Automatic Detection of Exudates in Digital Color Fundus Images Using Superpixel Multi-Feature Classification

Exudates can be regarded as one of the most prevalent clinical signs of diabetic retinopathy, and the detection of exudates has important clinical significance in diabetic retinopathy diagnosis. In this paper, a novel approach named superpixel multi-feature classification for the automatic detection of exudates is developed. First, an entire image is segmented into a series of superpixels considered as candidates. Then, a total of 20 features, including 19 multi-channel intensity features and a novel contextual feature, are proposed for characterizing each candidate. A supervised multi-variable classification algorithm is also introduced to distinguish the true exudates from the spurious candidates. Finally, a novel optic disc detection technique is designed to further improve the performance of classification accuracy. Extensive experiments are carried out on two publicly available online databases, DiaretDB1, and e-ophtha EX. Compared with other state-of-the-art approaches, the experimental results show the advantages and effectiveness of the proposed approach.

[1]  Jacques Wainer,et al.  Points of Interest and Visual Dictionaries for Automatic Retinal Lesion Detection , 2012, IEEE Transactions on Biomedical Engineering.

[2]  H. Kälviäinen,et al.  DIARETDB 1 diabetic retinopathy database and evaluation protocol , 2007 .

[3]  Bálint Antal,et al.  Automatic exudate detection with improved Naïve-bayes classifier , 2012, 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS).

[4]  Sharib Ali,et al.  Statistical atlas based exudate segmentation , 2013, Comput. Medical Imaging Graph..

[5]  Gwénolé Quellec,et al.  Exudate detection in color retinal images for mass screening of diabetic retinopathy , 2014, Medical Image Anal..

[6]  Kenneth W. Tobin,et al.  Automatic retina exudates segmentation without a manually labelled training set , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[7]  Jacob Scharcanski,et al.  A coarse-to-fine strategy for automatically detecting exudates in color eye fundus images , 2010, Comput. Medical Imaging Graph..

[8]  Ming Chung Chou,et al.  Automated detection of fovea in fundus images based on vessel-free zone and adaptive Gaussian template , 2014, Comput. Methods Programs Biomed..

[9]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[10]  András Hajdu,et al.  Automatic exudate detection by fusing multiple active contours and regionwise classification , 2014, Comput. Biol. Medicine.

[11]  Ihsan ul Haq,et al.  Referral system for hard exudates in eye fundus , 2015, Comput. Biol. Medicine.

[12]  Meindert Niemeijer.  Automatic Detection of Diabetic Retinopathy in Digital Fundus Photographs , 2006 .

[13]  Huiqi Li,et al.  Automated feature extraction in color retinal images by a model based approach , 2004, IEEE Transactions on Biomedical Engineering.

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

[15]  Manuel João Oliveira Ferreira,et al.  Exudate segmentation in fundus images using an ant colony optimization approach , 2015, Inf. Sci..

[16]  Anam Tariq,et al.  Automated detection of exudates in colored retinal images for diagnosis of diabetic retinopathy. , 2012, Applied optics.

[17]  Jitendra Malik,et al.  Learning a classification model for segmentation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[18]  S. Kumar,et al.  Automated lesion detectors in retinal fundus images , 2015, Comput. Biol. Medicine.

[19]  Roberto Hornero,et al.  A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis. , 2008, Medical engineering & physics.

[20]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[21]  Paria Mehrani,et al.  Superpixels and Supervoxels in an Energy Optimization Framework , 2010, ECCV.

[22]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[23]  C. Sinthanayothin,et al.  Automated detection of diabetic retinopathy on digital fundus images , 2002, Diabetic medicine : a journal of the British Diabetic Association.

[24]  Stefano Soatto,et al.  Quick Shift and Kernel Methods for Mode Seeking , 2008, ECCV.

[25]  Desire Sidibé,et al.  Discrimination of retinal images containing bright lesions using sparse coded features and SVM , 2015, Comput. Biol. Medicine.

[26]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[28]  Alireza Osareh,et al.  A Computational-Intelligence-Based Approach for Detection of Exudates in Diabetic Retinopathy Images , 2009, IEEE Transactions on Information Technology in Biomedicine.

[29]  Krishnamoorthy Sivakumar,et al.  Morphological Operators for Image Sequences , 1995, Comput. Vis. Image Underst..

[30]  Vineeta Das,et al.  Tsallis entropy and sparse reconstructive dictionary learning for exudate detection in diabetic retinopathy , 2017, Journal of medical imaging.

[31]  F. Mériaudeau,et al.  Bright retinal lesions detection using color fundus images containing reflective features , 2009 .

[32]  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.