Stratified Sampling Voxel Classification for Segmentation of Intraretinal and Subretinal Fluid in Longitudinal Clinical OCT Data

被引:62
作者
Xu, Xiayu [1 ,2 ]
Lee, Kyungmoo [2 ]
Zhang, Li [2 ]
Sonka, Milan [3 ,4 ]
Abramoff, Michael D. [5 ,6 ]
机构
[1] Xi An Jiao Tong Univ, Dept Life Sci & Technol, Xian 710049, Peoples R China
[2] Univ Iowa, Dept Elect & Comp Engn, Iowa City, IA 52242 USA
[3] Univ Iowa, Dept Ophthalmol & Visual Sci, Dept Elect & Comp Engn, Iowa City, IA 52242 USA
[4] Univ Iowa, Dept Radiat Oncol, Iowa City, IA 52242 USA
[5] Univ Iowa, Dept Ophthalmol & Visual Sci, Dept Biomed Engn, Dept Elect & Comp Engn, Iowa City, IA 52242 USA
[6] VA Med Ctr, Iowa City, IA 52246 USA
基金
美国国家卫生研究院; 中国国家自然科学基金;
关键词
Age-related macular degeneration; class imbalance; intraretinal fluid; stratified sampling; subretinal fluid; OPTICAL COHERENCE TOMOGRAPHY; RETINA; IMAGES; STRATEGIES;
D O I
10.1109/TMI.2015.2408632
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Automated three-dimensional retinal fluid (named symptomatic exudate-associated derangements, SEAD) segmentation in 3D OCT volumes is of high interest in the improved management of neovascular Age Related Macular Degeneration (AMD). SEAD segmentation plays an important role in the treatment of neovascular AMD, but accurate segmentation is challenging because of the large diversity of SEAD size, location, and shape. Here a novel voxel classification based approach using a layer-dependent stratified sampling strategy was developed to address the class imbalance problem in SEAD detection. The method was validated on a set of 30 longitudinal 3D OCT scans from 10 patients who underwent anti-VEGF treatment. Two retinal specialists manually delineated all intraretinal and subretinal fluid. Leave-one-patient-out evaluation resulted in a true positive rate and true negative rate of 96% and 0.16% respectively. This method showed promise for image guided therapy of neovascular AMD treatment.
引用
收藏
页码:1616 / 1623
页数:8
相关论文
共 30 条
[1]  
Abramoff Michael D, 2010, IEEE Rev Biomed Eng, V3, P169, DOI 10.1109/RBME.2010.2084567
[2]  
Answers Corp, 2013, 4 KINDS SAMPL TECHN
[3]   An optimal algorithm for approximate nearest neighbor searching in fixed dimensions [J].
Arya, S ;
Mount, DM ;
Netanyahu, NS ;
Silverman, R ;
Wu, AY .
JOURNAL OF THE ACM, 1998, 45 (06) :891-923
[4]   Strategies for learning in class imbalance problems [J].
Barandela, R ;
Sánchez, JS ;
García, V ;
Rangel, E .
PATTERN RECOGNITION, 2003, 36 (03) :849-851
[5]   Three-Dimensional Segmentation of Fluid-Associated Abnormalities in Retinal OCT: Probability Constrained Graph-Search-Graph-Cut [J].
Chen, Xinjian ;
Niemeijer, Meindert ;
Zhang, Li ;
Lee, Kyungmoo ;
Abramoff, Michael D. ;
Sonka, Milan .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2012, 31 (08) :1521-1531
[6]  
Christopher M, 2012, RETINA, V0, P1
[7]  
Drexler W., 2001, NEW TECHNOL, V7
[8]   Delineating fluid-filled region boundaries in optical coherence tomography images of the retina [J].
Fernández, DC .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2005, 24 (08) :929-945
[9]   Optical coherence tomography: An emerging technology for biomedical imaging and optical biopsy [J].
Fujimoto, JG ;
Pitris, C ;
Boppart, SA ;
Brezinski, ME .
NEOPLASIA, 2000, 2 (1-2) :9-25
[10]  
Garcia V., 2007, 2 C ESP INF, P289