Analysis of foveal avascular zone for grading of diabetic retinopathy severity based on curvelet transform

被引:30
作者
Alipour, Shirin Hajeb Mohammad [1 ]
Rabbani, Hossein [1 ]
Akhlaghi, Mohammadreza [2 ]
Dehnavi, Alireza Mehri
Javanmard, Shaghayegh Haghjooy [3 ]
机构
[1] Isfahan Univ Med Sci, Dept Biomed Engn, Med Image & Signal Proc Res Ctr, Esfahan, Iran
[2] Isfahan Univ Med Sci, Dept Ophthalmol, Sch Med, Esfahan, Iran
[3] Isfahan Univ Med Sci, Physiol Res Ctr, Esfahan, Iran
关键词
Diabetic Retinopathy (DR); Foveal Avascular Zone (FAZ); Digital Curvelet Transform (DCUT); Color Fundus Image; AUTOMATED SEGMENTATION; IDENTIFICATION; MICROCIRCULATION; IMAGES;
D O I
10.1007/s00417-012-2093-6
中图分类号
R77 [眼科学];
学科分类号
100212 ;
摘要
Introduction Diabetes disturbs many parts of the body. One of the most common and serious complications of this disease is Diabetic Retinopathy (DR). In this process, blood vessels of the retina are damaged and leak into the retina. In later stages, DR affects the fovea. In these cases, the shape and size of the Foveal Avascular Zone (FAZ), which is responsible for central vision, can become abnormal and contribute to loss of vision. Methods In this paper, appropriate features are extracted from the FAZ by means of Digital Curvelet Transform (DCUT) and used to grade of retina images into normal and abnormal classes. For this reason, DCUT is applied on enhanced color fundus images and its coefficients are modified to highlight vessels and the optic disc (OD). Through the use of this information about the anatomical location of the FAZ related to the OD and detected end points of segmented vessels, the FAZ is extracted. Then, the area and regularity of the extracted FAZ is determined and used for DR grading. Results Our method was tested on a database including 45 normal and 30 abnormal color fundus images, and showed sensitivity of 93 % for DR grading and specificity of 86 % for distinguishing between normal and abnormal cases. Conclusions This technique showed high reproducibility in characterizing the size and contour of the FAZ in diabetic maculopathy, thus it has the potential to serve as a powerful tool in the automated assessment and grading of images in a routine clinical setting.
引用
收藏
页码:1607 / 1614
页数:8
相关论文
共 35 条
[1]   PERIFOVEAL MICROCIRCULATION WITH NON-INSULIN-DEPENDENT DIABETES-MELLITUS [J].
AREND, O ;
WOLF, S ;
REMKY, A ;
SPONSEL, WE ;
HARRIS, A ;
BERTRAM, B ;
REIM, M .
GRAEFES ARCHIVE FOR CLINICAL AND EXPERIMENTAL OPHTHALMOLOGY, 1994, 232 (04) :225-231
[2]  
BRADLEY A, 1992, OPHTHAL PHYSL OPT, V12, P18, DOI 10.1111/j.1475-1313.1992.tb00248.x
[3]  
BRESNICK GH, 1984, ARCH OPHTHALMOL-CHIC, V102, P1286
[4]   Fast discrete curvelet transforms [J].
Candes, Emmanuel ;
Demanet, Laurent ;
Donoho, David ;
Ying, Lexing .
MULTISCALE MODELING & SIMULATION, 2006, 5 (03) :861-899
[5]   Diabetic retinopathy [J].
Cheung, Ning ;
Mitchell, Paul ;
Wong, Tien Yin .
LANCET, 2010, 376 (9735) :124-136
[6]   INDEPENDENT COMPONENT ANALYSIS, A NEW CONCEPT [J].
COMON, P .
SIGNAL PROCESSING, 1994, 36 (03) :287-314
[7]   Foveal avascular zone in diabetic retinopathy:: quantitative vs qualitative assessment [J].
Conrath, J ;
Giorgi, R ;
Raccah, D ;
Ridings, B .
EYE, 2005, 19 (03) :322-326
[8]  
Esmaeili M., 2009, P 9 INT C INF TECHN, P1
[9]   EXTRACTION OF RETINAL BLOOD VESSELS BY CURVELET TRANSFORM [J].
Esmaeili, Mahdad ;
Rabbani, Hossein ;
Mehri, Alireza ;
Dehghani, Alireza .
2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, :3353-+
[10]   Determination of foveal avascular zone in diabetic retinopathy digital fundus images [J].
Fadzil, M. H. Ahmad ;
Izhar, Lila Iznita ;
Nugroho, Hanung Adi .
COMPUTERS IN BIOLOGY AND MEDICINE, 2010, 40 (07) :657-664