An exudate detection method for diagnosis risk of diabetic macular edema in retinal images using feature-based and supervised classification

AbstractThe present paper aims at presenting the methodology and first results of a detection system of risk of diabetic macular edema (DME) in fundus images. The system is based on the detection of retinal exudates (Ex), whose presence in the image is clinically used for an early diagnosis of the disease. To do so, the system applies digital image processing algorithms to the retinal image in order to obtain a set of candidate regions to be Ex, which are validated by means of feature extraction and supervised classification techniques. The diagnoses provided by the system on 1058 retinographies of 529 diabetic patients at risk of having DME show that the system can operate at a level of sensitivity comparable to that of ophthalmological specialists: it achieved 0.9000 sensitivity per patient against 0.7733, 0.9133 and 0.9000 of several specialists, where the false negatives were mild clinical cases of the disease. In addition, the level of specificity reached by the system was 0.6939, high enough to screen about 70% of the patients with no evidence of DME. These values show that the system fulfils the requirements for its possible integration into a complete diabetic retinopathy pre-screening tool for the automated management of patients within a screening programme. Graphical AbstractDiagnosis system of risk of diabetic macular edema (DME) based on exudate (Ex) detection in fundus images.

[1]  Kenneth W. Tobin,et al.  Exudate-based diabetic macular edema detection in fundus images using publicly available datasets , 2012, Medical Image Anal..

[2]  U. Rajendra Acharya,et al.  Application of higher-order spectra for automated grading of diabetic maculopathy , 2015, Medical & Biological Engineering & Computing.

[3]  Cemal Köse,et al.  Simple methods for segmentation and measurement of diabetic retinopathy lesions in retinal fundus images , 2012, Comput. Methods Programs Biomed..

[4]  José Manuel Bravo,et al.  A tool for automated diabetic retinopathy pre-screening based on retinal image computer analysis , 2017, Comput. Biol. Medicine.

[5]  José Manuel Bravo,et al.  Locating the fovea center position in digital fundus images using thresholding and feature extraction techniques , 2013, Comput. Medical Imaging Graph..

[6]  Firat Hardalaç,et al.  A new approach to optic disc detection in human retinal images using the firefly algorithm , 2015, Medical & Biological Engineering & Computing.

[7]  Chikkannan Eswaran,et al.  An automated decision-support system for non-proliferative diabetic retinopathy disease based on MAs and HAs detection , 2012, Comput. Methods Programs Biomed..

[8]  B. Klein,et al.  Overview of epidemiologic studies of diabetic retinopathy. , 2007, Ophthalmic epidemiology.

[9]  G. Quellec,et al.  Automated analysis of retinal images for detection of referable diabetic retinopathy. , 2013, JAMA ophthalmology.

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

[11]  C. Thivolet,et al.  Screening of diabetic retinopathy: effect of field number and mydriasis on sensitivity and specificity of digital fundus photography. , 2008, Diabetes & metabolism.

[12]  U. Acharya,et al.  Automatic identification of diabetic maculopathy stages using fundus images , 2009, Journal of medical engineering & technology.

[13]  Enrico Grisan,et al.  Luminosity and contrast normalization in retinal images , 2005, Medical Image Anal..

[14]  Kevin Noronha,et al.  Classification of diabetes maculopathy images using data-adaptive neuro-fuzzy inference classifier , 2015, Medical & Biological Engineering & Computing.

[15]  Roberto Hornero,et al.  Detection of Hard Exudates in Retinal Images Using a Radial Basis Function Classifier , 2009, Annals of Biomedical Engineering.

[16]  Carla Pereira,et al.  Optic disc detection in color fundus images using ant colony optimization , 2012, Medical & Biological Engineering & Computing.

[17]  J. Sahel,et al.  [Detection, monitoring and treatment of diabetic retinopathy. Recommendations of ALFEDIAM. Committee of above-mentioned experts and validated by the board of directors and scientific board of ALFEDIAM]. , 1996, Diabetes & metabolism.

[18]  Joseph M. Reinhardt,et al.  Splat Feature Classification With Application to Retinal Hemorrhage Detection in Fundus Images , 2013, IEEE Transactions on Medical Imaging.

[19]  Stanislav S. Makhanov,et al.  Automatic optic disk detection in retinal images using hybrid vessel phase portrait analysis , 2018, Medical & Biological Engineering & Computing.

[20]  J. Olson,et al.  The efficacy of automated “disease/no disease” grading for diabetic retinopathy in a systematic screening programme , 2007, British Journal of Ophthalmology.

[21]  Javier Garrido,et al.  Inter-observer Reliability and Agreement Study on Early Diagnosis of Diabetic Retinopathy and Diabetic Macular Edema Risk , 2016, IWBBIO.

[22]  Grading diabetic retinopathy from stereoscopic color fundus photographs--an extension of the modified Airlie House classification. ETDRS report number 10. Early Treatment Diabetic Retinopathy Study Research Group. , 1991, Ophthalmology.

[23]  J. Shaw,et al.  Global estimates of diabetes prevalence for 2013 and projections for 2035. , 2014, Diabetes Research and Clinical Practice.

[24]  J. Boyce,et al.  Automated detection of diabetic retinopathy in digital retinal images: a tool for diabetic retinopathy screening , 2004, Diabetic medicine : a journal of the British Diabetic Association.

[25]  P Gain,et al.  Evaluation of automated fundus photograph analysis algorithms for detecting microaneurysms, haemorrhages and exudates, and of a computer-assisted diagnostic system for grading diabetic retinopathy. , 2010, Diabetes & metabolism.

[26]  José Manuel Bravo,et al.  Obtaining optic disc center and pixel region by automatic thresholding methods on morphologically processed fundus images , 2015, Comput. Methods Programs Biomed..

[27]  Anushikha Singh,et al.  Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image , 2016, Comput. Methods Programs Biomed..

[28]  Mohammad Alshayeji,et al.  Optic disc detection in retinal fundus images using gravitational law-based edge detection , 2017, Medical & Biological Engineering & Computing.

[29]  Xavier Badia Llach,et al.  Cámara de retina no midriática: estudio de coste-efectividad en la detección temprana de la retinopatía diabética , 2003 .

[30]  Qaisar Abbas,et al.  Automatic recognition of severity level for diagnosis of diabetic retinopathy using deep visual features , 2017, Medical & Biological Engineering & Computing.

[31]  U. Rajendra Acharya,et al.  Computer-aided diabetic retinopathy detection using trace transforms on digital fundus images , 2014, Medical & Biological Engineering & Computing.

[32]  Nahed H. Solouma,et al.  Accurate detection of blood vessels improves the detection of exudates in color fundus images , 2012, Comput. Methods Programs Biomed..

[33]  J. Sahel,et al.  [Recommendations of the ALFEDIAM (French Association for the Study of Diabetes and Metabolic Diseases) for the screening and surveillance of diabetic retinopathy]. , 1997, Journal francais d'ophtalmologie.

[34]  Lila Iznita Izhar,et al.  Analysis of retinal fundus images for grading of diabetic retinopathy severity , 2011, Medical & Biological Engineering & Computing.

[35]  U. Rajendra Acharya,et al.  Computer-aided diagnosis of diabetic retinopathy: A review , 2013, Comput. Biol. Medicine.

[36]  Michael H. Goldbaum,et al.  Luminosity and contrast normalization in color retinal images based on standard reference image , 2016, SPIE Medical Imaging.

[37]  Sameh A. Salem,et al.  Segmentation of retinal blood vessels using a novel clustering algorithm (RACAL) with a partial supervision strategy , 2007, 2006 14th European Signal Processing Conference.

[38]  J. Valentin.  Annex E , 2006 .

[39]  Baihua Li,et al.  Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: A review , 2013, Comput. Medical Imaging Graph..

[40]  Jamshid Dehmeshki,et al.  Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification , 2014, Comput. Methods Programs Biomed..

[41]  Malay Kishore Dutta,et al.  An adaptive threshold based image processing technique for improved glaucoma detection and classification , 2015, Comput. Methods Programs Biomed..

[42]  Peter F. Sharp,et al.  Evaluation of a System for Automatic Detection of Diabetic Retinopathy From Color Fundus Photographs in a Large Population of Patients With Diabetes , 2008, Diabetes Care.

[43]  Bram van Ginneken,et al.  Information Fusion for Diabetic Retinopathy CAD in Digital Color Fundus Photographs , 2009, IEEE Transactions on Medical Imaging.