Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Deep Learning and Image Augmentation

Diabetic retinopathy is a significant complication of diabetes, produced by high blood sugar level, which causes damage to the retina. Effective diabetic retinopathy screening is required because diabetic retinopathy does not show any symptoms in the initial stages, and can cause blindness if it is not diagnosed and treated promptly. This paper presents a novel diabetic retinopathy automatic detection in retinal images by implementing efficient image processing and deep learning techniques. Besides diabetic retinopathy detection, the developed system integrates a novel detection of maculopathy into one detection system. Maculopathy is the damage to the macula, the eye part that is responsible for central vision. Therefore, the combined detection of diabetic retinopathy and maculopathy is essential for an effective screening of diabetic retinopathy. The paper investigates the capability of image pre-processing techniques based on data augmentation as well as deep learning for diabetic retinopathy and maculopathy detection. Computer-assisted clinical decision-making is inevitably transforming the diabetic retinopathy detection and management today, which is crucial for clinicians and patients alike. Therefore, a high degree of accuracy, with which computer algorithms can detect the diabetic retinopathy and maculopathy, is absolutely necessary.

[1]  Daniel Rubin,et al.  Retinal Lesion Detection With Deep Learning Using Image Patches , 2018, Investigative ophthalmology & visual science.

[2]  Roy Taylor,et al.  Comprar Handbook Of Retinal Screening In Diabetes. Diagnosis And Management 2nd Ed. | Roy Taylor | 9780470658499 | Wiley , 2012 .

[3]  P. Aruna,et al.  Image Analysis Technique for Detecting Diapetic Retinopathy , 2013 .

[4]  M. Usman Akram,et al.  Automated Detection and Grading of Diabetic Maculopathy in Digital Retinal Images , 2013, Journal of Digital Imaging.

[5]  Andreas Holzinger,et al.  Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Fuzzy Image Processing , 2015, BIH.

[6]  Adarsh Punnolil,et al.  A novel approach for diagnosis and severity grading of diabetic maculopathy , 2013, 2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[7]  Andrew Hunter,et al.  Automated diagnosis of referable maculopathy in diabetic retinopathy screening , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[8]  Asoke K. Nandi,et al.  Automated localisation of optic disk and fovea in retinal fundus images , 2008, 2008 16th European Signal Processing Conference.

[9]  E. Ai.  Current management of diabetic retinopathy. , 1992, The Western journal of medicine.

[10]  M. Usman Akram,et al.  Automated system for macula detection in digital retinal images , 2011, 2011 International Conference on Information and Communication Technologies.

[11]  U. Rajendra Acharya,et al.  Automated segmentation of exudates, haemorrhages, microaneurysms using single convolutional neural network , 2017, Inf. Sci..

[12]  U. Rajendra Acharya,et al.  Ensemble selection for feature-based classification of diabetic maculopathy images , 2013, Comput. Biol. Medicine.

[13]  Lin Li,et al.  A Deep Learning Method for Microaneurysm Detection in Fundus Images , 2016, 2016 IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE).

[14]  Somshubra Majumdar,et al.  Microaneurysm detection using deep learning and interleaved freezing , 2018, Medical Imaging.

[15]  A. Rakhlin.  Diabetic Retinopathy detection through integration of Deep Learning classification framework , 2017 .

[16]  P. C. Siddalingaswamy,et al.  Automatic grading of diabetic maculopathy severity levels , 2010, 2010 International Conference on Systems in Medicine and Biology.

[17]  Kazuhiko Hamamoto,et al.  Automated Diabetic Retinopathy Screening System Using Hybrid Simulated Annealing and Ensemble Bagging Classifier , 2018, Applied Sciences.

[18]  Haibo Mi,et al.  Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image , 2017, Molecules.

[19]  Lars Ailo Bongo,et al.  Reproduction study using public data of: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs , 2018, PloS one.

[20]  Muhammad Younus Javed,et al.  Automated detection of exudates and macula for grading of diabetic macular edema , 2014, Comput. Methods Programs Biomed..

[21]  Kuntal Ghosh,et al.  Automatic detection and classification of diabetic retinopathy stages using CNN , 2017, 2017 4th International Conference on Signal Processing and Integrated Networks (SPIN).

[22]  Vasile Palade,et al.  Automatic Detection of Microaneurysms for Diabetic Retinopathy Screening Using Fuzzy Image Processing , 2015, EANN.

[23]  Freddy Lécué,et al.  Explainable AI: The New 42? , 2018, CD-MAKE.

[24]  Mrinal Haloi,et al.  Improved Microaneurysm Detection using Deep Neural Networks , 2015, ArXiv.

[25]  Vasile Palade,et al.  Automatic Screening and Classification of Diabetic Retinopathy Fundus Images , 2014, EANN.

[26]  Bin Sheng,et al.  Clinical Report Guided Retinal Microaneurysm Detection With Multi-Sieving Deep Learning , 2018, IEEE Transactions on Medical Imaging.

[27]  Darvin Yi,et al.  Automated Detection of Diabetic Retinopathy using Deep Learning , 2018, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[28]  Wataru Sunayama,et al.  Automatic microaneurysms detection on retinal images using deep convolution neural network , 2018, 2018 International Workshop on Advanced Image Technology (IWAIT).

[29]  P. Aruna,et al.  SVM and Neural Network based Diagnosis of Diabetic Retinopathy , 2012 .

[30]  G. S. Annie Grace Vimala,et al.  DETECTION OF DIABETIC MACULOPATHY IN HUMAN RETINAL IMAGES USING MORPHOLOGICAL OPERATIONS , 2014 .

[31]  Vasile Palade,et al.  Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing , 2016, Brain Informatics.

[32]  Frans Coenen,et al.  Convolutional Neural Networks for Diabetic Retinopathy , 2016, MIUA.

[33]  Ali Shokoufandeh,et al.  Neural Networks with Manifold Learning for Diabetic Retinopathy Detection , 2016, ArXiv.

[34]  U. Rajendra Acharya,et al.  Evolutionary algorithm based classifier parameter tuning for automatic diabetic retinopathy grading: A hybrid feature extraction approach , 2013, Knowl. Based Syst..

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

[36]  Roy Taylor,et al.  Handbook of Retinal Screening in Diabetes: Diagnosis and Management , 2012 .

[37]  Kurt Faber,et al.  Rational Engineering of a Flavoprotein Oxidase for Improved Direct Oxidation of Alcohols to Carboxylic Acids , 2017, Molecules.

[38]  Varghese Paul,et al.  A Novel Approach to the Detection of Macula in Human Retinal Imagery , 2013, SiPS 2013.

[39]  András Hajdu,et al.  Fusion of Deep Convolutional Neural Networks for Microaneurysm Detection in Color Fundus Images , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).