Hard Exudate Detection Using Local Texture Analysis and Gaussian Processes

Exudates are the most noticeable sign in the first stage of diabetic retinopathy. This disease causes about five percent of world blindness. Making use of retinal fundus images, exudates can be detected, which helps the early diagnosis of the pathology. In this work, a novel method for automatic hard exudate detection is presented. After an exhaustive pre-processing step, Local Binary Patterns Variance (LBPV) histograms are used to locally extract texture information. We then use Gaussian Processes to distinguish between healthy and pathological retinal patches. The proposed methodology is validated using the E-OPHTA exudates database. The experimental results demonstrate that Gaussian Process classifiers outperform the current state of the art classifiers for this problem.

[1]  Guy Cazuguel,et al.  TeleOphta: Machine learning and image processing methods for teleophthalmology , 2013 .

[2]  Mariano Alcañiz Raya,et al.  Automatic Detection of Optic Disc Based on PCA and Mathematical Morphology , 2013, IEEE Transactions on Medical Imaging.

[3]  Bunyarit Uyyanonvara,et al.  Machine learning approach to automatic exudate detection in retinal images from diabetic patients , 2010 .

[4]  C. JayaKumari,et al.  Detection of Hard Exudates in Color Fundus Images of the Human Retina , 2012 .

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  Adrián Colomer,et al.  Colour normalization of fundus images based on geometric transformations applied to their chromatic histogram , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[7]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[8]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[9]  Christine Guillemot,et al.  Image Inpainting : Overview and Recent Advances , 2014, IEEE Signal Processing Magazine.

[10]  Guy Cazuguel,et al.  Spatial normalization of eye fundus images , 2012, ISBI 2012.

[11]  G. Parisi,et al.  Statistical Field Theory , 1988 .

[12]  Christopher K. I. Williams,et al.  Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[13]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[14]  Pascale Massin,et al.  A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina , 2002, IEEE Transactions on Medical Imaging.

[15]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

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

[17]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[18]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[19]  Rafael Molina,et al.  Detection and localization of objects in Passive Millimeter Wave Images , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

[20]  Kjersti Engan,et al.  Retinal Disease Screening Through Local Binary Patterns , 2017, IEEE Journal of Biomedical and Health Informatics.

[21]  Zhenhua Guo,et al.  Rotation invariant texture classification using LBP variance (LBPV) with global matching , 2010, Pattern Recognit..

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

[23]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..