基于眼球生理结构和眼模型的眼底三维重建方法  

3D reconstruction of fundus based on anatomical structure of eyeball and eye model

作　　者：肖志涛[1] 李敏[1] 吴骏[1] 耿磊[1] 张芳[1] 温佳[1] 苏龙[2] 

机构地区：[1]天津工业大学电子与信息工程学院,天津300387 [2]天津医科大学第二医院,天津300211

出　　处：《天津工业大学学报》2016年第6期67-72,共6页Journal of Tiangong University

基　　金：天津市科技支撑计划重点项目(13ZCZDGX02100);天津市自然科学基金项目(15JCYBJC16600)

摘　　要：为将眼底的各项生理结构和病灶信息在三维空间中显示出来,更好地辅助医生诊断,提出一种基于眼球生理结构和眼模型的眼底三维重建方法.首先通过分析眼底的生理结构和眼模型,将眼球后极部近似为局部球面;然后根据眼底相机参数以及视轴长度构建局部球面模型,把眼底图像恢复为三维结构;分割眼底图像中的血管和病灶部位,利用眼底三维模型,将血管和病灶部位显示在三维空间中.实验表明,平均每幅图像处理用时1.410 1 s,重建速度快、准确度高、可重复性高.In order to show the physiological structure and lesion information of fundus in 3D space to assist diagnose, a kind of new 3D reconstruction method of fundus based on the anatomical structure of eyeball and the eye model is proposed. Firstly, the posterior pole of eyeball is approximated as the partial sphere by analyzing the anatomical structure of eyeball and the eye model. Secondly, the partial sphere is calculated according to the fundus camera parameters and the axial length of eyeball, and the 3D model of fundus is reconstructed from the fundus image. Fi-nally, vessel and lesions of the fundus image is segmented and showed in the 3D space using the 3D model of fundus. The experimental results show that the average processing time of each image is 1.410 1 s, the proposed method has high reconstruction speed, high accuracy and high reproducibility.

关 键 词：眼底图像 眼底三维重建 眼球生理结构 眼模型 局部球面模型 病灶信息 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]