Early diabetic retinopathy diagnosis based on local retinal blood vessel analysis in optical coherence tomography angiography (OCTA) images

PURPOSE This paper introduces a new computer-aided diagnosis (CAD) system for detecting early-stage diabetic retinopathy (DR) using optical coherence tomography angiography (OCTA) images. METHODS The proposed DR-CAD system is based on the analysis of new local features that describe both the appearance and retinal structure in OCTA images. It starts with a new segmentation approach that has the ability to extract the blood vessels from superficial and deep retinal OCTA maps. The high capability of our segmentation approach stems from using a joint Markov-Gibbs random field stochastic model integrating a 3D spatial statistical model with a first-order appearance model of the blood vessels. Following the segmentation step, three new local features are estimated from the segmented vessels and the foveal avascular zone (FAZ): (a) vessels density, (b) blood vessel calibre, and (c) width of the FAZ. To distinguish mild DR patients from normal cases, the estimated three features are used to train and test a support vector machine (SVM) classifier with the radial basis function (RBF) kernel. RESULTS On a cohort of 105 subjects, the presented DR-CAD system demonstrated an overall accuracy (ACC) of 94.3%, a sensitivity of 97.9%, a specificity of 87.0%, the area under the curve (AUC) of 92.4%, and a Dice similarity coefficient (DSC) of 95.8%. This in turn demonstrates the promise of the proposed CAD system as a supplemental tool for early detection of DR. CONCLUSION We developed a new DR-CAD system that is capable of diagnosing DR in its early stage. The proposed system is based on extracting three different features from the segmented OCTA images, which reflect the changes in the retinal vasculature network.

[1]  Xiaodong Wu,et al.  Multi-Surface and Multi-Field Co-Segmentation of 3-D Retinal Optical Coherence Tomography , 2014, IEEE Transactions on Medical Imaging.

[2]  Ayman El-Baz,et al.  Stochastic Modeling for Medical Image Analysis , 2015 .

[3]  Xinjian Chen,et al.  Automated segmentation of intraretinal cystoid macular edema for retinal 3D OCT images with macular hole , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[4]  S. Edward Rajan,et al.  Computerized screening of diabetic retinopathy employing blood vessel segmentation in retinal images , 2014 .

[5]  George Azzopardi,et al.  Trainable COSFIRE filters for vessel delineation with application to retinal images , 2015, Medical Image Anal..

[6]  L. Vuong,et al.  Subretinal fluid from anterior ischemic optic neuropathy demonstrated by optical coherence tomography. , 2008, Archives of ophthalmology.

[7]  Tomio Goto,et al.  An adaptive contrast enhancement using regional dynamic histogram equalization , 2012, 2012 IEEE International Conference on Consumer Electronics (ICCE).

[8]  Aruj Khurana,et al.  Quantification of Vessel Density in Retinal Optical Coherence Tomography Angiography Images Using Local Fractal Dimension. , 2016, Investigative ophthalmology & visual science.

[9]  Keshab K. Parhi,et al.  3-D localization of Diabetic Macular Edema using OCT thickness maps , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[10]  Klaus D. Tönnies Guide to Medical Image Analysis , 2012, Advances in Computer Vision and Pattern Recognition.

[11]  Ayman El-Baz,et al.  Automatic blood vessels segmentation based on different retinal maps from OCTA scans , 2017, Comput. Biol. Medicine.

[12]  Laura Strauss Guide To Medical Image Analysis Methods And Algorithms , 2016 .

[13]  Ayman El-Baz,et al.  Classification of retinal diseases based on OCT Images. , 2018, Frontiers in bioscience.

[14]  L. R. Dice Measures of the Amount of Ecologic Association Between Species , 1945 .

[15]  Yuzo Iano,et al.  Segmentation of Foveal Avascular Zone of the Retina Based on Morphological Alternating Sequential Filtering , 2015, 2015 IEEE 28th International Symposium on Computer-Based Medical Systems.

[16]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[17]  Ayman El-Baz,et al.  A computer‐aided diagnostic system for detecting diabetic retinopathy in optical coherence tomography images , 2017, Medical physics.

[18]  Jorge Oliveira,et al.  Sparse high order potentials for extending multi-surface segmentation of OCT images with drusen , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[19]  Lila Iznita Izhar,et al.  Analysis of Foveal Avascular Zone for grading of Diabetic Retinopathy , 2011 .

[20]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[21]  Gwénolé Quellec,et al.  Optimal Filter Framework for Automated, Instantaneous Detection of Lesions in Retinal Images , 2011, IEEE Transactions on Medical Imaging.

[22]  Hedi Trabelsi,et al.  Segmentation of cyctoids macular edema in optical cohenrence tomography , 2016, 2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).

[23]  Georgy L. Gimel'farb,et al.  EM Based Approximation of Empirical Distributions with Linear Combinations of Discrete Gaussians , 2007, 2007 IEEE International Conference on Image Processing.

[24]  Ahmad Reza Naghsh-Nilchi,et al.  Automatic wavelet-based retinal blood vessels segmentation and vessel diameter estimation , 2013, Biomed. Signal Process. Control..

[25]  M. Usman Akram,et al.  Multilayered thresholding-based blood vessel segmentation for screening of diabetic retinopathy , 2011, Engineering with Computers.

[26]  Farshad Tajeripour,et al.  Computerized Medical Imaging and Graphics Automated Characterization of Blood Vessels as Arteries and Veins in Retinal Images , 2022 .

[27]  Ken D. Sauer,et al.  A generalized Gaussian image model for edge-preserving MAP estimation , 1993, IEEE Trans. Image Process..

[28]  Chen Ding,et al.  Supervised segmentation of vasculature in retinal images using neural networks , 2014, 2014 International Conference on Orange Technologies.

[29]  M. Larsen,et al.  Automated detection of fundus photographic red lesions in diabetic retinopathy. , 2003, Investigative ophthalmology & visual science.

[30]  Ayman El-Baz,et al.  Automated diabetic retinopathy detection using optical coherence tomography angiography: a pilot study , 2018, British Journal of Ophthalmology.

[31]  Tien Yin Wong,et al.  A survey on computer aided diagnosis for ocular diseases , 2014, BMC Medical Informatics and Decision Making.

[32]  R. Spaide,et al.  ENHANCED DEPTH IMAGING OPTICAL COHERENCE TOMOGRAPHY OF THE CHOROID IN CENTRAL SEROUS CHORIORETINOPATHY , 2009, Retina.

[33]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[34]  Keshab K. Parhi,et al.  Automated localization of cysts in diabetic macular edema using optical coherence tomography images , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[35]  Aly A. Farag,et al.  Expectation-maximization for a linear combination of Gaussians , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[36]  M. Sonka,et al.  Retinal Imaging and Image Analysis , 2010, IEEE Reviews in Biomedical Engineering.

[37]  Xiaodong Wu,et al.  Intraretinal Layer Segmentation of Macular Optical Coherence Tomography Images Using Optimal 3-D Graph Search , 2008, IEEE Transactions on Medical Imaging.

[38]  Geoff Dougherty,et al.  Pattern Recognition and Classification , 2013, Springer New York.

[39]  Jelena Novosel,et al.  Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[40]  Chun Ding,et al.  Quantification of Vessel Density in Retinal Optical Coherence Tomography Angiography Images Using Local Fractal Dimension. , 2016, Investigative ophthalmology & visual science.

[41]  Geoff Dougherty,et al.  Pattern Recognition and Classification: An Introduction , 2012 .

[42]  Sebastian Wolf,et al.  OCT-angiography: A qualitative and quantitative comparison of 4 OCT-A devices , 2017, PloS one.

[43]  Luís Pinto,et al.  Monte Carlo simulation of diabetic macular edema changes on optical coherence tomography data , 2014, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[44]  Milan Sonka,et al.  Intra-retinal layer segmentation of 3D optical coherence tomography using coarse grained diffusion map , 2012, Medical Image Anal..

[45]  Kotagiri Ramamohanarao,et al.  An effective retinal blood vessel segmentation method using multi-scale line detection , 2013, Pattern Recognit..

[46]  Qi Yang,et al.  Automated layer segmentation of macular OCT images using dual-scale gradient information. , 2010, Optics express.

[47]  M Palta,et al.  Abnormalities of the foveal avascular zone in diabetic retinopathy. , 1984, Archives of ophthalmology.

[48]  Bunyarit Uyyanonvara,et al.  Blood vessel segmentation methodologies in retinal images - A survey , 2012, Comput. Methods Programs Biomed..

[49]  Robert N Weinreb,et al.  Optical Coherence Tomography Angiography Vessel Density in Glaucomatous Eyes with Focal Lamina Cribrosa Defects. , 2016, Ophthalmology.

[50]  Mong-Li Lee,et al.  Simultaneously Identifying All True Vessels From Segmented Retinal Images , 2013, IEEE Transactions on Biomedical Engineering.

[51]  Jayanthi Sivaswamy,et al.  Automatic glaucoma assessment from angio-OCT images , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).