FFT based detection of Diabetic Retinopathy in Fundus Retinal Images

We presented neural network based classifier for diabetic retinopathy detection in fundus images. The Multi Layer Perception Neural Network (MLPNN) based classifier is used to categorize fundus retinal images as normal and abnormal. Feature vector is composed of transform domain features and different statistical parameters of fundus retinal images. 64-point Fast Fourier Transform (FFT) is used as transform domain feature and Entropy, mean, standard deviation, average, Euler number, contrast, correlation, energy and homogeneity are used as statistical parameters. This feature vector is used as input to MLPNN based classifier. The classifier performance is calculated on DIARETDB0 database. The % classification accuracy on train and CV data sets is 99.48% and 100 respectively.

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  Frank Rosenblatt,et al.  PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS , 1963 .

[3]  C. V. D. Malsburg,et al.  Frank Rosenblatt: Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms , 1986 .

[4]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[5]  Jeffrey E. Boyd,et al.  Automated diagnosis and image understanding with object extraction, object classification, and inferencing in retinal images , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[6]  Qin Li,et al.  Retinopathy Online Challenge: Automatic Detection of Microaneurysms in Digital Color Fundus Photographs , 2010, IEEE Transactions on Medical Imaging.

[7]  C. Sinthanayothin,et al.  Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images , 1999, The British journal of ophthalmology.

[8]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[9]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[10]  M. Madheswaran,et al.  Extraction of Blood Vascular Network for Development of an Automated Diabetic Retinopathy Screening System , 2009, 2009 International Conference on Computer Technology and Development.

[11]  Roberto Hornero,et al.  Comparison of logistic regression and neural network classifiers in the detection of hard exudates in retinal images , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[12]  T. Batchelder,et al.  The Wisconsin Epidemiologic Study of Diabetic Retinopathy. , 1995, Archives of ophthalmology.

[13]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .