基于多模板匹配的局部自适应区域生长法在视网膜内出血自动检测中的应用  

Algorithm of Locally Adaptive Region Growing Based on Multi-Template Matching Applied to Automated Detection of Hemorrhages

作　　者：高玮玮[1] 沈建新[1] 王玉亮[1] 梁春[1] 左晶[2] 

机构地区：[1]南京航空航天大学机电学院,江苏南京210016 [2]江苏省中医院,江苏南京210029

出　　处：《光谱学与光谱分析》2013年第2期448-453,共6页Spectroscopy and Spectral Analysis

基　　金：国家(863计划)项目(2006AA020804);中央高校基本科研业务费专项(南航NJ20120007);江苏省科技支撑计划项目(BE2010652);江苏省普通高校研究生科研创新计划项目(CXLX11_0218)资助

摘　　要：为自动检测出眼底图像中的视网膜内出血,从而构建基于眼底图像的糖尿病视网膜病变自动筛查系统,提出了基于多模板匹配的局部自适应区域生长法用以自动检测该病灶。首先,对眼底主要生理结构进行光谱特征分析,从而为不同分割目标选取合适的RGB通道;其次,利用HSV空间的亮度校正以及对比度受限自适应直方图均衡方法对眼底图像进行预处理;在此基础上利用设计好的多个模板对图像进行归一化互相关模板匹配获取该病灶候选区域;然后,从中去除视盘、血管以消除相关假阳,从而得到区域生长所需种子;最后,利用局部自适应区域生长法获取其精确轮廓,从而实现该病灶的准确检测。利用该算法对90幅不同颜色、不同亮度、不同质量、不同分辨率眼底图像进行该病灶的自动检测,实验结果表明:该算法能快速、有效地自动检测出眼底图像中的视网膜内出血,且算法稳定可靠,可满足临床需求。In order to automatically detect hemorrhages in fundus images, and develop an automated diabetic retinopathy screen-ing system, a novel algorithm named locally adaptive region growing based on multi-template matching was established and stud-led. Firstly, spectral signature of major anatomical structures in fundus was studied, so that the right channel among RGB chan-nels could be selected for different segmentation objects. Secondly, the fundus image was preprocessed by means of HSV bright-ness correction and contrast limited adaptive histogram equalization（CLAHE）.Then, seeds of region growing were founded out by removing optic disc and vessel from the resulting image of normalized cross-correlation（NCC）template matching on the previ-ous preprocessed image with several templates. Finally, locally adaptive region growing segmentation was used to find out the exact contours of hemorrhages, and the automated detection of the lesions was accomplished. The approach was tested on 90 dif- ferent resolution fundus images with variable color, brightness and quality. Results suggest that the approach could fast and ef-fectively detect hemorrhages in fundus images, and it is stable and robust. As a result, the approach can meet the clinical de-mands.

关 键 词：视网膜内出血 光谱特征 模板匹配 区域生长 自动检测 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]