基于多分辨率三维图割的NRD分割  

Multiscale 3D Graph Cut Based Neurosensory Retinal Detachment Segmentation

作　　者：唐宇珠 何晓俊 吴梦麟[2] 范雯 袁松涛 陈强[1,4] Tang Yuzhu;He Xiaojun;Wu Menglin;Fan Wen;Yuan Songtao;Chen Qiang(School of Compute Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094;College of Electronic and Information Engineering,Nanjing University of Technology,Nanjing 211816;Department of Ophthalmology,Jiangsu Province Hospital,The First Affiliated Hospital With Nanjing Medical University,Nanjing 210029;Fujian Provincial Key Laboratory of Information Processing and Intelligent Control,Minjiang University,Fuzhou 350121)

机构地区：[1]南京理工大学计算机科学与工程学院,南京210094 [2]南京工业大学电子与信息工程学院,南京211816 [3]南京医科大学第一附属医院江苏省人民医院眼科,南京210029 [4]闽江学院福建省信息处理与智能控制重点实验室,福州350121

出　　处：《计算机辅助设计与图形学学报》2018年第12期2234-2241,共8页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61671242;61701222);中央高校基本科研业务费专项资金(30920140111004);江苏省高校自然科学基金(17KJB510026);福建省信息处理与智能控制重点实验室(闽江学院)开放课题基金(MJUKF201706)

摘　　要：为了提高视网膜神经上皮层脱离自动分割的精度和效率,提出一种基于多分辨率三维图割的自动分割算法.首先通过视网膜厚度变化信息准确定位目标和背景区域,统计目标和背景的灰度分布特征,为图割算法提供先验信息;然后采用三维图割算法对4倍下采样后的频域光学相干断层扫描(SD-OCT)图像进行分割,得到粗分割结果;最后在原始分辨率图像上,对粗分割结果两侧的窄带区域进行三维图割,得到最终分割结果.在18组CirrusSD-OCT数据集上进行分割的实验结果表明,该算法的Dice相似性系数为95.07%,分割一组数据的平均时间为57 s,精度和效率均优于现有算法.In order to improve the accuracy and efficiency of NRD segmentation,we propose a fully automatic segmentation method based on multiscale 3D graph cut algorithm.Firstly,we accurately locate the target and background regions based on changes in retinal thickness,and the grayscale distribution of the target and background provides prior information for the graph cut algorithm.Then,we obtain the coarse segmentation result by performing 3D graph cut algorithm on the downsampling SD-OCT image.Finally,on the original resolution image,we use 3D graph cut algorithm on the narrow-band regions on both sides of the coarse segmentation result to obtain the final segmentation result.The results of segmentation experiments on 18 sets of Cirrus SD-OCT datasets show that the Dice coefficient of the proposed algorithm is 95.07%,and the average time for segmenting a set of data is 57 seconds.Both the accuracy and efficiency of the proposed algorithm are better than existing algorithms.

关 键 词：光学相干断层扫描技术 视网膜神经上皮层脱离 三维图割 多分辨率 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]