Application of different imaging modalities for diagnosis of Diabetic Macular Edema: A review. (1st November 2015)

• Record Type: Journal Article
• Authors: Mookiah, Muthu Rama Krishnan; Acharya, U. Rajendra; Fujita, Hamido; Tan, Jen Hong; Chua, Chua Kuang; Bhandary, Sulatha V.; Laude, Augustinus; Tong, Louis
• Is Part Of: Computers in biology and medicine. Volume 66(2015)
• Page Start: 295
• Page End: 315
• Publication Date: 2015-11-01
• Subjects: DM Diabetes Mellitus -- DR Diabetic Retinopathy -- NPDR Non-Proliferative Diabetic Retinopathy -- PDR Proliferative Diabetic Retinopathy -- ME Macular Edema -- MA Microaneurysms -- HA Haemorrhages -- CWS Cotton Wool Spots -- VB Venous Beading -- NV Neovascularization -- DME Diabetic Macular Edema -- ETDRS Early Treatment Diabetic Retinopathy Study -- CSME Clinically Significant Macular Edema -- NCSME Non-Clinically Significant Macular Edema -- FA Fluorescein Angiography -- OCT Optical Coherence Tomography -- RGB Red Green Blue -- OD Optic Disk -- ON Optic Nerve -- SVD Singular Value Decomposition -- STARE STructured Analysis of the Retina -- k-NN k-Nearest Neighbour algorithm -- DRIVE Digital Retinal Images for Vessel Extraction -- MESSIDOR Méthodes ďEvaluation de Systèmes de Segmentation et ďIndexation Dédiées à ľOphtalmologie Rétinienne -- GMM Gaussian Mixture Model -- DIARETDB0 DIAbetic RETinopathy DataBase Calibration level 0 -- DIARETDB1 DIAbetic RETinopathy DataBase Calibration level 1 -- HE Hard Exudates -- FCM Fuzzy C-Means -- NN Neural Network -- GA Genetic Algorithm -- FLDA Fishers linear discriminant analysis -- SVM Support Vector Machine -- HEI-MED Hamilton Eye Institute Macular Edema Dataset -- CAD Computer Aided Diagnosis -- FAR Foveal Avascular Region -- AUC Area Under receiver operator characteristics Curve -- GDD Gaussian Data Description -- PCADD Principal Component Analysis Data Description -- FD Fractal Dimension -- LME Laws Mask Energy -- LBP Local Binary Pattern -- FS Fourier Spectrum -- GW Gabor Wavelet -- AMD Age-related Macular Degeneration -- CLAHE Contrast Limited Adaptive Histogram Equalization -- RTA Retinal Thickness Analyser -- RTM Retinal Thickness Map -- SD Standard Deviation -- SRD Serous Retinal Detachment -- RT Retinal Thickness -- CMT Central Macular Thickness -- DWT Discrete Wavelet Transform -- GLCM Grey Level Co-occurrence Matrix -- HMA Haemorrhages with or without microaneurysms -- HD High-Definition -- GCC Ganglion Cell Complex -- FD Fourier Domain -- CRVO Central Retinal Vein Occlusion -- PPV Positive Predictive Value -- PS Polarization Sensitive -- VA Visual Acuity -- FAZ Foveal Avascular Zone -- RNFL Retinal Nerve Fiber Layer -- CME Cystoid Macular Edema -- GCL Ganglion Cell Layer -- UTHSC-SA University of Texas Health Science Center in San Antonio -- AM Amplitude Modulation -- FM Frequency Modulation -- IA Instantaneous Amplitude -- IF Instantaneous Frequency -- DT-CWT Dual Tree Complex Wavelet Transform -- KLD Kull-back Leibler Divergence -- ONL Outer Nuclear Layer -- ARIA Automated Retinal Image Analysis -- EHD Edge Histogram Descriptor -- PSO Particle Swarm Optimization -- HRF High Resolution Fundus -- HOS Higher Order Spectra -- NB Naive Bayes -- DD Disc Diameter -- CNV Choroidal Neovascularization -- CDR Cup-to-Disc Ratio -- ANOVA Analysis of variance -- CI Confidence Interval -- ANFIS Adaptive Neuro-Fuzzy Inference System -- FAF Fundus Autofluorescence; Diabetic Macular Edema -- Fundus imaging -- Fluorescein Angiography -- Biomicroscopy -- Optical Coherence Tomography -- Computer-aided diagnosis; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2015.09.012
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Diabetic Macular Edema (DME) is caused by accumulation of extracellular fluid from hyperpermeable capillaries within the macula. DME is one of the leading causes of blindness among Diabetes Mellitus (DM) patients. Early detection followed by laser photocoagulation can save the visual loss. This review discusses various imaging modalities viz. biomicroscopy, Fluorescein Angiography (FA), Optical Coherence Tomography (OCT) and colour fundus photographs used for diagnosis of DME. Various automated DME grading systems using retinal fundus images, associated retinal image processing techniques for fovea, exudate detection and segmentation are presented. We have also compared various imaging modalities and automated screening methods used for DME grading. The reviewed literature indicates that FA and OCT identify DME related changes accurately. FA is an invasive method, which uses fluorescein dye, and OCT is an expensive imaging method compared to fundus photographs. Moreover, using fundus images DME can be identified and automated. DME grading algorithms can be implemented for telescreening. Hence, fundus imaging based DME grading is more suitable and affordable method compared to biomicroscopy, FA, and OCT modalities. Abstract : Highlights: Imaging modalities used for diagnosis of Diabetic Macular Edema (DME) are described. Computer-based detection of salient features of DME are presented. Automated grading of DME using fundus images is discussed in detail.