings
会议日期	2016-2-13
会议地点	San Francisco, California, United States
摘要	Light Sheet Microscopy is a high-resolution fluorescence microscopic technique which enables to observe the mouse brain vascular network clearly with immunostaining. However, micro-vessels are stained with few fluorescence antibodies and their signals are much weaker than large vessels, which make micro-vessels unclear in LSM images. In this work, we developed a vascular image enhancement method to enhance micro-vessel details which should be useful for vessel statistics analysis. Since gradient describes the edge information of the vessel, the main idea of our method is to increase the gradient values of the enhanced image to improve the micro-vessels contrast. Our method contained two steps: 1) calculate the gradient image of LSM image, and then amplify high gradient values of the original image to enhance the vessel edge and suppress low gradient values to remove noises. Then we formulated a new L1-norm regularization optimization problem to find an image with the expected gradient while keeping the main structure information of the original image. 2) The split bregman iteration method was used to deal with the L1-norm regularization problem and generate the final enhanced image. The main advantage of the split bregman method is that it has both fast convergence and low memory cost. In order to verify the effectiveness of our method, we applied our method to a series of mouse brain vascular images acquired from a commercial LSM system in our lab. The experimental results showed that our method could greatly enhance micro-vessel edges which were unclear in the original images.
关键词	Brain Vascular Image Enhancement Light Sheet Microscopy Split Bregman Algorithm Gradient Image Adjust L1-regularization
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11836
专题	中国科学院分子影像重点实验室
通讯作者	Tian Jie
作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Liang Xiao,Dong Di,Hui Hui,et al. Brain vascular image enhancement based on gradient adjust with split bregman[C],2016.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Brain vascular image（214KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载