基于三维限制区域生长的SD-OCT中浆NRD病变区域分割

计算机科学 ›› 2018, Vol. 45 ›› Issue (6A): 187-192.

基于三维限制区域生长的SD-OCT中浆NRD病变区域分割

何晓俊¹,吴梦麟²,范雯³,袁松涛³,陈强^1,4

南京理工大学计算机科学与工程学院南京210094¹
南京工业大学电子与信息工程学院南京211816²
南京医科大学第一附属医院江苏省人民医院眼科南京210029³
闽江学院福建省信息处理与智能控制重点实验室福州350121⁴

出版日期:2018-06-20 发布日期:2018-08-03
作者简介:何晓俊(1993-),女,硕士生,主要研究方向为图像处理,E-mail:hxthxj2017@163.com;吴梦麟(1982-),男,讲师,主要研究方向为模式识别与医学图像分析;范雯(1986-),女,讲师,主要研究方向为玻璃体视网膜疾病、眼表疾病;袁松涛(1974-),男,博士后,主要研究方向为视网膜疾病;陈强(1979-),男,教授,博士生导师,CCF高级会员,主要研究方向为模式识别、图像处理与分析,E-mail:chen2qiang@njust.edu.cn(通信作者)。
基金资助:
国家自然科学基金面上项目(61671242),中央高校基本科研业务费专项资金(30920140111004),六大人才高峰(2014-SWYY-024),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)资助

SD-OCT CSC NRD Region Segmentation Based on Region Restricted 3D Region Growing

HE Xiao-jun¹,WU Meng-lin²,FAN Wen³,YUAN Song-tao³,CHEN Qiang^1,4

School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China¹
College of Electronics and Information Engineering,Nanjing University of Technology,Nanjing 211816,China²
Dartment of Ophthalmology,The First Affiliated Hospital with Nanjing Medical University,Nanjing 210029,China³
Fujian Provincial Key Laboratory of Information Processing and Intelligent Control,Minjiang University,Fuzhou 350121,China⁴

Online:2018-06-20 Published:2018-08-03

摘要/Abstract

摘要： 中浆(CSC)病变区域的大小对于病变的诊断及研究有着关键的作用,而视网膜神经上皮层脱离(NRD)形态在中浆病变中最为普遍且病变程度最为严重,因此快速准确地分割出NRD病变区域十分重要。给出一种全自动的频域光学相干断层(SD-OCT)中浆NRD病变分割方法。首次在三维空间进行NRD病变分割,将二维图像上的病变区域分割问题转化为三维空间的体分割问题,充分利用了数据的三维结构信息,提高了分割精度。18组中浆NRD病变的SD-OCT图像的实验结果表明:该算法能够准确分割出中浆NRD病变,且平均覆盖率高达89.5%。与其他4种分割方法相比,所提方法精度最高且耗时最短,在临床应用与研究中具有极大的优势。

关键词: 频域光学相干层析图像, 三维区域生长, 视网膜神经上皮层分离, 中心性浆液性脉络膜视网膜病变, 自适应阈值

Abstract: It is important to segment neurosensory retianl detachment (NRD) of central serous chorioretinopathy (CSC) region,because the volume of CSC region plays a very important role in the diagnosis and study of CSC,while NRD is the most common and serious situation in CSC.The paper presented an automated spatial-domain optical cohe-rence tomography (SD-OCT) NRD segmentation method,which firstly segments NRD lesion in 3D space.And the segmentation of lesion in two-dimensional images is transformed into three-dimensional space segmentation problem,which makes full use of the three-dimensional structure information of data and improves the segmentation precision.The experiment results with 18 SD-OCT cubes indicate that the proposed method can segment the NRD accurately,and the average area coverage is as high as 89.5%.Compared to other four segmentation methods,the proposed algorithm achieves the highest accuracy and costs the least time,which has great advantages in clinical application and research.

Key words: 3-D region growing, Adaptive threshold, Central serous chorioretinopathy, Neurosensory retianl detachment, Spatial-domain optical coherence tomography

中图分类号:

TP391

何晓俊, 吴梦麟, 范雯, 袁松涛, 陈强. 基于三维限制区域生长的SD-OCT中浆NRD病变区域分割[J]. 计算机科学, 2018, 45(6A): 187-192. https://doi.org/

HE Xiao-jun, WU Meng-lin, FAN Wen, YUAN Song-tao, CHEN Qiang. SD-OCT CSC NRD Region Segmentation Based on Region Restricted 3D Region Growing[J]. Computer Science, 2018, 45(6A): 187-192. https://doi.org/

参考文献

[1]YU J,JIANG C,XU G.Study of subretinal exudation and consequent changes in acute Central Serous Chorioretinopathy by Optical Coherence Tomography[J].American Journal of Ophthalmology,2014,158(4):752-756.
[2]关新辉,张艳,梁勇.浅谈光学相干断层扫描对中浆病变于视力诊断中的应用价值[J].中国医药导刊,2013(11):1744-1745.
[3]HEE M R,PULIAFITO C A,WONG C,et al.Optical Cohe- rence Tomography of Central Serous Chorioretinopathy-American Journal of Ophthalmology[J].International Eye Science,2013,26(6):65-74.
[4]刘杏,凌运兰,李梅.中心性浆液性脉络膜视网膜病变的光学相干断层扫描[J].中华眼底病杂志,1999,15(3):131-134.
[5]汪难玢,徐昕,贺景波,等.119例中心性浆液性脉络膜视网膜病变的OCT图像分析[J].浙江医学,2007,29(11):1173-1174.
[6]CHEN X J,NIEMEIJER M,ZHANG L,et al.Three-Dimen- sional segmentation of fluid-associated abnormalities in retinal oct:probability constrained graph-search-graph-cut[J].IEEE Transactions on Medical Imaging,2012,31(8):1521-1531.
[7]SHI F,CHEN X,ZHAO H,et al.Automated 3-D retinal layer segmentation of macular Optical Coherence Tomography images with serous Pigment Epithelial Detachments[J].IEEE Transactions on Medical Imaging,2014,34(2):441-452.
[8]WILKINS G R,HOUGHTON O M,OLDENBURG A L.Automated segmentation of intraretinal cystoid fluid in optical cohe-rence tomography[J].IEEE Transactions on Biomedical Engineering,2012,59(4):1109-1114.
[9]DING W,YOUNG M,BOURGAULT S,et al.Automatic detection of subretinal fluid and sub-retinal pigment epithelium fluid in optical coherence tomography images[C]∥Conference:International Conference of the IEEE Engineering in Medicine & Bio-logy Society IEEE Engineering in Medicine & Biology Society Conference.2013:7388-7391.
[10]时佳佳,陈强.基于灰度和梯度的视网膜下积液分割[J].科技通报,2014(1):51-54.
[11]WU M,CHEN Q,HE X,et al.Automatic subretinal fluid segmentation of retinal SD-OCT images with Neurosensory Retinal Detachment guided by enface fundus imaging[J].IEEE Transactions on Biomedical Engineering,2017(99):1-10.
[12]XU X,LEE K,ZHANG L,et al.Stratified sampling voxel classification for segmentation of intraretinal and subretinal fluid in longitudinal clinical OCT data[J].IEEE Transactions on Medical Imaging,2015,34(7):1616-1623.
[13]SUN Z,CHEN H,SHI F,et al.An automated framework for 3D serous pigment epithelium detachment segmentation in SD-OCT images[J].Scientific Reports,2016,6(298):243-244.
[14]NOVOSEL J,WANG Z,JONG H D,et al.Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy[C]∥IEEE,International Symposium on Biomedical Imaging.IEEE,2016.
[15]WANG T,JI Z,SUN Q,et al.Label propagation and higher-order constraint-based segmentation of fluid-associated regions in retinal SD-OCT images[J].Information Sciences,2016,358(C):92-111.
[16]TOMASI C,MANDUCHI R.Bilateral filtering for gray and co- lor images[C]∥IEEE Computer Society,1998:839-846.
[17]LI K,WU X,CHEN D Z,et al.Optimal surface segmentation in volumetric images-a graph-theoretic approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(1):119-134.
[18]GARVIN M K,ABRMOFF M D,KARDON R,et al.Intrare- tinal layer segmentation of macular optical coherence tomography images using optimal 3-D graph search[J].IEEE Transactions on Medical Imaging,2008,27(10):1495-1505.
[19]BOGUNOVIC′ H,SONKA M,KWON Y H,et al.Multi-surface and multi-field co-segmentation of 3-D retinal optical coherence tomography[J].IEEE Transactions on Medical Imaging,2014,33(12):2242-2253.
[20]樊鲁杰,孙延奎,张田,等.光学相干层析视网膜体数据的三维分割[J].中国图象图形学报,2013,18(3):330-335.
[21]BOYKOV Y,KOLMOGOROV V.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J].Tissue Engineering,2005,11(12):1631-1639.
[22]牛四杰,陈强,陆圣陶,等.应用多尺度三维图搜索的SD-OCT图像层分割方法[J].计算机科学,2015,42(9):272-277.
[23]王茜,彭中,刘莉.一种基于自适应阈值的图像分割算法[J].北京理工大学学报,2003,23(4):521-524.
[24]CARASS A,LANG A,SWINGLE E K,et al.Automatic segmentation of microcystic macular edema in OCT[J].Biomedical Optics Express,2015,6(1):155-169.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed