Discrimination of exudates and non exudates pixels in fundus images and classification of color autocorrelogram features using multilayer perceptron and support vector machine

Fundus images provide an opportunity for early detection of diabetes. Generally, retina fundus images of diabetic patients exhibit exudates, which are lesions indicative of Diabetic Retinopathy (DR). Computational tools have the potential to assist medical practitioners in early screening of the disease. The experiment consists of two parts: 1) detection of exudates in the fundus image (using the Multilayer Perceptron (MLP1) and Support Vector Machine (SVM1)), followed by 2) removal of exudates detected in step (1), feature representation using Color Autocorrelogram (CAC) and classification using another set of classifiers (MLP2 and SVM2). Experimental results on the MESSIDOR dataset suggest that the method has the potential to be used for early indication of DR.

[1]  Rohilah Sahak,et al.  Optimization of Principal Component Analysis and Support Vector Machine for the Recognition of Infant Cry with Asphyxia , 2013 .

[2]  K. Udayakumar,et al.  Automatic Estimation of Vision Degradation from Color Fundus Image , 2015 .

[3]  Levente Kovács,et al.  Analysis of a novel time-delay diabetes model , 2015, 2015 European Control Conference (ECC).

[4]  U. Rajendra Acharya,et al.  Algorithms for the Automated Detection of Diabetic Retinopathy Using Digital Fundus Images: A Review , 2012, Journal of Medical Systems.

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

[6]  Jing Huang,et al.  Color-Spatial Image Indexing and Applications , 1998 .

[7]  K KadeMahesh,et al.  Review on Fundus Image Acquisition Techniques with Data base Reference to Retinal Abnormalities in Diabetic Retinopathy , 2013 .

[8]  Meenakshi Garg,et al.  CBIR Approach Based On Combined HSV, Auto Correlogram, Color Moments and Gabor Wavelet , 2014 .

[9]  Asha Gowda Karegowda,et al.  Exudates Detection in Retinal Images using Back Propagation Neural Network , 2011 .

[10]  Baoxin Li,et al.  Classification of diabetic retinopathy images using multi-class multiple-instance learning based on color correlogram features , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  Sungbin Lim,et al.  Automatic classification of diabetic macular edema in digital fundus images , 2011, 2011 IEEE Colloquium on Humanities, Science and Engineering.

[12]  Hossein Rabbani,et al.  Automatic detection of exudates and optic disk in retinal images using curvelet transform , 2012 .

[13]  N. M. Tahir,et al.  Automated Optic Disc removal in fundus images using iterative heuristics and morphological operations , 2013, 2013 IEEE Conference on Systems, Process & Control (ICSPC).

[14]  Shyamala C. Doraisamy,et al.  Multi-resolution Joint Auto Correlograms: Determining the distance function , 2012, 2012 International Conference on Information Retrieval & Knowledge Management.

[15]  C. M. Lim,et al.  Computer-based detection of diabetes retinopathy stages using digital fundus images , 2009, Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine.

[16]  Saifur Rahaman,et al.  Diabetes diagnosis decision support system based on symptoms, signs and risk factor using special computational algorithm by rule base , 2012, 2012 15th International Conference on Computer and Information Technology (ICCIT).

[17]  W. Sae-Tang,et al.  Exudates detection in fundus image using non-uniform illumination background subtraction , 2010, TENCON 2010 - 2010 IEEE Region 10 Conference.

[18]  Husniza Husni,et al.  Efficient, Compact, and Dominant Color Correlogram Descriptors for Content-based Image Retrieval , 2013 .

[19]  V. Vijayakumari,et al.  Detection of exudates and feature extraction of retinal images using fuzzy clustering method , 2013 .

[20]  K. Prasad,et al.  Automatic Detection of Hard Exudates in Diabetic Retinopathy Using Morphological Segmentation and Fuzzy Logic , 2008 .

[21]  U. Acharya,et al.  Assessment of retinopathy severity using digital fundus images , 2011, 2011 1st Middle East Conference on Biomedical Engineering.

[23]  Rangaraj M. Rangayyan,et al.  A graphical user interface for measurement of temporal arcade angles in fundus images of the retina , 2012, 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).

[24]  Dipika Gadriye,et al.  Neural Network Based Method for the Diagnosis of Diabetic Retinopathy , 2014, 2014 International Conference on Computational Intelligence and Communication Networks.

[25]  Ravinda G. N. Meegama,et al.  Detection of hard exudates from diabetic retinopathy images using fuzzy logic , 2013, IET Image Process..

[26]  Anushikha Singh,et al.  Automatic exudates detection in fundus image using intensity thresholding and morphology , 2015, 2015 7th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT).

[27]  Vesna Zeljkovic,et al.  Classification algorithm of retina images of diabetic patients based on exudates detection , 2012, 2012 International Conference on High Performance Computing & Simulation (HPCS).

[28]  K. Y. E. Aryanto,et al.  Branches filtering approach to extract retinal blood vessels in fundus image , 2009, International Conference on Instrumentation, Communication, Information Technology, and Biomedical Engineering 2009.

[29]  Siti Zaiton Mohd Hashim,et al.  Diabetic retinopathy lesion detection using region-based approach , 2014, 2014 8th. Malaysian Software Engineering Conference (MySEC).

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

[31]  Jing Huang,et al.  Image indexing using color correlograms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[32]  Aliaa A. A. Youssif,et al.  Optic Disc Detection From Normalized Digital Fundus Images by Means of a Vessels' Direction Matched Filter , 2008, IEEE Transactions on Medical Imaging.

[33]  Muhammad Younus Javed,et al.  Background and Noise Extraction from Colored Retinal Images , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.